LLMs acquire a wide range of abilities during pre-training, but aligning LLMs under Reinforcement Learning with Human Feedback (RLHF) can lead to forgetting pretrained abilities, which is also known as the alignment tax. To investigate alignment tax, we conducted experiments with existing RLHF algorithms using OpenLLaMA-3B, which revealed a pronounced alignment tax in NLP tasks. Whereas, despite various techniques to mitigate forgetting, they are often at odds with the RLHF performance, leading to a trade-off between alignment performance and forgetting mitigation, leading to an alignment-forgetting trade-off. In this paper we show that model averaging, which simply interpolates between pre and post RLHF model weights, surprisingly achieves the most strongest alignment-forgetting Pareto front among a wide range of competing methods. To understand its effectiveness, we offer theoretical insights into model averaging, revealing that it enhances performance Pareto front by increasing feature diversity on the layers where tasks share overlapped feature spaces. Empirical evidence corroborates our analysis by showing the benefits of averaging low-level transformer layers. Building on the analysis and the observation that averaging different layers of the transformer leads to significantly different alignment-forgetting trade-offs, we propose Heterogeneous Model Averaging (HMA) to Heterogeneously find various combination ratios of model layers. HMA seeks to maximize the alignment performance while incurring minimal alignment tax. Moreover, we validate HMA’s performance across a range of RLHF algorithms over OpenLLaMA-3B and further extend our findings to Mistral-7B which is evaluated by open-sourced preference model and GPT4. Code available here.
The dynamic nature of real-world information necessitates knowledge editing (KE) in large language models (LLMs). The edited knowledge should propagate and facilitate the deduction of new information based on existing model knowledge. We term the existing related knowledge in LLM serving as the origination of knowledge propagation as ”deduction anchors”. However, current KE approaches, which only operate on (subject, relation, object) triple. We both theoretically and empirically observe that this simplified setting often leads to uncertainty when determining the deduction anchors, causing low confidence in their answers. To mitigate this issue, we propose a novel task of event-based knowledge editing that pairs facts with event descriptions. This task manifests not only a closer simulation of real-world editing scenarios but also a more logically sound setting, implicitly defining the deduction anchor and enabling LLMs to propagate knowledge confidently. We curate a new benchmark dataset Evedit derived from the CounterFact dataset and validate its superiority in improving model confidence. Moreover, while we observe that the event-based setting is significantly challenging for existing approaches, we propose a novel approach Self-Edit that showcases stronger performance, achieving 55.6% consistency improvement while maintaining the naturalness of generation.
Recent advances in instruction-tuned Large Vision-Language Models (LVLMs) have imbued the models with the ability to generate high-level, image-grounded explanations with ease. While such capability is largely attributed to the rich world knowledge contained within the Large Language Models (LLMs), our work reveals their shortcomings in fine-grained visual categorization (FGVC) across six different benchmark settings. Most recent state-of-the-art LVLMs such as LLaVa-1.5, InstructBLIP and GPT-4V not only severely deteriorate in terms of classification performance, e.g., average drop of 65.58 in EM for Stanford Dogs for LLaVA-1.5, but also struggle to generate descriptive visual attributes based on a concept that appears within an input image despite their prominent zero-shot image captioning ability. In-depth analyses show that instruction-tuned LVLMs suffer from modality gap, showing discrepancy when given textual and visual inputs that correspond to the same concept. In an effort to further the community’s endeavor in this direction, we propose a multiple granularity attribute-centric benchmark and training mixture, Finer, which aims to establish a ground to evaluate LVLMs’ fine-grained visual comprehension ability and provide significantly improved explainability.
Ranking is a fundamental problem in search, however, existing ranking algorithms usually restrict the granularity of ranking to full passages or require a specific dense index for each desired level of granularity. Such lack of flexibility in granularity negatively affects many applications that can benefit from more granular ranking, such as sentence-level ranking for open-domain QA, or proposition-level ranking for attribution. In this work, we introduce the idea of any-granularity ranking which leverages multi-vector embeddings to rank at varying levels of granularity while maintaining encoding at a single (coarser) level of granularity. We propose a multi-granular contrastive loss for training multi-vector approaches and validate its utility with both sentences and propositions as ranking units. Finally, we demonstrate the application of proposition-level ranking to post-hoc citation addition in retrieval-augmented generation, surpassing the performance of prompt-driven citation generation.
Large Language Models (LLMs) have significantly advanced the field of information retrieval, particularly for reranking. Listwise LLM rerankers have showcased superior performance and generalizability compared to existing supervised approaches. However, conventional listwise LLM reranking methods lack efficiency as they provide ranking output in the form of a generated ordered sequence of candidate passage identifiers. Further, they are trained with the typical language modeling objective, which treats all ranking errors uniformly–potentially at the cost of misranking highly relevant passages. Addressing these limitations, we introduce FIRST, a novel listwise LLM reranking approach leveraging the output logits of the first generated identifier to directly obtain a ranked ordering of the candidates. Further, we incorporate a learning-to-rank loss during training, prioritizing ranking accuracy for the more relevant passages. Empirical results demonstrate that FIRST accelerates inference by 50% while maintaining a robust ranking performance with gains across the BEIR benchmark. Finally, to illustrate the practical effectiveness of listwise LLM rerankers, we investigate their application in providing relevance feedback for retrievers during inference. Our results show that LLM rerankers can provide a stronger distillation signal compared to cross-encoders, yielding substantial improvements in retriever recall after relevance feedback.
Extensive previous research has focused on post-training knowledge editing (KE) for language models (LMs) to ensure that knowledge remains accurate and up-to-date. One desired property and open question in KE is to let edited LMs correctly handle ripple effects, where LM is expected to answer its logically related knowledge accurately. In this paper, we answer the question of why most KE methods still create messy ripple effects. We conduct extensive analysis and identify a salient indicator, GradSim, that effectively reveals when and why updated knowledge ripples in LMs. GradSim is computed by the cosine similarity between gradients of the original fact and its related knowledge. We observe a strong positive correlation between ripple effect performance and GradSim across different LMs, KE methods, and evaluation metrics. Further investigations into three counter-intuitive failure cases (Negation, Over-Ripple, Multi-Lingual) of ripple effects demonstrate that these failures are often associated with very low GradSim. This finding validates that GradSim is an effective indicator of when knowledge ripples in LMs.
Recently, enabling pretrained language models (PLMs) to perform zero-shot crossmodal tasks such as video question answering has been extensively studied. A popular approach is to learn a projection network that projects visual features into the input text embedding space of a PLM, as well as feed-forward adaptation layers, with the weights of the PLM frozen. However, is it really necessary to learn such additional layers? In this paper, we make the first attempt to demonstrate that the PLM is able to perform zero-shot crossmodal tasks without any crossmodal pretraining, when the observed visual concepts are injected as both additional input text tokens and augmentation in the intermediate features within each feed-forward network for the PLM. Specifically, inputting observed visual concepts as text tokens helps to inject them through the self-attention layers in the PLM; to augment the intermediate features in a way that is compatible with the PLM, we propose to construct adaptation layers based on the intermediate representation of concepts (obtained by solely inputting them to the PLM). These two complementary injection mechanisms form the proposed Deep Concept Injection, which comprehensively enables the PLM to perceive instantly without crossmodal pretraining. Extensive empirical analysis on zero-shot video question answering, as well as visual question answering, shows Deep Concept Injection achieves competitive or even better results in both zero-shot and fine-tuning settings, compared to state-of-the-art methods that require crossmodal pretraining.
Complex news events, such as natural disasters and socio-political conflicts, require swift responses from the government and society. Relying on historical events to project the future is insufficient as such events are sparse and do not cover all possible conditions and nuanced situations. Simulation of these complex events can help better prepare and reduce the negative impact. We develop a controllable complex news event simulator guided by both the event schema representing domain knowledge about the scenario and user-provided assumptions representing case-specific conditions.As event dynamics depend on the fine-grained social and cultural context, we further introduce a geo-diverse commonsense and cultural norm-aware knowledge enhancement component.To enhance the coherence of the simulation, apart from the global timeline of events,we take an agent-based approach to simulate the individual character states, plans, and actions. By incorporating the schema and cultural norms, our generated simulations achieve much higher coherence and appropriateness and are received favorably by participants from a humanitarian assistance organization.
Recently, large language models (LLMs) have evolved into interactive agents, proficient in planning, tool use, and task execution across various tasks. However, without agent-tuning, open-source models like LLaMA2 currently struggle to match the efficiency of larger models such as GPT-4 in scientific applications due to a lack of agent tuning datasets. In response, we introduce MIMIR, a streamlined platform that leverages large LLMs to generate agent-tuning data for fine-tuning smaller, specialized models. By employing a role-playing methodology, MIMIR enables larger models to simulate various roles and create interaction data, which can then be used to fine-tune open-source models like LLaMA2. This approach ensures that even smaller models can effectively serve as agents in scientific tasks. Integrating these features into an end-to-end platform, MIMIR facilitates everything from the uploading of scientific data to one-click agent fine-tuning. MIMIR is publicly released and actively maintained at https://github. com/gersteinlab/MIMIR, along with a demo video for quick-start, calling for broader development.
Fine-grained few-shot entity extraction in the chemical domain faces two unique challenges. First, compared with entity extraction tasks in the general domain, sentences from chemical papers usually contain more entities. Moreover, entity extraction models usually have difficulty extracting entities of long-tailed types. In this paper, we propose Chem-FINESE, a novel sequence-to-sequence (seq2seq) based few-shot entity extraction approach, to address these two challenges. Our Chem-FINESE has two components: a seq2seq entity extractor to extract named entities from the input sentence and a seq2seq self-validation module to reconstruct the original input sentence from extracted entities. Inspired by the fact that a good entity extraction system needs to extract entities faithfully, our new self-validation module leverages entity extraction results to reconstruct the original input sentence. Besides, we design a new contrastive loss to reduce excessive copying during the extraction process. Finally, we release ChemNER+, a new fine-grained chemical entity extraction dataset that is annotated by domain experts with the ChemNER schema. Experiments in few-shot settings with both ChemNER+ and CHEMET datasets show that our newly proposed framework has contributed up to 8.26% and 6.84% absolute F1-score gains respectively.
Fine-tuning pre-trained language models (LMs) is essential for enhancing their capabilities.Existing techniques commonly fine-tune on input-output pairs (e.g., instruction tuning) or with numerical rewards that gauge the output quality (e.g., RLHF). We explore LMs’ potential to **le**arn from **t**extual **i**nteractions (**LETI**) that not only check their correctness with *binary labels* but also pinpoint and explain errors in their outputs through *textual feedback*.Our focus is the code generation task, where the model produces code based on natural language instructions. This setting invites a natural and scalable way to acquire textual feedback: the error messages and stack traces from code execution using a Python interpreter. LETI iteratively fine-tunes the model, using the LM objective, on a concatenation of natural language instructions, LM-generated programs, and textual feedback. Prepended to this fine-tuning text, a binary reward token is used to differentiate correct and buggy solutions.LETI requires *no* ground-truth outputs for training and even outperforms a fine-tuned baseline that does. LETI not only improves the performance of LMs on a code generation dataset MBPP, but also generalizes to other datasets. Trained on MBPP, it achieves comparable or better performance than the base LMs on unseen problems in HumanEval. Furthermore, compared to binary feedback, we observe that textual feedback leads to improved generation quality and sample efficiency, achieving the same performance with fewer than half of the gradient steps.LETI is equally applicable in natural language tasks when they can be formulated as code generation, which we empirically verified on event argument extraction.
Open-domain Question Answering (OpenQA) aims at answering factual questions with an external large-scale knowledge corpus. However, real-world knowledge is not static; it updates and evolves continually. Such a dynamic characteristic of knowledge poses a vital challenge for these models, as the trained models need to constantly adapt to the latest information to make sure that the answers remain accurate. In addition, it is still unclear how well an OpenQA model can transfer to completely new knowledge domains. In this paper, we investigate the generalization performance of a retrieval-augmented QA model in two specific scenarios: 1) adapting to updated versions of the same knowledge corpus; 2) switching to completely different knowledge domains. We observe that the generalization challenges of OpenQA models stem from the reader’s over-reliance on memorizing the knowledge from the external corpus, which hinders the model from generalizing to a new knowledge corpus. We introduce Corpus-Invariant Tuning (CIT), a simple but effective training strategy, to mitigate the knowledge over-memorization by controlling the likelihood of retrieved contexts during training. Extensive experimental results on multiple OpenQA benchmarks show that CIT achieves significantly better generalizability without compromising the model’s performance in its original corpus and domain.
This paper investigates using Large Language Models (LLMs) to automatically perform web software tasks using click, scroll, and text in- put operations. Previous approaches, such as reinforcement learning (RL) or imitation learning, are inefficient to train and task-specific. Our method uses filtered Document Object Model (DOM) elements as observations and performs tasks step-by-step, sequentially generating small programs based on the current observations. We use in-context learning, either benefiting from a single manually provided example, or an automatically generated example based on a successful zero-shot trial. We evaluate our proposed method on the MiniWob++ benchmark. With only one in-context example, our WebWISE method using gpt-3.5-turbo achieves similar or better performance than other methods that require many demonstrations or trials.
The task of information extraction (IE) is to extract structured knowledge from text. However, it is often not straightforward to utilize IE output due to the mismatch between the IE ontology and the downstream application needs. We propose a new formulation of IE, Text2DB, that emphasizes the integration of IE output and the target database (or knowledge base). Given a user instruction, a document set, and a database, our task requires the model to update the database with values from the document set to satisfy the user instruction. This task requires understanding user instructions for what to extract and adapting to the given DB/KB schema for how to extract on the fly. To evaluate this new task, we introduce a new benchmark featuring common demands such as data infilling, row population, and column addition. In addition, we propose an LLM agent framework OPAL (Observe-Plan-Analyze LLM) which includes an Observer component that interacts with the database, the Planner component that generates a code-based plan with calls to IE models, and the Analyzer component that provides feedback regarding code quality before execution. Experiments show that OPAL can successfully adapt to diverse database schemas by generating different code plans and calling the required IE models. We also highlight difficult cases such as dealing with large databases with complex dependencies and extraction hallucination, which we believe deserve further investigation.
Advances in large vision-language models (LVLMs) have led to significant progress in generating natural language descriptions for visual contents. These powerful models are known for producing texts that are factually inconsistent with the visual input. While some efforts mitigate such inconsistencies in natural image captioning, the factuality of generated captions for structured visuals, such as charts, has not received as much scrutiny. This work introduces a comprehensive typology of factual errors in generated chart captions. A large-scale human annotation effort provides insight into the error patterns in captions generated by various models, ultimately forming the foundation of a dataset, CHOCOLATE. Our analysis reveals that even advanced models like GPT-4V frequently produce captions laced with factual inaccuracies. To combat this, we establish the task of Chart Caption Factual Error Correction and introduce CHARTVE, a visual entailment model that outperforms current LVLMs in evaluating caption factuality. Furthermore, we propose C2TFEC, an interpretable two-stage framework that excels at correcting factual errors. This work inaugurates a new domain in factual error correction for chart captions, presenting a novel evaluation metric, and demonstrating an effective approach to ensuring the factuality of generated chart captions. The code and data as well as the continuously updated benchmark can be found at: https://khuangaf.github.io/CHOCOLATE/.
Event extraction has gained considerable interest due to its wide-ranging applications. However, recent studies draw attention to evaluation issues, suggesting that reported scores may not accurately reflect the true performance. In this work, we identify and address evaluation challenges, including inconsistency due to varying data assumptions or preprocessing steps, the insufficiency of current evaluation frameworks that may introduce dataset or data split bias, and the low reproducibility of some previous approaches. To address these challenges, we present TextEE, a standardized, fair, and reproducible benchmark for event extraction. TextEE comprises standardized data preprocessing scripts and splits for 16 datasets spanning eight diverse domains and includes 14 recent methodologies, conducting a comprehensive benchmark reevaluation. We also evaluate five varied large language models on our TextEE benchmark and demonstrate how they struggle to achieve satisfactory performance. Inspired by our reevaluation results and findings, we discuss the role of event extraction in the current NLP era, as well as future challenges and insights derived from TextEE. We believe TextEE, the first standardized comprehensive benchmarking tool, will significantly facilitate future event extraction research.
Large vision-language models (LVLMs), while proficient in following instructions and responding to diverse questions, invariably generate detailed responses even when questions are ambiguous or unanswerable, leading to hallucinations and bias issues. Thus, it is essential for LVLMs to proactively engage with humans to ask for clarifications or additional information for better responses. In this study, we aim to shift LVLMs from passive answer providers to proactive engaged partners. We begin by establishing a three-tiered hierarchy for questions of invalid, ambiguous, and personalizable nature to measure the proactive engagement capabilities of LVLMs. Utilizing this hierarchy, we create PIE, (ProactIve Engagement Evaluation) through GPT-4o and human annotators, consisting of 853 questions across six distinct, fine-grained question types that are verified by human annotators and accompanied with well-defined metrics. Our evaluations on indicate poor performance of existing LVLMs, with the best-performing open-weights model only achieving an Aggregate Align Rate (AAR) of 0.28. In response, we introduce MACAROON, self-iMaginAtion for ContrAstive pReference OptimizatiON, which instructs LVLMs to autonomously generate contrastive response pairs for unlabeled questions given the task description and human-crafted criteria. Then, the self-imagined data is formatted for conditional reinforcement learning. Experimental results show MACAROON effectively improves LVLMs’ capabilities to be proactively engaged (0.84 AAR) while maintaining comparable performance on general tasks.
LLM-driven dialog systems are used in a diverse set of applications, ranging from healthcare to customer service. However, given their generalization capability, it is difficult to ensure that these chatbots stay within the boundaries of the specialized domains, potentially resulting in inaccurate information and irrelevant responses. This paper introduces an unsupervised approach for automatically inducing domain-specific dialog flows that can be used to constrain LLM-based chatbots. We introduce two variants of dialog flow based on the availability of in-domain conversation instances. Through human and automatic evaluation over 24 dialog domains, we demonstrate that our high-quality data-guided dialog flows achieve better domain coverage, thereby overcoming the need for extensive manual crafting of such flows.
Large Language Models (LLMs) struggle with providing current information due to the outdated pre-training data. Existing methods for updating LLMs, such as knowledge editing and continual fine-tuning, have significant drawbacks in generalizability of new information and the requirements on structured updating corpus. We identify the core challenge behind these drawbacks: the LM-logical discrepancy featuring the difference between language modeling probabilities and logical probabilities. To evaluate and address the core challenge, we propose a new task formulation of the information updating task that only requires the provision of an unstructured updating corpus and evaluates the performance of information updating on the generalizability to question-answer pairs pertaining to the updating information.We further propose a novel and effective pipeline approach for the task, highlighting a self-prompting-based question-answer generation process and a associative distillation methods to bridge the LM-logical discrepancy.We develop two datasets for evaluation, one sourced from news articles published in March and April 2023, and the other from the Natural Questions benchmark.Experimental results demonstrate the superiority of our approach, significantly increasing the factual consistency score (on a scale from 0 to 1) by up to 0.16. Furthermore, our method effectively mitigates forgetting utilizing a compact replay buffer with only 2.3% of the training tokens.
Language-molecule models have emerged as an exciting direction for molecular discovery and understanding. However, training these models is challenging due to the scarcity of molecule-language pair datasets. At this point, datasets have been released which are 1) small and scraped from existing databases, 2) large but noisy and constructed by performing entity linking on the scientific literature, and 3) built by converting property prediction datasets to natural language using templates. In this document, we detail the L+M-24 dataset, which has been created for the Language + Molecules Workshop shared task at ACL 2024. In particular, L+M-24 is designed to focus on three key benefits of natural language in molecule design: compositionality, functionality, and abstraction
Named entity recognition is a key component of Information Extraction (IE), particularly in scientific domains such as biomedicine and chemistry, where large language models (LLMs), e.g., ChatGPT, fall short. We investigate the applicability of transfer learning for enhancing a named entity recognition model trained in the biomedical domain (the source domain) to be used in the chemical domain (the target domain). A common practice for training such a model in a few-shot learning setting is to pretrain the model on the labeled source data, and then, to finetune it on a hand-full of labeled target examples. In our experiments, we observed that such a model is prone to mislabeling the source entities, which can often appear in the text, as the target entities. To alleviate this problem, we propose a model to transfer the knowledge from the source domain to the target domain, but, at the same time, to project the source entities and target entities into separate regions of the feature space. This diminishes the risk of mislabeling the source entities as the target entities. Our model consists of two stages: 1) entity grouping in the source domain, which incorporates knowledge from annotated events to establish relations between entities, and 2) entity discrimination in the target domain, which relies on pseudo labeling and contrastive learning to enhance discrimination between the entities in the two domains. We conduct our extensive experiments across three source and three target datasets, demonstrating that our method outperforms the baselines by up to 5% absolute value. Code, data, and resources are publicly available for research purposes: https://github.com/Lhtie/Bio-Domain-Transfer .
Vision-language models (VLMs) have recently demonstrated strong efficacy as visual assistants that can parse natural queries about the visual content and generate human-like outputs. In this work, we explore the ability of these models to demonstrate human-like reasoning based on the perceived information. To address a crucial concern regarding the extent to which their reasoning capabilities are fully consistent and grounded, we also measure the reasoning consistency of these models. We achieve this by proposing a chain-of-thought (CoT) based consistency measure. However, such an evaluation requires a benchmark that encompasses both high-level inference and detailed reasoning chains, which is costly. We tackle this challenge by proposing an LLM-Human-in-the-Loop pipeline, which notably reduces cost while simultaneously ensuring the generation of a high-quality dataset. Based on this pipeline and the existing coarse-grained annotated dataset, we build the CURE benchmark to measure both the zero-shot reasoning performance and consistency of VLMs. We evaluate existing state-of-the-art VLMs, and find that even the best-performing model is unable to demonstrate strong visual reasoning capabilities and consistency, indicating that substantial efforts are required to enable VLMs to perform visual reasoning as systematically and consistently as humans. As an early step, we propose a two-stage training framework aimed at improving both the reasoning performance and consistency of VLMs. The first stage involves employing supervised fine-tuning of VLMs using step-by-step reasoning samples automatically generated by LLMs. In the second stage, we further augment the training process by incorporating feedback provided by LLMs to produce reasoning chains that are highly consistent and grounded. We empirically highlight the effectiveness of our framework in both reasoning performance and consistency.
Human intelligence thrives on cognitive synergy, where collaboration among different minds yield superior outcomes compared to isolated individuals. In this work, we propose Solo Performance Prompting (SPP), which transforms a single LLM into a cognitive synergist by engaging in multi-turn self-collaboration with multiple personas. A cognitive synergist is an intelligent agent that collaboratively combines multiple minds’ strengths and knowledge to enhance problem-solving in complex tasks. By dynamically identifying and simulating different personas based on task inputs, SPP unleashes the potential of cognitive synergy in LLMs. Our in-depth analysis shows that assigning multiple fine-grained personas in LLMs improves problem-solving abilities compared to using a single or fixed number of personas. We evaluate SPP on three challenging tasks: Trivia Creative Writing, Codenames Collaborative, and Logic Grid Puzzle, encompassing both knowledge-intensive and reasoning-intensive types. Unlike previous works, such as Chain-of-Thought, that solely enhance the reasoning abilities in LLMs, experimental results demonstrate that SPP effectively reduces factual hallucination, and maintains strong reasoning capabilities. Additionally, comparative experiments show that cognitive synergy only emerges in GPT-4 and does not appear in less capable models, such as GPT-3.5-turbo and Llama2-13b-chat, which draws an interesting analogy to human development. Code, data, and prompts can be found at: https://github.com/MikeWangWZHL/Solo-Performance-Prompting.git.
Evaluating the veracity of everyday claims is time consuming and in some cases requires domain expertise. We empirically demonstrate that the commonly used fact checking pipeline, known as the retriever-reader, suffers from performance deterioration when it is trained on the labeled data from one domain and used in another domain. Afterwards, we delve into each component of the pipeline and propose novel algorithms to address this problem. We propose an adversarial algorithm to make the retriever component robust against distribution shift. Our core idea is to initially train a bi-encoder on the labeled source data, and then, to adversarially train two separate document and claim encoders using unlabeled target data. We then focus on the reader component and propose to train it such that it is insensitive towards the order of claims and evidence documents. Our empirical evaluations support the hypothesis that such a reader shows a higher robustness against distribution shift. To our knowledge, there is no publicly available multi-topic fact checking dataset. Thus, we propose a simple automatic method to re-purpose two well-known fact checking datasets. We then construct eight fact checking scenarios from these datasets, and compare our model to a set of strong baseline models, including recent domain adaptation models that use GPT4 for generating synthetic data.
Today’s large language models (LLMs) typically train on short text segments (e.g., <4K tokens) due to the quadratic complexity of their Transformer architectures. As a result, their performance suffers drastically on inputs longer than those encountered during training, substantially limiting their applications in real-world tasks involving long contexts such as encod- ing scientific articles, code repositories, or long dialogues. Through both theoretical analysis and empirical investigation, this work identifies three major factors contributing to this length generalization failure. Our theoretical analysis reveals that commonly used techniques like using a sliding-window attention pattern or relative positional encodings are inadequate to address them. Answering these challenges, we propose LM-Infinite, a simple and effective method for enhancing LLMs’ capabilities of handling long contexts. LM-Infinite is highly flexible and can be used with most modern LLMs off-the-shelf. Without any parameter updates, it allows LLMs pre-trained with 2K or 4K-long segments to generalize to up to 200M length inputs while retaining perplexity. It also improves performance on downstream tasks such as Passkey Retrieval and Qasper in the zero-shot setting. LM-Infinite brings substantial efficiency improvements: it achieves 2.7× decoding speed up and 7.5× memory saving over the original model. Our code will be publicly available upon publication.
Large language models (LLMs) have revolutionized numerous domains with their impressive performance but still face their challenges. A predominant issue is the propensity for these models to generate non-existent facts, a concern termed hallucination. Our research is motivated by the observation that previous instruction tuning methods force the model to complete a sentence no matter whether the model knows the knowledge or not. When the question is out of the parametric knowledge, it will try to make up something and fail to indicate when it lacks knowledge. In this paper, we present a new approach called Refusal-Aware Instruction Tuning (R-Tuning). This approach is formalized by first identifying the disparity in knowledge encompassed by pre-trained parameters compared to that of instruction tuning data. Then, we construct the refusal-aware data based on the knowledge intersection, to tune LLMs to refrain from responding to questions beyond its parametric knowledge. Experimental results demonstrate R-Tuning effectively improves a model’s ability to answer known questions and refrain from answering unknown questions. Furthermore, when tested on out-of-domain datasets, the refusal ability was found to be a meta-skill that could be generalized to other tasks. Further analysis surprisingly finds that learning the uncertainty results in better calibration and an improved ability to estimate the uncertainty than uncertainty-based testing. Our code is available at https://github.com/shizhediao/R-Tuning
In Multimodal Language Models (MLMs), the cost of manually annotating high-quality image-text pair data for fine-tuning and alignment is extremely high. While existing multimodal data augmentation frameworks propose ways to augment image-text pairs, they either suffer from semantic inconsistency between texts and images, or generate unrealistic images, causing knowledge gap with real world examples. To address these issues, we propose Attribute-based Multimodal Data Augmentation (ARMADA), a novel multimodal data augmentation method via knowledge-guided manipulation of visual attributes of the mentioned entities. Specifically, we extract entities and their visual attributes from the original text data, then search for alternative values for the visual attributes under the guidance of knowledge bases (KBs) and large language models (LLMs). We then utilize an image-editing model to edit the images with the extracted attributes. ARMADA is a novel multimodal data generation framework that: (i) extracts knowledge-grounded attributes from symbolic KBs for semantically consistent yet distinctive image-text pair generation, (ii) generates visually similar images of disparate categories using neighboring entities in the KB hierarchy, and (iii) uses the commonsense knowledge of LLMs to modulate auxiliary visual attributes such as backgrounds for more robust representation of original entities. Our empirical results over four downstream tasks demonstrate the efficacy of our framework to produce high-quality data and enhance the model performance. This also highlights the need to leverage external knowledge proxies for enhanced interpretability and real-world grounding.
Climate change, access to food and water, pandemics–the world faces an enormous number of problems in the coming decades on scales of complexity never-before-seen. To address these issues, development of scientific solutions which are scalable, flexible, and inexpensive are critical. Over the last couple years, considerable interest has arisen for applying natural language-driven solutions to these problems. Particularly, the chemistry field is posed to be substantially accelerated by language+molecule models. This tutorial is designed to provide an introduction to this area of research. It requires no knowledge outside mainstream NLP, and it will enable participants to begin exploring relevant research. By discussing cutting-edge work, we will highlight the key roles language can fill for 1) abstract, compositional control of generative models, 2) bridging different biochemical modalities, 3) planning experimental procedures, and 4) broadening access to computational approaches. Beyond this, language models have also seen considerable success when applied to proteins or molecule structures, which can be considered as ‘exotic’ languages, and computational linguistics researchers’ expertise can be highly valuable for these impactful, possibly life-saving tasks.
We explore and enhance the ability of neural language models to generate novel scientific directions grounded in literature. Work on literature-based hypothesis generation has traditionally focused on binary link prediction—severely limiting the expressivity of hypotheses. This line of work also does not focus on optimizing novelty. We take a dramatic departure with a novel setting in which models use as input background contexts (e.g., problems, experimental settings, goals), and output natural language ideas grounded in literature. We present SciMON, a modeling framework that uses retrieval of “inspirations” from past scientific papers, and explicitly optimizes for novelty by iteratively comparing to prior papers and updating idea suggestions until sufficient novelty is achieved. Comprehensive evaluations reveal that GPT-4 tends to generate ideas with overall low technical depth and novelty, while our methods partially mitigate this issue. Our work represents a first step toward evaluating and developing language models that generate new ideas derived from the scientific literature. Code, data, and resources are publicly available for research purposes: https://github.com/eaglew/clbd.
Extraction of experimental procedures from human language in scientific literature and patents into actionable sequences in robotics language holds immense significance in scientific domains. Such an action extraction task is particularly challenging given the intricate details and context-dependent nature of the instructions, especially in fields like chemistry where reproducibility is paramount. In this paper, we introduce ActionIE, a method that leverages Large Language Models (LLMs) to bridge this divide by converting actions written in natural language into executable Python code. This enables us to capture the entities of interest, and the relationship between each action, given the features of Programming Languages. Utilizing linguistic cues identified by frequent patterns, ActionIE provides an improved mechanism to discern entities of interest. While our method is broadly applicable, we exemplify its power in the domain of chemical literature, wherein we focus on extracting experimental procedures for chemical synthesis. The code generated by our method can be easily transformed into robotics language which is in high demand in scientific fields. Comprehensive experiments demonstrate the superiority of our method. In addition, we propose a graph-based metric to more accurately reflect the precision of extraction. We also develop a dataset to address the scarcity of scientific literature occurred in existing datasets.
Language models (LMs) automatically learn word embeddings during pre-training on language corpora. Although word embeddings are usually interpreted as feature vectors for individual words, their roles in language model generation remain underexplored. In this work, we theoretically and empirically revisit output word embeddings and find that their linear transformations are equivalent to steering language model generation styles. We name such steers LM-Steers and find them existing in LMs of all sizes. It requires learning parameters equal to 0.2% of the original LMs’ size for steering each style. On tasks such as language model detoxification and sentiment control, LM-Steers can achieve comparable or superior performance compared with state-of-the-art controlled generation methods while maintaining a better balance with generation quality. The learned LM-Steer serves as a lens in text styles: it reveals that word embeddings are interpretable when associated with language model generations and can highlight text spans that most indicate the style differences. An LM-Steer is transferrable between different language models by an explicit form calculation. One can also continuously steer LMs simply by scaling the LM-Steer or compose multiple LM-Steers by adding their transformations. Our codes are publicly available at https://github.com/Glaciohound/LM-Steer.
This paper introduces a novel problem of automated question generation for courtroom examinations, CourtQG. While question generation has been studied in domains such as educational testing and product description, CourtQG poses several unique challenges owing to its non-cooperative and agenda-driven nature. Specifically, not only the generated questions need to be relevant to the case and underlying context, they also have to achieve certain objectives such as challenging the opponent’s arguments and/or revealing potential inconsistencies in their answers. We propose to leverage large language models (LLM) for CourtQG by fine-tuning them on two auxiliary tasks, agenda explanation (i.e., uncovering the underlying intents) and question type prediction. We additionally propose cold-start generation of questions from background documents without relying on examination history. We construct a dataset to evaluate our proposed method and show that it generates better questions according to standard metrics when compared to several baselines.
Event extraction is a crucial task for semantic understanding and structured knowledge construction. However, the expense of collecting and labeling data for training event extraction models is usually high. To address this issue, we propose a novel schema-based data augmentation method that utilizes event schemas to guide the data generation process. The event schemas depict the typical patterns of complex events and can be used to create new synthetic data for event extraction. Specifically, we sub-sample from the schema graph to obtain a subgraph, instantiate the schema subgraph, and then convert the instantiated subgraph to natural language texts. We conduct extensive experiments on event trigger detection, event trigger extraction, and event argument extraction tasks using two datasets (including five scenarios). The experimental results demonstrate that our proposed data-augmentation method produces high-quality generated data and significantly enhances the model performance, with up to 12% increase in F1 score compared to baseline methods.
Due to the rapid growth of publications varying in quality, there exists a pressing need to help scientists digest and evaluate relevant papers, thereby facilitating scientific discovery. This creates a number of urgent questions; however, computer-human collaboration in the scientific paper lifecycle is still in the exploratory stage and lacks a unified framework for analyzing the relevant tasks. Additionally, with the recent significant success of large language models (LLMs), they have increasingly played an important role in academic writing. In this cutting-edge tutorial, we aim to provide an all-encompassing overview of the paper lifecycle, detailing how machines can augment every stage of the research process for the scientist, including scientific literature understanding, experiment development, manuscript draft writing, and finally draft evaluation. This tutorial is devised for researchers interested in this rapidly-developing field of NLP-augmented paper writing. The tutorial will also feature a session of hands-on exercises during which participants can guide machines in generating ideas and automatically composing key paper elements. Furthermore, we will address current challenges, explore future directions, and discuss potential ethical issues. A toolkit designed for human-computer collaboration throughout the paper lifecycle will also be made publically available.
We describe our submission to SemEval 2023 Task 3, specifically the subtask on persuasion technique detection. In this work, our team NLUBot101 tackled a novel task of classifying persuasion techniques in online news articles at a paragraph level. The low-resource multilingual datasets, along with the imbalanced label distribution, make this task challenging. Our team presented a cross-lingual data augmentation approach and leveraged a recently proposed multilingual natural language inference model to address these challenges. Our solution achieves the highest macro-F1 score for the English task, and top 5 micro-F1 scores on both the English and Russian leaderboards.
Pre-trained language models (PLMs) may fail in giving reliable estimates of their predictive uncertainty. We take a close look into this problem, aiming to answer two questions: (1) Do PLMs learn to become calibrated in the training process? (2) How effective are existing calibration methods? For the first question, we conduct fine-grained control experiments to study the dynamic change in PLMs’ calibration performance in training. We consider six factors as control variables, including dataset difficulty, available training samples, training steps, the number of tunable parameters, model scale, and pretraining. We observe a consistent change in calibration performance across six factors. We find that PLMs don’t learn to become calibrated in training, evidenced by the continual increase in confidence, no matter whether the predictions are correct or not. We highlight that our finding somewhat contradicts two established conclusions: (a) Larger PLMs are more calibrated; (b) Pretraining improves model calibration. Next, we study the effectiveness of existing calibration methods in mitigating the overconfidence issue. Besides unlearnable calibration methods (e.g., label smoothing), we adapt and extend two recently proposed learnable methods that directly collect data to train models to have reasonable confidence estimations. Experimental results show that learnable methods significantly reduce PLMs’ confidence in wrong predictions.
Large Language Model (LLM) trained on a mixture of text and code has demonstrated impressive capability in translating natural language (NL) into structured code. We observe that semantic structures can be conveniently translated into code and propose Code4Struct to leverage such text-to-structure translation capability to tackle structured prediction tasks. As a case study, we formulate Event Argument Extraction (EAE) as converting text into event-argument structures that can be represented as a class object using code. This alignment between structures and code enables us to take advantage of Programming Language (PL) features such as inheritance and type annotation to introduce external knowledge or add constraints. We show that, with sufficient in-context examples, formulating EAE as a code generation problem is advantageous over using variants of text-based prompts. Despite only using 20 training event instances for each event type, Code4Struct is comparable to supervised models trained on 4,202 instances and outperforms current state-of-the-art (SOTA) trained on 20-shot data by 29.5% absolute F1. Code4Struct can use 10-shot training data from a sibling event type to predict arguments for zero-resource event types and outperforms the zero-shot baseline by 12% absolute F1.
Existing bias mitigation methods require social-group-specific word pairs (e.g., “man” – “woman”) for each social attribute (e.g., gender), restricting the bias mitigation to only one specified social attribute. Further, this constraint renders such methods impractical and costly for mitigating bias in understudied and/or unmarked social groups. We propose that the Stereotype Content Model (SCM) — a theoretical framework developed in social psychology for understanding the content of stereotyping — can help debiasing efforts to become social-group-agnostic by capturing the underlying connection between bias and stereotypes. SCM proposes that the content of stereotypes map to two psychological dimensions of warmth and competence. Using only pairs of terms for these two dimensions (e.g., warmth: “genuine” – “fake”; competence: “smart” – “stupid”), we perform debiasing with established methods on both pre-trained word embeddings and large language models. We demonstrate that our social-group-agnostic, SCM-based debiasing technique performs comparably to group-specific debiasing on multiple bias benchmarks, but has theoretical and practical advantages over existing approaches.
Online resources such as WikiHow compile a wide range of scripts for performing everyday tasks, which can assist models in learning to reason about procedures. However, the scripts are always presented in a linear manner, which does not reflect the flexibility displayed by people executing tasks in real life. For example, in the CrossTask Dataset, 64.5% of consecutive step pairs are also observed in the reverse order, suggesting their ordering is not fixed. In addition, each step has an average of 2.56 frequent next steps, demonstrating “branching”. In this paper, we propose the new challenging task of non-sequential graph script induction, aiming to capture optional and interchangeable steps in procedural planning. To automate the induction of such graph scripts for given tasks, we propose to take advantage of loosely aligned videos of people performing the tasks. In particular, we design a multimodal framework to ground procedural videos to WikiHow textual steps and thus transform each video into an observed step path on the latent ground truth graph script. This key transformation enables us to train a script knowledge model capable of both generating explicit graph scripts for learnt tasks and predicting future steps given a partial step sequence. Our best model outperforms the strongest pure text/vision baselines by 17.52% absolute gains on F1@3 for next step prediction and 13.8% absolute gains on Acc@1 for partial sequence completion. Human evaluation shows our model outperforming the WikiHow linear baseline by 48.76% absolute gains in capturing sequential and non-sequential step relationships.
Faithfully correcting factual errors is critical for maintaining the integrity of textual knowledge bases and preventing hallucinations in sequence-to-sequence models. Drawing on humans’ ability to identify and correct factual errors, we present a zero-shot framework that formulates questions about input claims, looks for correct answers in the given evidence, and assesses the faithfulness of each correction based on its consistency with the evidence. Our zero-shot framework outperforms fully-supervised approaches, as demonstrated by experiments on the FEVER and SciFact datasets, where our outputs are shown to be more faithful. More importantly, the decomposability nature of our framework inherently provides interpretability. Additionally, to reveal the most suitable metrics for evaluating factual error corrections, we analyze the correlation between commonly used metrics with human judgments in terms of three different dimensions regarding intelligibility and faithfulness.
Event schemas are a form of world knowledge about the typical progression of events. Recent methods for event schema induction use information extraction systems to construct a large number of event graph instances from documents, and then learn to generalize the schema from such instances. In contrast, we propose to treat event schemas as a form of commonsense knowledge that can be derived from large language models (LLMs). This new paradigm greatly simplifies the schema induction process and allows us to handle both hierarchical relations and temporal relations between events in a straightforward way. Since event schemas have complex graph structures, we design an incremental prompting and verification method IncPrompt to break down the construction of a complex event graph into three stages: event skeleton construction, event expansion, and event-event relation verification. Compared to directly using LLMs to generate a linearized graph, IncSchema can generate large and complex schemas with 7.2% F1 improvement in temporal relations and 31.0% F1 improvement in hierarchical relations. In addition, compared to the previous state-of-the-art closed-domain schema induction model, human assessors were able to cover ~10% more events when translating the schemas into coherent stories and rated our schemas 1.3 points higher (on a 5-point scale) in terms of readability.
With emerging online topics as a source for numerous new events, detecting unseen / rare event types presents an elusive challenge for existing event detection methods, where only limited data access is provided for training. To address the data scarcity problem in event detection, we propose MetaEvent, a meta learning-based framework for zero- and few-shot event detection. Specifically, we sample training tasks from existing event types and perform meta training to search for optimal parameters that quickly adapt to unseen tasks. In our framework, we propose to use the cloze-based prompt and a trigger-aware soft verbalizer to efficiently project output to unseen event types. Moreover, we design a contrastive meta objective based on maximum mean discrepancy (MMD) to learn class-separating features. As such, the proposed MetaEvent can perform zero-shot event detection by mapping features to event types without any prior knowledge. In our experiments, we demonstrate the effectiveness of MetaEvent in both zero-shot and few-shot scenarios, where the proposed method achieves state-of-the-art performance in extensive experiments on benchmark datasets FewEvent and MAVEN.
Despite recent advances in detecting fake news generated by neural models, their results are not readily applicable to effective detection of human-written disinformation. What limits the successful transfer between them is the sizable gap between machine-generated fake news and human-authored ones, including the notable differences in terms of style and underlying intent. With this in mind, we propose a novel framework for generating training examples that are informed by the known styles and strategies of human-authored propaganda. Specifically, we perform self-critical sequence training guided by natural language inference to ensure the validity of the generated articles, while also incorporating propaganda techniques, such as appeal to authority and loaded language. In particular, we create a new training dataset, PropaNews, with 2,256 examples, which we release for future use. Our experimental results show that fake news detectors trained on PropaNews are better at detecting human-written disinformation by 3.62–7.69% F1 score on two public datasets.
Predicting how a user responds to news events enables important applications such as allowing intelligent agents or content producers to estimate the effect on different communities and revise unreleased messages to prevent unexpected bad outcomes such as social conflict and moral injury. We present a new task, Response Forecasting on Personas for News Media, to estimate the response a persona (characterizing an individual or a group) might have upon seeing a news message. Compared to the previous efforts which only predict generic comments to news, the proposed task not only introduces personalization in the modeling but also predicts the sentiment polarity and intensity of each response. This enables more accurate and comprehensive inference on the mental state of the persona. Meanwhile, the generated sentiment dimensions make the evaluation and application more reliable. We create the first benchmark dataset, which consists of 13,357 responses to 3,847 news headlines from Twitter. We further evaluate the SOTA neural language models with our dataset. The empirical results suggest that the included persona attributes are helpful for the performance of all response dimensions. Our analysis shows that the best-performing models are capable of predicting responses that are consistent with the personas, and as a byproduct, the task formulation also enables many interesting applications in the analysis of social network groups and their opinions, such as the discovery of extreme opinion groups.
Schema induction builds a graph representation explaining how events unfold in a scenario. Existing approaches have been based on information retrieval (IR) and information extraction (IE), often with limited human curation. We demonstrate a human-in-the-loop schema induction system powered by GPT-3. We first describe the different modules of our system, including prompting to generate schematic elements, manual edit of those elements, and conversion of those into a schema graph. By qualitatively comparing our system to previous ones, we show that our system not only transfers to new domains more easily than previous approaches, but also reduces efforts of human curation thanks to our interactive interface.
Recent research in cross-lingual learning has found that combining large-scale pretrained multilingual language models with machine translation can yield good performance. We explore this idea for cross-lingual event extraction with a new model architecture that jointly encodes a source language input sentence with its translation to the target language during training, and takes a target language sentence with its translation back to the source language as input during evaluation. However, we observe significant representational gap between the native source language texts during training and the texts translated into source language during evaluation, as well as the texts translated into target language during training and the native target language texts during evaluation. This representational gap undermines the effectiveness of cross-lingual transfer learning for event extraction with machine-translated data. In order to mitigate this problem, we propose an adversarial training framework that encourages the language model to produce more similar representations for the translated text and the native text. To be specific, we train the language model such that its hidden representations are able to fool a jointly trained discriminator that distinguishes translated texts’ representations from native texts’ representations. We conduct experiments on cross-lingual for event extraction across three languages. Results demonstrate that our proposed adversarial training can effectively incorporate machine translation to improve event extraction, while simply adding machine-translated data yields unstable performance due to the representational gap.
Goal-oriented generative script learning aims to generate subsequent steps to reach a particular goal, which is an essential task to assist robots or humans in performing stereotypical activities. An important aspect of this process is the ability to capture historical states visually, which provides detailed information that is not covered by text and will guide subsequent steps. Therefore, we propose a new task, Multimedia Generative Script Learning, to generate subsequent steps by tracking historical states in both text and vision modalities, as well as presenting the first benchmark containing 5,652 tasks and 79,089 multimedia steps. This task is challenging in three aspects: the multimedia challenge of capturing the visual states in images, the induction challenge of performing unseen tasks, and the diversity challenge of covering different information in individual steps. We propose to encode visual state changes through a selective multimedia encoder to address the multimedia challenge, transfer knowledge from previously observed tasks using a retrieval-augmented decoder to overcome the induction challenge, and further present distinct information at each step by optimizing a diversity-oriented contrastive learning objective. We define metrics to evaluate both generation and inductive quality. Experiment results demonstrate that our approach significantly outperforms strong baselines.
Building cross-model intelligence that can understand charts and communicate the salient information hidden behind them is an appealing challenge in the vision and language (V+L) community. The capability to uncover the underlined table data of chart figures is a critical key to automatic chart understanding. We introduce ChartT5, a V+L model that learns how to interpret table information from chart images via cross-modal pre-training on plot table pairs. Specifically, we propose two novel pre-training objectives: Masked Header Prediction (MHP) and Masked Value Prediction (MVP) to facilitate the model with different skills to interpret the table information. We have conducted extensive experiments on chart question answering and chart summarization to verify the effectiveness of the proposed pre-training strategies. In particular, on the ChartQA benchmark, our ChartT5 outperforms the state-of-the-art non-pretraining methods by over 8% performance gains.
Procedure planning, or the ability to predict a series of steps that can achieve a given goal conditioned on the current observation, is critical for building intelligent embodied agents that can assist users in everyday tasks. Encouraged by the recent success of language models (LMs) for zero-shot and few-shot planning, we hypothesize that LMs may be equipped with stronger priors for planning compared to their visual counterparts. To this end, we propose a language-first procedure planning framework with a modularized design: we first align the current and goal observations with corresponding steps and then use a pre-trained LM to predict the intermediate steps. Under this framework, we find that using an image captioning model for alignment can already match state-of-the-art performance and by designing a double retrieval model conditioned over current and goal observations jointly, we can achieve large improvements (19.2%-98.9% relatively higher success rate than state-of-the-art) on both COIN and CrossTask benchmarks. Our work verifies the planning ability of LMs and demonstrates how LMs can serve as a powerful “reasoning engine” even when the input is provided in another modality.
Although large language models have exhibited impressive zero-shot ability, the huge model size generally incurs high cost. Recently, semi-parametric language models, which augment a smaller language model with retrieved related background knowledge, alleviate the need for storing everything into the model parameters. Although existing semi-parametric language models have demonstrated promising language modeling capabilities, it remains unclear whether they can exhibit competitive zero-shot abilities as their fully-parametric counterparts. In this work, we introduce Zemi, a semi-parametric language model for zero-shot task generalization. To our best knowledge, this is the first semi-parametric language model that can demonstrate strong zero-shot performance on a wide range of held-out unseen tasks. We train Zemi with semi-parametric multitask training, which shows significant improvement compared with the parametric multitask training as proposed by T0. Specifically, during both training and inference, Zemi is equipped with a retrieval system based on the unlabeled pretraining corpus of our backbone model. To address the unique challenges from large-scale retrieval, we further propose a novel retrieval-augmentation fusion module that can effectively incorporate noisy retrieved documents. Finally, we show detailed analysis and ablation studies on the key ingredients towards building effective zero-shot semi-parametric language models. Notably, our proposed Zemi_Large model outperforms T0-3B by 16% across seven diverse evaluation tasks while being 3.8x smaller in scale.
Recent research has shown that large-scale pretrained language models, specifically transformers, tend to exhibit issues relating to racism, sexism, religion bias, and toxicity in general. Unfortunately, these pretrained language models are used almost universally in downstream tasks, and natural language processing is often applied to make real-world predictions. Thus, debiasing these language models as early in development as possible is increasingly crucial for preventing unintentional harms caused by natural language systems. To this end, we propose a new technique called partitioned contrastive gradient unlearning (PCGU), a gray-box method for debiasing pretrained masked language models. PCGU aims to optimize only the weights that contribute most to a specific domain of bias, doing so by computing a first-order approximation based on the gradients of contrastive sentence pairs. Our experiments show that PCGU is both low-cost and seems particularly effective at pinpointing the sources of implicit social bias in large pretrained transformers. Although we train using PCGU in the gender-profession domain only, we find that doing so can also partially mitigate bias across other domains. All code for our implementation and experiments can be found at https://github.com/CharlesYu2000/PCGU-UnlearningBias.
Existing factual consistency evaluation approaches for text summarization provide binary predictions and limited insights into the weakness of summarization systems. Therefore, we propose the task of fine-grained inconsistency detection, the goal of which is to predict the fine-grained types of factual errors in a summary. Motivated by how humans inspect factual inconsistency in summaries, we propose an interpretable fine-grained inconsistency detection model, FineGrainFact, which explicitly represents the facts in the documents and summaries with semantic frames extracted by semantic role labeling, and highlights the related semantic frames to predict inconsistency. The highlighted semantic frames help verify predicted error types and correct inconsistent summaries. Experiment results demonstrate that our model outperforms strong baselines and provides evidence to support or refute the summary.
Open-vocabulary state tracking is a more practical version of state tracking that aims to track state changes of entities throughout a process without restricting the state space and entity space. OpenPI (Tandon et al., 2020) is to date the only dataset annotated for open-vocabulary state tracking. However, we identify issues with the dataset quality and evaluation metric. For the dataset, we categorize 3 types of problems on the procedure level, step level and state change level respectively, and build a clean dataset OpenPI-C using multiple rounds of human judgment. For the evaluation metric, we propose a cluster-based metric to fix the original metric’s preference for repetition. Model-wise, we enhance the seq2seq generation baseline by reinstating two key properties for state tracking: temporal dependency and entity awareness. The state of the world after an action is inherently dependent on the previous state. We model this dependency through a dynamic memory bank and allow the model to attend to the memory slots during decoding. On the other hand, the state of the world is naturally a union of the states of involved entities. Since the entities are unknown in the open-vocabulary setting, we propose a two-stage model that refines the state change prediction conditioned on entities predicted from the first stage. Empirical results show the effectiveness of our proposed model, especially on the cleaned dataset and the cluster-based metric. The code and data are released at https://github.com/shirley-wu/openpi-c
Humans can classify data of an unseen category by reasoning on its language explanations. This ability is owing to the compositional nature of language: we can combine previously seen attributes to describe the new category. For example, we might describe a sage thrasher as “it has a slim straight relatively short bill, yellow eyes and a long tail”, so that others can use their knowledge of attributes “slim straight relatively short bill”, “yellow eyes” and “long tail” to recognize a sage thrasher. Inspired by this observation, in this work we tackle zero-shot classification task by logically parsing and reasoning on natural language explanations. To this end, we propose the framework CLORE (Classification by LOgical Reasoning on Explanations). While previous methods usually regard textual information as implicit features, CLORE parses explanations into logical structures and then explicitly reasons along this structure on the input to produce a classification score. Experimental results on explanation-based zero-shot classification benchmarks demonstrate that CLORE is superior to baselines, which we show is mainly due to higher scores on tasks requiring more logical reasoning. We also demonstrate that our framework can be extended to zero-shot classification on visual modality. Alongside classification decisions, CLORE can provide the logical parsing and reasoning process as a clear form of rationale. Through empirical analysis we demonstrate that CLORE is also less affected by linguistic biases than baselines.
Textual adversarial attacks can discover models’ weaknesses by adding semantic-preserved but misleading perturbations to the inputs. The long-lasting adversarial attack-and-defense arms race in Natural Language Processing (NLP) is algorithm-centric, providing valuable techniques for automatic robustness evaluation. However, the existing practice of robustness evaluation may exhibit issues of incomprehensive evaluation, impractical evaluation protocol, and invalid adversarial samples. In this paper, we aim to set up a unified automatic robustness evaluation framework, shifting towards model-centric evaluation to further exploit the advantages of adversarial attacks. To address the above challenges, we first determine robustness evaluation dimensions based on model capabilities and specify the reasonable algorithm to generate adversarial samples for each dimension. Then we establish the evaluation protocol, including evaluation settings and metrics, under realistic demands. Finally, we use the perturbation degree of adversarial samples to control the sample validity. We implement a toolkit RobTest that realizes our automatic robustness evaluation framework. In our experiments, we conduct a robustness evaluation of RoBERTa models to demonstrate the effectiveness of our evaluation framework, and further show the rationality of each component in the framework.
Pre-trained language models (PLMs) serve as backbones for various real-world systems. For high-stake applications, it’s equally essential to have reasonable confidence estimations in predictions. While the vanilla confidence scores of PLMs can already be effectively utilized, PLMs consistently become overconfident in their wrong predictions, which is not desirable in practice. Previous work shows that introducing an extra calibration task can mitigate this issue. The basic idea involves acquiring additional data to train models in predicting the confidence of their initial predictions. However, it only demonstrates the feasibility of this kind of method, assuming that there are abundant extra available samples for the introduced calibration task. In this work, we consider the practical scenario that we need to effectively utilize training samples to make PLMs both task-solvers and self-calibrators. Three challenges are presented, including limited training samples, data imbalance, and distribution shifts. We first conduct pilot experiments to quantify various decisive factors in the calibration task. Based on the empirical analysis results, we propose a training algorithm LM-TOAST to tackle the challenges. Experimental results show that LM-TOAST can effectively utilize the training data to make PLMs have reasonable confidence estimations while maintaining the original task performance. Further, we consider three downstream applications, namely selective classification, adversarial defense, and model cascading, to show the practical usefulness of LM-TOAST.
Open-domain dialog involves generating search queries that help obtain relevant knowledge for holding informative conversations. However, it can be challenging to determine what information to retrieve when the user is passive and does not express a clear need or request. To tackle this issue, we present a novel approach that focuses on generating internet search queries that are guided by social commonsense. Specifically, we leverage a commonsense dialog system to establish connections related to the conversation topic, which subsequently guides our query generation. Our proposed framework addresses passive user interactions by integrating topic tracking, commonsense response generation and instruction-driven query generation. Through extensive evaluations, we show that our approach overcomes limitations of existing query generation techniques that rely solely on explicit dialog information, and produces search queries that are more relevant, specific, and compelling, ultimately resulting in more engaging responses.
Large Language Models (LLMs) have made significant progress in utilizing tools, but their ability is limited by API availability and the instability of implicit reasoning, particularly when both planning and execution are involved. To overcome these limitations, we propose CREATOR, a novel framework that enables LLMs to create their own tools using documentation and code realization. CREATOR disentangles abstract tool creation and concrete decision execution, resulting in improved performance. We evaluate CREATOR on MATH and TabMWP benchmarks, respectively consisting of challenging math competition problems and diverse tabular contents. Remarkably, CREATOR outperforms existing chain-of-thought, program-of-thought, and tool-using baselines. Additionally, we introduce the Creation Challenge dataset, featuring 2K diverse questions, to emphasize the necessity and benefits of LLMs’ tool creation ability. Further research demonstrates that leveraging LLMs as tool creators facilitates knowledge transfer, and LLMs exhibit varying levels of tool creation abilities, enabling them to adapt to diverse situations. The tool creation ability revolutionizes the LLM’s problem-solving paradigm, driving us closer to the next frontier of artificial intelligence.
Discovering novel catalysts requires complex reasoning involving multiple chemical properties and resultant trade-offs, leading to a combinatorial growth in the search space. While large language models (LLM) have demonstrated novel capabilities for chemistry through complex instruction following capabilities and high quality reasoning, a goal-driven combinatorial search using LLMs has not been explored in detail. In this work, we present a Monte Carlo Tree Search-based approach that improves beyond state-of-the-art chain-of-thought prompting variants to augment scientific reasoning. We introduce two new reasoning datasets: 1) a curation of computational chemistry simulations, and 2) diverse questions written by catalysis researchers for reasoning about novel chemical conversion processes. We improve over the best baseline by 25.8% and find that our approach can augment scientist’s reasoning and discovery process with novel insights.
The dominance of proprietary LLMs has led to restricted access and raised information privacy concerns. The SoTA open-source alternatives are crucial for information-sensitive and high-volume applications but often lag behind in performance. To address this gap, we propose (1) A generalized variant of iterative self-critique and self-refinement devoid of external influence. (2) A novel ranking metric - Performance, Refinement, and Inference Cost Score (PeRFICS) - to find the optimal model for a given task considering refined performance and cost. Our experiments show that SoTA open source models of varying sizes from 7B - 65B, on average, improve 8.2% from their baseline performance. Strikingly, even models with extremely small memory footprints, such as Vicuna-7B, show a 11.74% improvement overall and up to a 25.39% improvement in high-creativity, open ended tasks on the Vicuna benchmark. Vicuna-13B takes it a step further and outperforms ChatGPT post-refinement. This work has profound implications for resource-constrained and information-sensitive environments seeking to leverage LLMs without incurring prohibitive costs, compromising on performance and privacy. The domain-agnostic self-refinement process coupled with our novel ranking metric facilitates informed decision-making in model selection, thereby reducing costs and democratizing access to high-performing language models, as evidenced by three case studies on personal computing, gaming and enterprise solutions.
Current abstractive summarization models often generate inconsistent content, i.e. texts that are not directly inferable from the source document, are not consistent with respect to world knowledge, or are self-contradictory. These inconsistencies motivate a new consistency taxonomy that we define as faithfulness, factuality, and self-supportiveness. However, most recent work on reducing inconsistency in document summarization only focuses on faithfulness detection and correction while ignoring other inconsistency phenomena, which limits the model’s scalability. To improve the general consistency we introduce EnergySum, where we apply the Residual Energy-based Model by designing energy scorers that reflect each type of consistency. These energy scores are utilized in candidate re-ranking during the sampling process. Experiments on XSUM and CNN/DM datasets show that EnergySum mitigates the trade-off between accuracy and consistency.
The recent explosion of performance of large language models (LLMs) has changed the field of Natural Language Processing (NLP) more abruptly and seismically than any other shift in the field’s 80 year history. This has resulted in concerns that the field will become homogenized and resource-intensive. This new status quo has put many academic researchers, especially PhD students, at a disadvantage. This paper aims to define a new NLP playground by proposing 20+ PhD-dissertation-worthy research directions, covering theoretical analysis, new and challenging problems, learning paradigms and interdisciplinary applications.
Large language models (LLM’s) have been widely used for several applications such as question answering, text classification and clustering. While the preliminary results across the aforementioned tasks looks promising, recent work has dived deep into LLM’s performing poorly for complex Named Entity Recognition (NER) tasks in comparison to fine-tuned pre-trained language models (PLM’s). To enhance wider adoption of LLM’s, our paper investigates the robustness of such LLM NER models and its instruction fine-tuned variants to adversarial attacks. In particular, we propose a novel attack which relies on disentanglement and word attribution techniques where the former aids in learning an embedding capturing both entity and non-entity influences separately, and the latter aids in identifying important words across both components. This is in stark contrast to most techniques which primarily leverage non-entity words for perturbations limiting the space being explored to synthesize effective adversarial examples. Adversarial training results based on our method improves the F1 score over original LLM NER model by 8% and 18% on CoNLL-2003 and Ontonotes 5.0 datasets respectively.
Automatic response forecasting for news media plays a crucial role in enabling content producers to efficiently predict the impact of news releases and prevent unexpected negative outcomes such as social conflict and moral injury. To effectively forecast responses, it is essential to develop measures that leverage the social dynamics and contextual information surrounding individuals, especially in cases where explicit profiles or historical actions of the users are limited (referred to as lurkers). As shown in a previous study, 97% of all tweets are produced by only the most active 25% of users. However, existing approaches have limited exploration of how to best process and utilize these important features. To address this gap, we propose a novel framework, named SocialSense, that leverages a large language model to induce a belief-centered graph on top of an existent social network, along with graph-based propagation to capture social dynamics. We hypothesize that the induced graph that bridges the gap between distant users who share similar beliefs allows the model to effectively capture the response patterns. Our method surpasses existing state-of-the-art in experimental evaluations for both zero-shot and supervised settings, demonstrating its effectiveness in response forecasting. Moreover, the analysis reveals the framework’s capability to effectively handle unseen user and lurker scenarios, further highlighting its robustness and practical applicability.
Recent progress in Large Language Models (LLMs) has produced models that exhibit remarkable performance across a variety of NLP tasks. However, it remains unclear whether the existing focus of NLP research accurately captures the genuine requirements of human users. This paper provides a comprehensive analysis of the divergence between academic research in NLP and the needs of real-world NLP applications via a large-scale collection of user-GPT conversations. We analyze a large-scale collection of real user queries to GPT. We compare these queries against existing NLP benchmark tasks and identify a significant gap between the tasks that users frequently request from LLMs and the tasks that are commonly studied in academic research. For example, we find that tasks such as “design” and “planning” are prevalent in user interactions but largely neglected or different from traditional NLP benchmarks. We investigate these overlooked tasks, dissect the practical challenges, and provide insights toward a roadmap to make LLMs better aligned with user needs.
The progress of event extraction research has been hindered by the absence of wide-coverage, large-scale datasets. To make event extraction systems more accessible, we build a general-purpose event detection dataset GLEN, which covers 205K event mentions with 3,465 different types, making it more than 20x larger in ontology than today’s largest event dataset. GLEN is created by utilizing the DWD Overlay, which provides a mapping between Wikidata Qnodes and PropBank rolesets. This enables us to use the abundant existing annotation for PropBank as distant supervision. In addition, we also propose a new multi-stage event detection model specifically designed to handle the large ontology size in GLEN. We show that our model exhibits superior performance compared to a range of baselines including InstructGPT. Finally, we perform error analysis and show that label noise is still the largest challenge for improving performance for this new dataset.
Large language models with instruction-following capabilities open the door to a wider group of users. However, when it comes to information extraction – a classic task in natural language processing – most task-specific systems cannot align well with long-tail ad hoc extraction use cases for non-expert users. To address this, we propose a novel paradigm, termed On-Demand Information Extraction, to fulfill the personalized demands of real-world users. Our task aims to follow the instructions to extract the desired content from the associated text and present it in a structured tabular format. The table headers can either be user-specified or inferred contextually by the model. To facilitate research in this emerging area, we present a benchmark named InstructIE, inclusive of both automatically generated training data, as well as the human-annotated test set. Building on InstructIE, we further develop an On-Demand Information Extractor, ODIE. Comprehensive evaluations on our benchmark reveal that ODIE substantially outperforms the existing open-source models of similar size.
State-of-the-art vision-language models (VLMs) still have limited performance in structural knowledge extraction, such as relations between objects. In this work, we present ViStruct, a training framework to learn VLMs for effective visual structural knowledge extraction. Two novel designs are incorporated. First, we propose to leverage the inherent structure of programming language to depict visual structural information. This approach enables explicit and consistent representation of visual structural information of multiple granularities, such as concepts, relations, and events, in a well-organized structured format. Second, we introduce curriculum-based learning for VLMs to progressively comprehend visual structures, from fundamental visual concepts to intricate event structures. Our intuition is that lower-level knowledge may contribute to complex visual structure understanding. Furthermore, we compile and release a collection of datasets tailored for visual structural knowledge extraction. We adopt a weakly-supervised approach to directly generate visual event structures from captions for ViStruct training, capitalizing on abundant image-caption pairs from the web. In experiments, we evaluate ViStruct on visual structure prediction tasks, demonstrating its effectiveness in improving the understanding of visual structures. The code will be made public to facilitate future research.
Knowledge of norms is needed to understand and reason about acceptable behavior in human communication and interactions across sociocultural scenarios. Most computational research on norms has focused on a single culture, and manually built datasets, from non-conversational settings. We address these limitations by proposing a new framework, NormSage, to automatically extract culture-specific norms from multi-lingual conversations. NormSage uses GPT-3 prompting to 1) extract candidate norms directly from conversations and 2) provide explainable self-verification to ensure correctness and relevance. Comprehensive empirical results show the promise of our approach to extract high-quality culture-aware norms from multi-lingual conversations (English and Chinese), across several quality metrics. Further, our relevance verification can be extended to assess the adherence and violation of any norm with respect to a conversation on-the-fly, along with textual explanation. NormSage achieves an AUC of 94.6% in this grounding setup, with generated explanations matching human-written quality.
In this paper, we present RESIN-EDITOR, an interactive event graph visualizer and editor designed for analyzing complex events. Our RESIN-EDITOR system allows users to render and freely edit hierarchical event graphs extracted from multimedia and multi-document news clusters with guidance from human-curated event schemas. RESIN-EDITOR’s unique features include hierarchical graph visualization, comprehensive source tracing, and interactive user editing, which significantly outperforms existing Information Extraction (IE) visualization tools in both IE result analysis and general model improvements. In our evaluation of RESIN-EDITOR, we demonstrate ways in which our tool is effective in understanding complex events and enhancing system performances. The source code, a video demonstration, and a live website for RESIN-EDITOR have been made publicly available.
Chemical reactions, as a core entity in the realm of chemistry, hold crucial implications in diverse areas ranging from hands-on laboratory research to advanced computational drug design. Despite a burgeoning interest in employing NLP techniques to extract these reactions, aligning this task with the real-world requirements of chemistry practitioners remains an ongoing challenge. In this paper, we present Reaction Miner, a system specifically designed to interact with raw scientific literature, delivering precise and more informative chemical reactions. Going beyond mere extraction, Reaction Miner integrates a holistic workflow: it accepts PDF files as input, bypassing the need for pre-processing and bolstering user accessibility. Subsequently, a text segmentation module ensures that the refined text encapsulates complete chemical reactions, augmenting the accuracy of extraction. Moreover, Reaction Miner broadens the scope of existing pre-defined reaction roles, including vital attributes previously neglected, thereby offering a more comprehensive depiction of chemical reactions. Evaluations conducted by chemistry domain users highlight the efficacy of each module in our system, demonstrating Reaction Miner as a powerful tool in this field.
Product attribute extraction is an emerging field in information extraction and e-commerce, with applications including knowledge base construction, product recommendation, and enhancing customer experiences. In this work, we explore the use of generative models for product attribute extraction. We analyze their utility with hard and soft prompting methods, and demonstrate their ability to generate implicit attribute values, which state-of-the-art sequence tagging models are unable to extract. We perform a wide range of experiments on Amazon and MAVE product attribute datasets, and are the first to present results on multilingual attribute extraction. Our results show that generative models can outperform state- of-the-art tagging models for explicit product attribute extraction while having greater data efficiency, that they have the unique ability to perform implicit attribute extraction, and that in certain settings large language models can perform competitively with finetuned models with as little as two in-context examples.
The distribution of knowledge elements such as entity types and event types is long-tailed in natural language. Hence information extraction datasets naturally conform long-tailed distribution. Although imbalanced datasets can teach the model about the useful real-world bias, deep learning models may learn features not generalizable to rare or unseen expressions of entities or events during evaluation, especially for rare types without sufficient training instances. Existing approaches for the long-tailed learning problem seek to manipulate the training data by re-balancing, augmentation or introducing extra prior knowledge. In comparison, we propose to handle the generalization challenge by making the evaluation instances closer to the frequent training cases. We design a new transformation module that transforms infrequent candidate mention representation during evaluation with the average mention representation in the training dataset. Experimental results on classic benchmarks on three entity or event extraction datasets demonstrates the effectiveness of our framework.
Information extraction (IE) and summarization are closely related, both tasked with presenting a subset of the information contained in a natural language text. However, while IE extracts structural representations, summarization aims to abstract the most salient information into a generated text summary – thus potentially encountering the technical limitations of current text generation methods (e.g., hallucination). To mitigate this risk, this work uses structured IE graphs to enhance the abstractive summarization task. Specifically, we focus on improving Multi-Document Summarization (MDS) performance by using cross-document IE output, incorporating two novel components: (1) the use of auxiliary entity and event recognition systems to focus the summary generation model; (2) incorporating an alignment loss between IE nodes and their text spans to reduce inconsistencies between the IE graphs and text representations. Operationally, both the IE nodes and corresponding text spans are projected into the same embedding space and pairwise distance is minimized. Experimental results on multiple MDS benchmarks show that summaries generated by our model are more factually consistent with the source documents than baseline models while maintaining the same level of abstractiveness.
In this paper, we present Tetris, a new task of Goal-Oriented Script Completion. Unlike previous work, it considers a more realistic and general setting, where the input includes not only the goal but also additional user context, including preferences and history. To address this problem, we propose a novel approach, which uses two techniques to improve performance: (1) concept prompting, and (2) script-oriented contrastive learning that addresses step repetition and hallucination problems. On our WikiHow-based dataset, we find that both methods improve performance.
Long video content understanding poses a challenging set of research questions as it involves long-distance, cross-media reasoning and knowledge awareness. In this paper, we present a new benchmark for this problem domain, targeting the task of deep movie/TV question answering (QA) beyond previous work’s focus on simple plot summary and short video moment settings. We define several baselines based on direct retrieval of relevant context for long-distance movie QA. Observing that real-world QAs may require higher-order multi-hop inferences, we further propose a novel framework, called the DeepMaven, which extracts events, entities, and relations from the rich multimedia content in long videos to pre-construct movie knowledge graphs (movieKGs), and at the time of QA inference, complements general semantics with structured knowledge for more effective information retrieval and knowledge reasoning. We also introduce our recently collected DeepMovieQA dataset, including 1,000 long-form QA pairs from 41 hours of videos, to serve as a new and useful resource for future work. Empirical results show the DeepMaven performs competitively for both the new DeepMovieQA and the pre-existing MovieQA dataset.
End-to-end neural models for conversational AI often assume that a response can be generated by considering only the knowledge acquired by the model during training. Document-oriented conversational models make a similar assumption by conditioning the input on the document and assuming that any other knowledge is captured in the model’s weights. However, a conversation may refer to external knowledge sources. In this work, we present EKo-Doc, an architecture for document-oriented conversations with access to external knowledge: we assume that a conversation is centered around a topic document and that external knowledge is needed to produce responses. EKo-Doc includes a dense passage retriever, a re-ranker, and a response generation model. We train the model end-to-end by using silver labels for the retrieval and re-ranking components that we automatically acquire from the attention signals of the response generation model. We demonstrate with automatic and human evaluations that incorporating external knowledge improves response generation in document-oriented conversations. Our architecture achieves new state-of-the-art results on the Wizard of Wikipedia dataset, outperforming a competitive baseline by 10.3% in Recall@1 and 7.4% in ROUGE-L.
Most event extraction methods have traditionally relied on an annotated set of event types. However, creating event ontologies and annotating supervised training data are expensive and time-consuming. Previous work has proposed semi-supervised approaches which leverage seen (annotated) types to learn how to automatically discover new event types. State-of-the-art methods, both semi-supervised or fully unsupervised, use a form of reconstruction loss on specific tokens in a context. In contrast, we present a novel approach to semi-supervised new event type induction using a masked contrastive loss, which learns similarities between event mentions by enforcing an attention mechanism over the data minibatch. We further disentangle the discovered clusters by approximating the underlying manifolds in the data, which allows us to achieve an adjusted rand index score of 48.85%. Building on these clustering results, we extend our approach to two new tasks: predicting the type name of the discovered clusters and linking them to FrameNet frames.
Conversational recommendation systems (CRS) have gained popularity in e-commerce as they can recommend items during user interactions. However, current open-ended CRS have limited recommendation performance due to their short-sighted training process, which only predicts one utterance at a time without considering its future impact. To address this, we propose a User Simulator (US) that communicates with the CRS using natural language based on given user preferences, enabling long-term reinforcement learning. We also introduce a framework that uses reinforcement learning (RL) with two novel rewards, i.e., recommendation and conversation rewards, to train the CRS. This approach considers the long-term goals and improves both the conversation and recommendation performance of the CRS. Our experiments show that our proposed framework improves the recall of recommendations by almost 100%. Moreover, human evaluation demonstrates the superiority of our framework in enhancing the informativeness of generated utterances.
Existing reference-free turn-level evaluation metrics for chatbots inadequately capture the interaction between the user and the system. Consequently, they often correlate poorly with human evaluations. To address this issue, we propose a novel model-agnostic approach that leverages Conditional Pointwise Mutual Information (C-PMI) to measure the turn-level interaction between the system and the user based on a given evaluation dimension. Experimental results on the widely used FED dialogue evaluation dataset demonstrate that our approach significantly improves the correlation with human judgment compared with existing evaluation systems. By replacing the negative log-likelihood-based scorer with our proposed C-PMI scorer, we achieve a relative 60.5% higher Spearman correlation on average for the FED evaluation metric. Our code is publicly available at https://github.com/renll/C-PMI.
Event-event temporal relation extraction aims to extract the temporal order between a pair of event mentions, which is usually used to construct temporal event graphs. However, event graphs generated by existing methods are usually globally inconsistent (event graphs containing cycles), semantically irrelevant (two unrelated events having temporal links), and context unaware (neglecting neighborhood information of an event node). In this paper, we propose a novel event-event temporal relation extraction method to address these limitations. Our model combines a pretrained language model and a graph neural network to output event embeddings, which captures the contextual information of event graphs. Moreover, to achieve global consistency and semantic relevance, (1) event temporal order should be in accordance with the norm of their embeddings, and (2) two events have temporal relation only if their embeddings are close enough. Experimental results on a real-world event dataset demonstrate that our method achieves state-of-the-art performance and generates high-quality event graphs.
Entity coreference resolution is an important research problem with many applications, including information extraction and question answering. Coreference resolution for English has been studied extensively. However, there is relatively little work for other languages. A problem that frequently occurs when working with a non-English language is the scarcity of annotated training data. To overcome this challenge, we design a simple but effective ensemble-based framework that combines various transfer learning (TL) techniques. We first train several models using different TL methods. Then, during inference, we compute the unweighted average scores of the models’ predictions to extract the final set of predicted clusters. Furthermore, we also propose a low-cost TL method that bootstraps coreference resolution models by utilizing Wikipedia anchor texts. Leveraging the idea that the coreferential links naturally exist between anchor texts pointing to the same article, our method builds a sizeable distantly-supervised dataset for the target language that consists of tens of thousands of documents. We can pre-train a model on the pseudo-labeled dataset before finetuning it on the final target dataset. Experimental results on two benchmark datasets, OntoNotes and SemEval, confirm the effectiveness of our methods. Our best ensembles consistently outperform the baseline approach of simple training by up to 7.68% in the F1 score. These ensembles also achieve new state-of-the-art results for three languages: Arabic, Dutch, and Spanish.
For emerging events, human readers are often exposed to both real news and fake news. Multiple news articles may contain complementary or contradictory information that readers can leverage to help detect fake news. Inspired by this process, we propose a novel task of cross-document misinformation detection. Given a cluster of topically related news documents, we aim to detect misinformation at both document level and a more fine-grained level, event level. Due to the lack of data, we generate fake news by manipulating real news, and construct 3 new datasets with 422, 276, and 1,413 clusters of topically related documents, respectively. We further propose a graph-based detector that constructs a cross-document knowledge graph using cross-document event coreference resolution and employs a heterogeneous graph neural network to conduct detection at two levels. We then feed the event-level detection results into the document-level detector. Experimental results show that our proposed method significantly outperforms existing methods by up to 7 F1 points on this new task.
Event schema depicts the typical structure of complex events, serving as a scaffolding to effectively analyze, predict, and possibly intervene in the ongoing events. To induce event schemas from historical events, previous work uses an event-by-event scheme, ignoring the global structure of the entire schema graph. We propose a new event schema induction framework using double graph autoencoders, which captures the global dependencies among nodes in event graphs. Specifically, we first extract the event skeleton from an event graph and design a variational directed acyclic graph (DAG) autoencoder to learn its global structure. Then we further fill in the event arguments for the skeleton, and use another Graph Convolutional Network (GCN) based autoencoder to reconstruct entity-entity relations as well as to detect coreferential entities. By performing this two-stage induction decomposition, the model can avoid reconstructing the entire graph in one step, allowing it to focus on learning global structures between events. Experimental results on three event graph datasets demonstrate that our method achieves state-of-the-art performance and induces high-quality event schemas with global consistency.
Providing conversation models with background knowledge has been shown to make open-domain dialogues more informative and engaging. Existing models treat knowledge selection as a sentence ranking or classification problem where each sentence is handled individually, ignoring the internal semantic connection between sentences. In this work, we propose to automatically convert the background knowledge documents into document semantic graphs and then perform knowledge selection over such graphs. Our document semantic graphs preserve sentence-level information through the use of sentence nodes and provide concept connections between sentences. We apply multi-task learning to perform sentence-level knowledge selection and concept-level knowledge selection, showing that it improves sentence-level selection. Our experiments show that our semantic graph-based knowledge selection improves over sentence selection baselines for both the knowledge selection task and the end-to-end response generation task on HollE and improves generalization on unseen topics in WoW.
Transformer-based models are not efficient in processing long sequences due to the quadratic space and time complexity of the self-attention modules. To address this limitation, Linformer and Informer reduce the quadratic complexity to linear (modulo logarithmic factors) via low-dimensional projection and row selection, respectively. These two models are intrinsically connected, and to understand their connection we introduce a theoretical framework of matrix sketching. Based on the theoretical analysis, we propose Skeinformer to accelerate self-attention and further improve the accuracy of matrix approximation to self-attention with column sampling, adaptive row normalization and pilot sampling reutilization. Experiments on the Long Range Arena benchmark demonstrate that our methods outperform alternatives with a consistently smaller time/space footprint.
We introduce RESIN-11, a new schema-guided event extraction&prediction framework that can be applied to a large variety of newsworthy scenarios. The framework consists of two parts: (1) an open-domain end-to-end multimedia multilingual information extraction system with weak-supervision and zero-shot learningbased techniques. (2) schema matching and schema-guided event prediction based on our curated schema library. We build a demo website based on our dockerized system and schema library publicly available for installation (https://github.com/RESIN-KAIROS/RESIN-11). We also include a video demonstrating the system.
This tutorial targets researchers and practitioners who are interested in AI and ML technologies for structural information extraction (IE) from unstructured textual sources. Particularly, this tutorial will provide audience with a systematic introduction to recent advances of IE, by answering several important research questions. These questions include (i) how to develop an robust IE system from noisy, insufficient training data, while ensuring the reliability of its prediction? (ii) how to foster the generalizability of IE through enhancing the system’s cross-lingual, cross-domain, cross-task and cross-modal transferability? (iii) how to precisely support extracting structural information with extremely fine-grained, diverse and boundless labels? (iv) how to further improve IE by leveraging indirect supervision from other NLP tasks, such as NLI, QA or summarization, and pre-trained language models? (v) how to acquire knowledge to guide the inference of IE systems? We will discuss several lines of frontier research that tackle those challenges, and will conclude the tutorial by outlining directions for further investigation.
Extracting informative arguments of events from news articles is a challenging problem in information extraction, which requires a global contextual understanding of each document. While recent work on document-level extraction has gone beyond single-sentence and increased the cross-sentence inference capability of end-to-end models, they are still restricted by certain input sequence length constraints and usually ignore the global context between events. To tackle this issue, we introduce a new global neural generation-based framework for document-level event argument extraction by constructing a document memory store to record the contextual event information and leveraging it to implicitly and explicitly help with decoding of arguments for later events. Empirical results show that our framework outperforms prior methods substantially and it is more robust to adversarially annotated examples with our constrained decoding design.
To tackle the challenge of accurate and timely communication regarding the COVID-19 pandemic, we present a COVID-19 Claim Radar to automatically extract supporting and refuting claims on a daily basis. We provide a comprehensive structured view of claims, including rich claim attributes (such as claimers and claimer affiliations) and associated knowledge elements as claim semantics (such as events, relations and entities), enabling users to explore equivalent, refuting, or supporting claims with structural evidence, such as shared claimers, similar centroid events and arguments. In order to consolidate claim structures at the corpus-level, we leverage Wikidata as the hub to merge coreferential knowledge elements. The system automatically provides users a comprehensive exposure to COVID-19 related claims, their importance, and their interconnections. The system is publicly available at GitHub and DockerHub, with complete documentation.
Supervised event extraction models require a substantial amount of training data to perform well. However, event annotation requires a lot of human effort and costs much time, which limits the application of existing supervised approaches to new event types. In order to reduce manual labor and shorten the time to build an event extraction system for an arbitrary event ontology, we present a new framework to train such systems much more efficiently without large annotations. Our event trigger labeling model uses a weak supervision approach, which only requires a set of keywords, a small number of examples and an unlabeled corpus, on which our approach automatically collects weakly supervised annotations. Our argument role labeling component performs zero-shot learning, which only requires the names of the argument roles of new event types. The source codes of our event trigger detection1 and event argument extraction2 models are publicly available for research purposes. We also release a dockerized system connecting the two models into an unified event extraction pipeline.
We present MolT5 - a self-supervised learning framework for pretraining models on a vast amount of unlabeled natural language text and molecule strings. MolT5 allows for new, useful, and challenging analogs of traditional vision-language tasks, such as molecule captioning and text-based de novo molecule generation (altogether: translation between molecules and language), which we explore for the first time. Since MolT5 pretrains models on single-modal data, it helps overcome the chemistry domain shortcoming of data scarcity. Furthermore, we consider several metrics, including a new cross-modal embedding-based metric, to evaluate the tasks of molecule captioning and text-based molecule generation. Our results show that MolT5-based models are able to generate outputs, both molecules and captions, which in many cases are high quality.
Modern large-scale Pre-trained Language Models (PLMs) have achieved tremendous success on a wide range of downstream tasks. However, most of the LM pre-training objectives only focus on text reconstruction, but have not sought to learn latent-level interpretable representations of sentences. In this paper, we manage to push the language models to obtain a deeper understanding of sentences by proposing a new pre-training objective, Sparse Latent Typing, which enables the model to sparsely extract sentence-level keywords with diverse latent types. Experimental results show that our model is able to learn interpretable latent type categories in a self-supervised manner without using any external knowledge. Besides, the language model pre-trained with such an objective also significantly improves Information Extraction related downstream tasks in both supervised and few-shot settings. Our code is publicly available at https://github.com/renll/SparseLT.
Multi-dimensional evaluation is the dominant paradigm for human evaluation in Natural Language Generation (NLG), i.e., evaluating the generated text from multiple explainable dimensions, such as coherence and fluency. However, automatic evaluation in NLG is still dominated by similarity-based metrics, and we lack a reliable framework for a more comprehensive evaluation of advanced models. In this paper, we propose a unified multi-dimensional evaluator UniEval for NLG. We re-frame NLG evaluation as a Boolean Question Answering (QA) task, and by guiding the model with different questions, we can use one evaluator to evaluate from multiple dimensions. Furthermore, thanks to the unified Boolean QA format, we are able to introduce an intermediate learning phase that enables UniEval to incorporate external knowledge from multiple related tasks and gain further improvement. Experiments on three typical NLG tasks show that UniEval correlates substantially better with human judgments than existing metrics. Specifically, compared to the top-performing unified evaluators, UniEval achieves a 23% higher correlation on text summarization, and over 43% on dialogue response generation. Also, UniEval demonstrates a strong zero-shot learning ability for unseen evaluation dimensions and tasks. Source code, data, and all pre-trained evaluators are available at https://github.com/maszhongming/UniEval.
Event argument extraction has long been studied as a sequential prediction problem with extractive-based methods, tackling each argument in isolation. Although recent work proposes generation-based methods to capture cross-argument dependency, they require generating and post-processing a complicated target sequence (template). Motivated by these observations and recent pretrained language models’ capabilities of learning from demonstrations. We propose a retrieval-augmented generative QA model (R-GQA) for event argument extraction. It retrieves the most similar QA pair and augments it as prompt to the current example’s context, then decodes the arguments as answers. Our approach outperforms substantially prior methods across various settings (i.e. fully supervised, domain transfer, and fewshot learning). Finally, we propose a clustering-based sampling strategy (JointEnc) and conduct a thorough analysis of how different strategies influence the few-shot learning performances.
Claim detection and verification are crucial for news understanding and have emerged as promising technologies for mitigating misinformation and disinformation in the news. However, most existing work has focused on claim sentence analysis while overlooking additional crucial attributes (e.g., the claimer and the main object associated with the claim).In this work, we present NewsClaims, a new benchmark for attribute-aware claim detection in the news domain. We extend the claim detection problem to include extraction of additional attributes related to each claim and release 889 claims annotated over 143 news articles. NewsClaims aims to benchmark claim detection systems in emerging scenarios, comprising unseen topics with little or no training data. To this end, we see that zero-shot and prompt-based baselines show promising performance on this benchmark, while still considerably behind human performance.
Conventional “closed-world” information extraction (IE) approaches rely on human ontologies to define the scope for extraction. As a result, such approaches fall short when applied to new domains. This calls for systems that can automatically infer new types from given corpora, a task which we refer to as type discovery.To tackle this problem, we introduce the idea of type abstraction, where the model is prompted to generalize and name the type. Then we use the similarity between inferred names to induce clusters. Observing that this abstraction-based representation is often complementary to the entity/trigger token representation, we set up these two representations as two views and design our model as a co-training framework. Our experiments on multiple relation extraction and event extraction datasets consistently show the advantage of our type abstraction approach.
Given a long untrimmed video and natural language queries, video grounding (VG) aims to temporally localize the semantically-aligned video segments. Almost all existing VG work holds two simple but unrealistic assumptions: 1) All query sentences can be grounded in the corresponding video. 2) All query sentences for the same video are always at the same semantic scale. Unfortunately, both assumptions make today’s VG models fail to work in practice. For example, in real-world multimodal assets (eg, news articles), most of the sentences in the article can not be grounded in their affiliated videos, and they typically have rich hierarchical relations (ie, at different semantic scales). To this end, we propose a new challenging grounding task: Weakly-Supervised temporal Article Grounding (WSAG). Specifically, given an article and a relevant video, WSAG aims to localize all “groundable” sentences to the video, and these sentences are possibly at different semantic scales. Accordingly, we collect the first WSAG dataset to facilitate this task: YouwikiHow, which borrows the inherent multi-scale descriptions in wikiHow articles and plentiful YouTube videos. In addition, we propose a simple but effective method DualMIL for WSAG, which consists of a two-level MIL loss and a single-/cross- sentence constraint loss. These training objectives are carefully designed for these relaxed assumptions. Extensive ablations have verified the effectiveness of DualMIL.
Entity linking (EL) is the task of linking entity mentions in a document to referent entities in a knowledge base (KB). Many previous studies focus on Wikipedia-derived KBs. There is little work on EL over Wikidata, even though it is the most extensive crowdsourced KB. The scale of Wikidata can open up many new real-world applications, but its massive number of entities also makes EL challenging. To effectively narrow down the search space, we propose a novel candidate retrieval paradigm based on entity profiling. Wikidata entities and their textual fields are first indexed into a text search engine (e.g., Elasticsearch). During inference, given a mention and its context, we use a sequence-to-sequence (seq2seq) model to generate the profile of the target entity, which consists of its title and description. We use the profile to query the indexed search engine to retrieve candidate entities. Our approach complements the traditional approach of using a Wikipedia anchor-text dictionary, enabling us to further design a highly effective hybrid method for candidate retrieval. Combined with a simple cross-attention reranker, our complete EL framework achieves state-of-the-art results on three Wikidata-based datasets and strong performance on TACKBP-2010.
Events are inter-related in documents. Motivated by the one-sense-per-discourse theory, we hypothesize that a participant tends to play consistent roles across multiple events in the same document. However recent work on document-level event argument extraction models each individual event in isolation and therefore causes inconsistency among extracted arguments across events, which will further cause discrepancy for downstream applications such as event knowledge base population, question answering, and hypothesis generation. In this work, we formulate event argument consistency as the constraints from event-event relations under the document-level setting. To improve consistency we introduce the Event-Aware Argument Extraction (EA2E) model with augmented context for training and inference. Experiment results on WIKIEVENTS and ACE2005 datasets demonstrate the effectiveness of EA2E compared to baseline methods.
Practitioners from many disciplines (e.g., political science) use expert-crafted taxonomies to make sense of large, unlabeled corpora. In this work, we study Seeded Hierarchical Clustering (SHC): the task of automatically fitting unlabeled data to such taxonomies using a small set of labeled examples. We propose HierSeed, a novel weakly supervised algorithm for this task that uses only a small set of labeled seed examples in a computation and data efficient manner. HierSeed assigns documents to topics by weighing document density against topic hierarchical structure. It outperforms unsupervised and supervised baselines for the SHC task on three real-world datasets.
This paper presents a parameter-lite transfer learning approach of pretrained language models (LM) for knowledge graph (KG) completion. Instead of finetuning, which modifies all LM parameters, we only tune a few new parameters while keeping the original LM parameters fixed. We establish this via reformulating KG completion as a “fill-in-the-blank” task, and introducing a parameter-lite encoder on top of the original LMs. We show that, by tuning far fewer parameters than finetuning, LMs transfer non-trivially to most tasks and reach competitiveness with prior state-of-the-art approaches. For instance, we outperform the fully finetuning approaches on a KG completion benchmark by tuning only 1% of the parameters.
The argument role in event extraction refers to the relation between an event and an argument participating in it. Despite the great progress in event extraction, existing studies still depend on roles pre-defined by domain experts. These studies expose obvious weakness when extending to emerging event types or new domains without available roles. Therefore, more attention and effort needs to be devoted to automatically customizing argument roles. In this paper, we define this essential but under-explored task: open-vocabulary argument role prediction. The goal of this task is to infer a set of argument roles for a given event type. We propose a novel unsupervised framework, RolePred for this task. Specifically, we formulate the role prediction problem as an in-filling task and construct prompts for a pre-trained language model to generate candidate roles. By extracting and analyzing the candidate arguments, the event-specific roles are further merged and selected. To standardize the research of this task, we collect a new human-annotated event extraction dataset including 143 customized argument roles with rich semantics. On this dataset, RolePred outperforms the existing methods by a large margin.
Misinformation is a pressing issue in modern society. It arouses a mixture of anger, distrust, confusion, and anxiety that cause damage on our daily life judgments and public policy decisions. While recent studies have explored various fake news detection and media bias detection techniques in attempts to tackle the problem, there remain many ongoing challenges yet to be addressed, as can be witnessed from the plethora of untrue and harmful content present during the COVID-19 pandemic and the international crises of late. In this tutorial, we provide researchers and practitioners with a systematic overview of the frontier in fighting misinformation. Specifically, we dive into the important research questions of how to (i) develop a robust fake news detection system, which not only fact-check information pieces provable by background knowledge but also reason about the consistency and the reliability of subtle details for emerging events; (ii) uncover the bias and agenda of news sources to better characterize misinformation; as well as (iii) correct false information and mitigate news bias, while allowing diverse opinions to be expressed. Moreover, we discuss the remaining challenges, future research directions, and exciting opportunities to help make this world a better place, with safer and more harmonic information sharing.
Fact-checking has gained increasing attention due to the widespread of falsified information. Most fact-checking approaches focus on claims made in English only due to the data scarcity issue in other languages. The lack of fact-checking datasets in low-resource languages calls for an effective cross-lingual transfer technique for fact-checking. Additionally, trustworthy information in different languages can be complementary and helpful in verifying facts. To this end, we present the first fact-checking framework augmented with cross-lingual retrieval that aggregates evidence retrieved from multiple languages through a cross-lingual retriever. Given the absence of cross-lingual information retrieval datasets with claim-like queries, we train the retriever with our proposed Cross-lingual Inverse Cloze Task (X-ICT), a self-supervised algorithm that creates training instances by translating the title of a passage. The goal for X-ICT is to learn cross-lingual retrieval in which the model learns to identify the passage corresponding to a given translated title. On the X-Fact dataset, our approach achieves 2.23% absolute F1 improvement in the zero-shot cross-lingual setup over prior systems. The source code and data are publicly available at https://github.com/khuangaf/CONCRETE.
Research on neural IR has so far been focused primarily on standard supervised learning settings, where it outperforms traditional term matching baselines. Many practical use cases of such models, however, may involve previously unseen target domains. In this paper, we propose to improve the out-of-domain generalization of Dense Passage Retrieval (DPR) - a popular choice for neural IR - through synthetic data augmentation only in the source domain. We empirically show that pre-finetuning DPR with additional synthetic data in its source domain (Wikipedia), which we generate using a fine-tuned sequence-to-sequence generator, can be a low-cost yet effective first step towards its generalization. Across five different test sets, our augmented model shows more robust performance than DPR in both in-domain and zero-shot out-of-domain evaluation.
In recent years, there has been an increasing interest in claim detection as an important building block for misinformation detection. This involves detecting more fine-grained attributes relating to the claim, such as the claimer, claim topic, claim object pertaining to the topic, etc. Yet, a notable bottleneck of existing claim detection approaches is their portability to emerging events and low-resource training data settings. In this regard, we propose a fine-grained claim detection framework that leverages zero-shot Question Answering (QA) using directed questions to solve a diverse set of sub-tasks such as topic filtering, claim object detection, and claimer detection. We show that our approach significantly outperforms various zero-shot, few-shot and task-specific baselines on the NewsClaims benchmark (Reddy et al., 2021).
Despite achieving state-of-the-art zero-shot performance, existing vision-language models still fall short of few-shot transfer ability on domain-specific problems. Classical fine-tuning often fails to prevent highly expressive models from exploiting spurious correlations. Although model-agnostic meta-learning (MAML) presents as a natural alternative for few-shot transfer learning, the expensive computation due to implicit second-order optimization limits its use on large-scale vision-language models such as CLIP. While much literature has been devoted to exploring alternative optimization strategies, we identify another essential aspect towards effective few-shot transfer learning, task sampling, which is previously only be viewed as part of data pre-processing in MAML. To show the impact of task sampling, we propose a simple algorithm, Model-Agnostic Multitask Fine-tuning (MAMF), which differentiates classical fine-tuning only on uniformly sampling multiple tasks. Despite its simplicity, we show that MAMF consistently outperforms classical fine-tuning on five few-shot image classification tasks. We further show that the effectiveness of the bi-level optimization in MAML is highly sensitive to the zero-shot performance of a task in the context of few-shot vision-language classification. The goal of this paper is to provide new insights on what makes few-shot learning work, and encourage more research into investigating better task sampling strategies.
To defend against machine-generated fake news, an effective mechanism is urgently needed. We contribute a novel benchmark for fake news detection at the knowledge element level, as well as a solution for this task which incorporates cross-media consistency checking to detect the fine-grained knowledge elements making news articles misinformative. Due to training data scarcity, we also formulate a novel data synthesis method by manipulating knowledge elements within the knowledge graph to generate noisy training data with specific, hard to detect, known inconsistencies. Our detection approach outperforms the state-of-the-art (up to 16.8% accuracy gain), and more critically, yields fine-grained explanations.
Pre-trained Language Models (PLMs) have shown superior performance on various downstream Natural Language Processing (NLP) tasks. However, conventional pre-training objectives do not explicitly model relational facts in text, which are crucial for textual understanding. To address this issue, we propose a novel contrastive learning framework ERICA to obtain a deep understanding of the entities and their relations in text. Specifically, we define two novel pre-training tasks to better understand entities and relations: (1) the entity discrimination task to distinguish which tail entity can be inferred by the given head entity and relation; (2) the relation discrimination task to distinguish whether two relations are close or not semantically, which involves complex relational reasoning. Experimental results demonstrate that ERICA can improve typical PLMs (BERT and RoBERTa) on several language understanding tasks, including relation extraction, entity typing and question answering, especially under low-resource settings.
Compared to the general news domain, information extraction (IE) from biomedical text requires much broader domain knowledge. However, many previous IE methods do not utilize any external knowledge during inference. Due to the exponential growth of biomedical publications, models that do not go beyond their fixed set of parameters will likely fall behind. Inspired by how humans look up relevant information to comprehend a scientific text, we present a novel framework that utilizes external knowledge for joint entity and relation extraction named KECI (Knowledge-Enhanced Collective Inference). Given an input text, KECI first constructs an initial span graph representing its initial understanding of the text. It then uses an entity linker to form a knowledge graph containing relevant background knowledge for the the entity mentions in the text. To make the final predictions, KECI fuses the initial span graph and the knowledge graph into a more refined graph using an attention mechanism. KECI takes a collective approach to link mention spans to entities by integrating global relational information into local representations using graph convolutional networks. Our experimental results show that the framework is highly effective, achieving new state-of-the-art results in two different benchmark datasets: BioRelEx (binding interaction detection) and ADE (adverse drug event extraction). For example, KECI achieves absolute improvements of 4.59% and 4.91% in F1 scores over the state-of-the-art on the BioRelEx entity and relation extraction tasks
Biomedical Information Extraction from scientific literature presents two unique and non-trivial challenges. First, compared with general natural language texts, sentences from scientific papers usually possess wider contexts between knowledge elements. Moreover, comprehending the fine-grained scientific entities and events urgently requires domain-specific background knowledge. In this paper, we propose a novel biomedical Information Extraction (IE) model to tackle these two challenges and extract scientific entities and events from English research papers. We perform Abstract Meaning Representation (AMR) to compress the wide context to uncover a clear semantic structure for each complex sentence. Besides, we construct the sentence-level knowledge graph from an external knowledge base and use it to enrich the AMR graph to improve the model’s understanding of complex scientific concepts. We use an edge-conditioned graph attention network to encode the knowledge-enriched AMR graph for biomedical IE tasks. Experiments on the GENIA 2011 dataset show that the AMR and external knowledge have contributed 1.8% and 3.0% absolute F-score gains respectively. In order to evaluate the impact of our approach on real-world problems that involve topic-specific fine-grained knowledge elements, we have also created a new ontology and annotated corpus for entity and event extraction for the COVID-19 scientific literature, which can serve as a new benchmark for the biomedical IE community.
Existing models on Machine Reading Comprehension (MRC) require complex model architecture for effectively modeling long texts with paragraph representation and classification, thereby making inference computationally inefficient for production use. In this work, we propose VAULT: a light-weight and parallel-efficient paragraph representation for MRC based on contextualized representation from long document input, trained using a new Gaussian distribution-based objective that pays close attention to the partially correct instances that are close to the ground-truth. We validate our VAULT architecture showing experimental results on two benchmark MRC datasets that require long context modeling; one Wikipedia-based (Natural Questions (NQ)) and the other on TechNotes (TechQA). VAULT can achieve comparable performance on NQ with a state-of-the-art (SOTA) complex document modeling approach while being 16 times faster, demonstrating the efficiency of our proposed model. We also demonstrate that our model can also be effectively adapted to a completely different domain – TechQA – with large improvement over a model fine-tuned on a previously published large PLM.
Graph-to-text generation has benefited from pre-trained language models (PLMs) in achieving better performance than structured graph encoders. However, they fail to fully utilize the structure information of the input graph. In this paper, we aim to further improve the performance of the pre-trained language model by proposing a structured graph-to-text model with a two-step fine-tuning mechanism which first fine-tunes model on Wikipedia before adapting to the graph-to-text generation. In addition to using the traditional token and position embeddings to encode the knowledge graph (KG), we propose a novel tree-level embedding method to capture the inter-dependency structures of the input graph. This new approach has significantly improved the performance of all text generation metrics for the English WebNLG 2017 dataset.
Constructing knowledge graphs from unstructured text is an important task that is relevant to many domains. Most previous work focuses on extracting information from sentences or paragraphs, due to the difficulty of analyzing longer contexts. In this paper we propose a new jointly trained model that can be used for various information extraction tasks at the document level. The tasks performed by this system are entity and event identification, typing, and coreference resolution. In order to improve entity and event typing, we utilize context-aware representations aggregated from the detected mentions of the corresponding entities and events across the entire document. By extending our system to document-level, we can improve our results by incorporating cross-sentence dependencies and additional contextual information that might not be available at the sentence level, which allows for more globally optimized predictions. We evaluate our system on documents from the ACE05-E+ dataset and find significant improvement over the sentence-level SOTA on entity and event trigger identification and classification.
This tutorial targets researchers and practitioners who are interested in AI technologies that help machines understand natural language text, particularly real-world events described in the text. These include methods to extract the internal structures of an event regarding its protagonist(s), participant(s) and properties, as well as external structures concerning memberships, temporal and causal relations of multiple events. This tutorial will provide audience with a systematic introduction of (i) knowledge representations of events, (ii) various methods for automated extraction, conceptualization and prediction of events and their relations, (iii) induction of event processes and properties, and (iv) a wide range of NLU and commonsense understanding tasks that benefit from aforementioned techniques. We will conclude the tutorial by outlining emerging research problems in this area.
The tasks of Rich Semantic Parsing, such as Abstract Meaning Representation (AMR), share similar goals with Information Extraction (IE) to convert natural language texts into structured semantic representations. To take advantage of such similarity, we propose a novel AMR-guided framework for joint information extraction to discover entities, relations, and events with the help of a pre-trained AMR parser. Our framework consists of two novel components: 1) an AMR based semantic graph aggregator to let the candidate entity and event trigger nodes collect neighborhood information from AMR graph for passing message among related knowledge elements; 2) an AMR guided graph decoder to extract knowledge elements based on the order decided by the hierarchical structures in AMR. Experiments on multiple datasets have shown that the AMR graph encoder and decoder have provided significant gains and our approach has achieved new state-of-the-art performance on all IE subtasks.
Grounding events into a precise timeline is important for natural language understanding but has received limited attention in recent work. This problem is challenging due to the inherent ambiguity of language and the requirement for information propagation over inter-related events. This paper first formulates this problem based on a 4-tuple temporal representation used in entity slot filling, which allows us to represent fuzzy time spans more conveniently. We then propose a graph attention network-based approach to propagate temporal information over document-level event graphs constructed by shared entity arguments and temporal relations. To better evaluate our approach, we present a challenging new benchmark on the ACE2005 corpus, where more than 78% of events do not have time spans mentioned explicitly in their local contexts. The proposed approach yields an absolute gain of 7.0% in match rate over contextualized embedding approaches, and 16.3% higher match rate compared to sentence-level manual event time argument annotation.
Event extraction has long been treated as a sentence-level task in the IE community. We argue that this setting does not match human informative seeking behavior and leads to incomplete and uninformative extraction results. We propose a document-level neural event argument extraction model by formulating the task as conditional generation following event templates. We also compile a new document-level event extraction benchmark dataset WikiEvents which includes complete event and coreference annotation. On the task of argument extraction, we achieve an absolute gain of 7.6% F1 and 5.7% F1 over the next best model on the RAMS and WikiEvents dataset respectively. On the more challenging task of informative argument extraction, which requires implicit coreference reasoning, we achieve a 9.3% F1 gain over the best baseline. To demonstrate the portability of our model, we also create the first end-to-end zero-shot event extraction framework and achieve 97% of fully supervised model’s trigger extraction performance and 82% of the argument extraction performance given only access to 10 out of the 33 types on ACE.
The quadratic computational and memory complexities of large Transformers have limited their scalability for long document summarization. In this paper, we propose Hepos, a novel efficient encoder-decoder attention with head-wise positional strides to effectively pinpoint salient information from the source. We further conduct a systematic study of existing efficient self-attentions. Combined with Hepos, we are able to process ten times more tokens than existing models that use full attentions. For evaluation, we present a new dataset, GovReport, with significantly longer documents and summaries. Results show that our models produce significantly higher ROUGE scores than competitive comparisons, including new state-of-the-art results on PubMed. Human evaluation also shows that our models generate more informative summaries with fewer unfaithful errors.
Event coreference resolution is an important research problem with many applications. Despite the recent remarkable success of pre-trained language models, we argue that it is still highly beneficial to utilize symbolic features for the task. However, as the input for coreference resolution typically comes from upstream components in the information extraction pipeline, the automatically extracted symbolic features can be noisy and contain errors. Also, depending on the specific context, some features can be more informative than others. Motivated by these observations, we propose a novel context-dependent gated module to adaptively control the information flows from the input symbolic features. Combined with a simple noisy training method, our best models achieve state-of-the-art results on two datasets: ACE 2005 and KBP 2016.
To combat COVID-19, both clinicians and scientists need to digest the vast amount of relevant biomedical knowledge in literature to understand the disease mechanism and the related biological functions. We have developed a novel and comprehensive knowledge discovery framework, COVID-KG to extract fine-grained multimedia knowledge elements (entities, relations and events) from scientific literature. We then exploit the constructed multimedia knowledge graphs (KGs) for question answering and report generation, using drug repurposing as a case study. Our framework also provides detailed contextual sentences, subfigures, and knowledge subgraphs as evidence. All of the data, KGs, reports.
We present a new information extraction system that can automatically construct temporal event graphs from a collection of news documents from multiple sources, multiple languages (English and Spanish for our experiment), and multiple data modalities (speech, text, image and video). The system advances state-of-the-art from two aspects: (1) extending from sentence-level event extraction to cross-document cross-lingual cross-media event extraction, coreference resolution and temporal event tracking; (2) using human curated event schema library to match and enhance the extraction output. We have made the dockerlized system publicly available for research purpose at GitHub, with a demo video.
Due to its great power in modeling non-Euclidean data like graphs or manifolds, deep learning on graph techniques (i.e., Graph Neural Networks (GNNs)) have opened a new door to solving challenging graph-related NLP problems. There has seen a surge of interests in applying deep learning on graph techniques to NLP, and has achieved considerable success in many NLP tasks, ranging from classification tasks like sentence classification, semantic role labeling and relation extraction, to generation tasks like machine translation, question generation and summarization. Despite these successes, deep learning on graphs for NLP still face many challenges, including automatically transforming original text sequence data into highly graph-structured data, and effectively modeling complex data that involves mapping between graph-based inputs and other highly structured output data such as sequences, trees, and graph data with multi-types in both nodes and edges. This tutorial will cover relevant and interesting topics on applying deep learning on graph techniques to NLP, including automatic graph construction for NLP, graph representation learning for NLP, advanced GNN based models (e.g., graph2seq, graph2tree, and graph2graph) for NLP, and the applications of GNNs in various NLP tasks (e.g., machine translation, natural language generation, information extraction and semantic parsing). In addition, hands-on demonstration sessions will be included to help the audience gain practical experience on applying GNNs to solve challenging NLP problems using our recently developed open source library – Graph4NLP, the first library for researchers and practitioners for easy use of GNNs for various NLP tasks.
Current methods for event representation ignore related events in a corpus-level global context. For a deep and comprehensive understanding of complex events, we introduce a new task, Event Network Embedding, which aims to represent events by capturing the connections among events. We propose a novel framework, Global Event Network Embedding (GENE), that encodes the event network with a multi-view graph encoder while preserving the graph topology and node semantics. The graph encoder is trained by minimizing both structural and semantic losses. We develop a new series of structured probing tasks, and show that our approach effectively outperforms baseline models on node typing, argument role classification, and event coreference resolution.
The growing popularity of Virtual Assistants poses new challenges for Entity Resolution, the task of linking mentions in text to their referent entities in a knowledge base. Specifically, in the shopping domain, customers tend to mention the entities implicitly (e.g., “organic milk”) rather than use the entity names explicitly, leading to a large number of candidate products. Meanwhile, for the same query, different customers may expect different results. For example, with “add milk to my cart”, a customer may refer to a certain product from his/her favorite brand, while some customers may want to re-order products they regularly purchase. Moreover, new customers may lack persistent shopping history, which requires us to enrich the connections between customers through products and their attributes. To address these issues, we propose a new framework that leverages personalized features to improve the accuracy of product ranking. We first build a cross-source heterogeneous knowledge graph from customer purchase history and product knowledge graph to jointly learn customer and product embeddings. After that, we incorporate product, customer, and history representations into a neural reranking model to predict which candidate is most likely to be purchased by a specific customer. Experiment results show that our model substantially improves the accuracy of the top ranked candidates by 24.6% compared to the state-of-the-art product search model.
Event coreference resolution is critical to understand events in the growing number of online news with multiple modalities including text, video, speech, etc. However, the events and entities depicting in different modalities may not be perfectly aligned and can be difficult to annotate, which makes the task especially challenging with little supervision available. To address the above issues, we propose a supervised model based on attention mechanism and an unsupervised model based on statistical machine translation, capable of learning the relative importance of modalities for event coreference resolution. Experiments on a video multimedia event dataset show that our multimodal models outperform text-only systems in event coreference resolution tasks. A careful analysis reveals that the performance gain of the multimodal model especially under unsupervised settings comes from better learning of visually salient events.
Visual and textual modalities contribute complementary information about events described in multimedia documents. Videos contain rich dynamics and detailed unfoldings of events, while text describes more high-level and abstract concepts. However, existing event extraction methods either do not handle video or solely target video while ignoring other modalities. In contrast, we propose the first approach to jointly extract events from both video and text articles. We introduce the new task of Video MultiMedia Event Extraction and propose two novel components to build the first system towards this task. First, we propose the first self-supervised cross-modal event coreference model that can determine coreference between video events and text events without any manually annotated pairs. Second, we introduce the first cross-modal transformer architecture, which extracts structured event information from both videos and text documents. We also construct and will publicly release a new benchmark of video-article pairs, consisting of 860 video-article pairs with extensive annotations for evaluating methods on this task. Our experimental results demonstrate the effectiveness of our proposed method on our new benchmark dataset. We achieve 6.0% and 5.8% absolute F-score gain on multimodal event coreference resolution and multimedia event extraction.
Relations in most of the traditional knowledge graphs (KGs) only reflect static and factual connections, but fail to represent the dynamic activities and state changes about entities. In this paper, we emphasize the importance of incorporating events in KG representation learning, and propose an event-enhanced KG embedding model EventKE. Specifically, given the original KG, we first incorporate event nodes by building a heterogeneous network, where entity nodes and event nodes are distributed on the two sides of the network inter-connected by event argument links. We then use entity-entity relations from the original KG and event-event temporal links to inner-connect entity and event nodes respectively. We design a novel and effective attention-based message passing method, which is conducted on entity-entity, event-entity, and event-event relations to fuse the event information into KG embeddings. Experimental results on real-world datasets demonstrate that events can greatly improve the quality of the KG embeddings on multiple downstream tasks.
Biomedical entity linking is the task of linking entity mentions in a biomedical document to referent entities in a knowledge base. Recently, many BERT-based models have been introduced for the task. While these models achieve competitive results on many datasets, they are computationally expensive and contain about 110M parameters. Little is known about the factors contributing to their impressive performance and whether the over-parameterization is needed. In this work, we shed some light on the inner workings of these large BERT-based models. Through a set of probing experiments, we have found that the entity linking performance only changes slightly when the input word order is shuffled or when the attention scope is limited to a fixed window size. From these observations, we propose an efficient convolutional neural network with residual connections for biomedical entity linking. Because of the sparse connectivity and weight sharing properties, our model has a small number of parameters and is highly efficient. On five public datasets, our model achieves comparable or even better linking accuracy than the state-of-the-art BERT-based models while having about 60 times fewer parameters.
We propose a new task, Text2Mol, to retrieve molecules using natural language descriptions as queries. Natural language and molecules encode information in very different ways, which leads to the exciting but challenging problem of integrating these two very different modalities. Although some work has been done on text-based retrieval and structure-based retrieval, this new task requires integrating molecules and natural language more directly. Moreover, this can be viewed as an especially challenging cross-lingual retrieval problem by considering the molecules as a language with a very unique grammar. We construct a paired dataset of molecules and their corresponding text descriptions, which we use to learn an aligned common semantic embedding space for retrieval. We extend this to create a cross-modal attention-based model for explainability and reranking by interpreting the attentions as association rules. We also employ an ensemble approach to integrate our different architectures, which significantly improves results from 0.372 to 0.499 MRR. This new multimodal approach opens a new perspective on solving problems in chemistry literature understanding and molecular machine learning.
Event schemas encode knowledge of stereotypical structures of events and their connections. As events unfold, schemas are crucial to act as a scaffolding. Previous work on event schema induction focuses either on atomic events or linear temporal event sequences, ignoring the interplay between events via arguments and argument relations. We introduce a new concept of Temporal Complex Event Schema: a graph-based schema representation that encompasses events, arguments, temporal connections and argument relations. In addition, we propose a Temporal Event Graph Model that predicts event instances following the temporal complex event schema. To build and evaluate such schemas, we release a new schema learning corpus containing 6,399 documents accompanied with event graphs, and we have manually constructed gold-standard schemas. Intrinsic evaluations by schema matching and instance graph perplexity, prove the superior quality of our probabilistic graph schema library compared to linear representations. Extrinsic evaluation on schema-guided future event prediction further demonstrates the predictive power of our event graph model, significantly outperforming human schemas and baselines by more than 17.8% on HITS@1.
Traditional supervised Information Extraction (IE) methods can extract structured knowledge elements from unstructured data, but it is limited to a pre-defined target ontology. In reality, the ontology of interest may change over time, adding emergent new types or more fine-grained subtypes. We propose a new lifelong learning framework to address this challenge. We focus on lifelong event detection as an exemplar case and propose a new problem formulation that is also generalizable to other IE tasks. In event detection and more general IE tasks, rich correlations or semantic relatedness exist among hierarchical knowledge element types. In our proposed framework, knowledge is being transferred between learned old event types and new event types. Specifically, we update old knowledge with new event types’ mentions using a self-training loss. In addition, we aggregate old event types’ representations based on their similarities with new event types to initialize the new event types’ representations. Experimental results show that our framework outperforms competitive baselines with a 5.1% absolute gain in the F1 score. Moreover, our proposed framework can boost the F1 score for over 30% absolute gain on some new long-tail rare event types with few training instances. Our knowledge transfer module improves performance on both learned event types and new event types under the lifelong learning setting, showing that it helps consolidate old knowledge and improve novel knowledge acquisition.
Traditional event extraction methods require predefined event types and their corresponding annotations to learn event extractors. These prerequisites are often hard to be satisfied in real-world applications. This work presents a corpus-based open-domain event type induction method that automatically discovers a set of event types from a given corpus. As events of the same type could be expressed in multiple ways, we propose to represent each event type as a cluster of <predicate sense, object head> pairs. Specifically, our method (1) selects salient predicates and object heads, (2) disambiguates predicate senses using only a verb sense dictionary, and (3) obtains event types by jointly embedding and clustering <predicate sense, object head> pairs in a latent spherical space. Our experiments, on three datasets from different domains, show our method can discover salient and high-quality event types, according to both automatic and human evaluations.
Timeline Summarization identifies major events from a news collection and describes them following temporal order, with key dates tagged. Previous methods generally generate summaries separately for each date after they determine the key dates of events. These methods overlook the events’ intra-structures (arguments) and inter-structures (event-event connections). Following a different route, we propose to represent the news articles as an event-graph, thus the summarization becomes compressing the whole graph to its salient sub-graph. The key hypothesis is that the events connected through shared arguments and temporal order depict the skeleton of a timeline, containing events that are semantically related, temporally coherent and structurally salient in the global event graph. A time-aware optimal transport distance is then introduced for learning the compression model in an unsupervised manner. We show that our approach significantly improves on the state of the art on three real-world datasets, including two public standard benchmarks and our newly collected Timeline100 dataset.
We study the problem of training named entity recognition (NER) models using only distantly-labeled data, which can be automatically obtained by matching entity mentions in the raw text with entity types in a knowledge base. The biggest challenge of distantly-supervised NER is that the distant supervision may induce incomplete and noisy labels, rendering the straightforward application of supervised learning ineffective. In this paper, we propose (1) a noise-robust learning scheme comprised of a new loss function and a noisy label removal step, for training NER models on distantly-labeled data, and (2) a self-training method that uses contextualized augmentations created by pre-trained language models to improve the generalization ability of the NER model. On three benchmark datasets, our method achieves superior performance, outperforming existing distantly-supervised NER models by significant margins.
Event time is one of the most important features for event-event temporal relation extraction. However, explicit event time information in text is sparse. For example, only about 20% of event mentions in TimeBank-Dense have event-time links. In this paper, we propose a joint model for event-event temporal relation classification and an auxiliary task, relative event time prediction, which predicts the event time as real numbers. We adopt the Stack-Propagation framework to incorporate predicted relative event time for temporal relation classification and keep the differentiability. Our experiments on MATRES dataset show that our model can significantly improve the RoBERTa-based baseline and achieve state-of-the-art performance.
Knowledge-enriched text generation poses unique challenges in modeling and learning, driving active research in several core directions, ranging from integrated modeling of neural representations and symbolic information in the sequential/hierarchical/graphical structures, learning without direct supervisions due to the cost of structured annotation, efficient optimization and inference with massive and global constraints, to language grounding on multiple modalities, and generative reasoning with implicit commonsense knowledge and background knowledge. In this tutorial we will present a roadmap to line up the state-of-the-art methods to tackle these challenges on this cutting-edge problem. We will dive deep into various technical components: how to represent knowledge, how to feed knowledge into a generation model, how to evaluate generation results, and what are the remaining challenges?
Most of the current cross-lingual transfer learning methods for Information Extraction (IE) have been only applied to name tagging. To tackle more complex tasks such as event extraction we need to transfer graph structures (event trigger linked to multiple arguments with various roles) across languages. We develop a novel share-and-transfer framework to reach this goal with three steps: (1) Convert each sentence in any language to language-universal graph structures; in this paper we explore two approaches based on universal dependency parses and complete graphs, respectively. (2) Represent each node in the graph structure with a cross-lingual word embedding so that all sentences in multiple languages can be represented with one shared semantic space. (3) Using this common semantic space, train event extractors from English training data and apply them to languages that do not have any event annotations. Experimental results on three languages (Spanish, Russian and Ukrainian) without any annotations show this framework achieves comparable performance to a state-of-the-art supervised model trained from more than 1,500 manually annotated event mentions.
To assist human review process, we build a novel ReviewRobot to automatically assign a review score and write comments for multiple categories such as novelty and meaningful comparison. A good review needs to be knowledgeable, namely that the comments should be constructive and informative to help improve the paper; and explainable by providing detailed evidence. ReviewRobot achieves these goals via three steps: (1) We perform domain-specific Information Extraction to construct a knowledge graph (KG) from the target paper under review, a related work KG from the papers cited by the target paper, and a background KG from a large collection of previous papers in the domain. (2) By comparing these three KGs, we predict a review score and detailed structured knowledge as evidence for each review category. (3) We carefully select and generalize human review sentences into templates, and apply these templates to transform the review scores and evidence into natural language comments. Experimental results show that our review score predictor reaches 71.4%-100% accuracy. Human assessment by domain experts shows that 41.7%-70.5% of the comments generated by ReviewRobot are valid and constructive, and better than human-written ones for 20% of the time. Thus, ReviewRobot can serve as an assistant for paper reviewers, program chairs and authors.
We introduce a new task, MultiMedia Event Extraction, which aims to extract events and their arguments from multimedia documents. We develop the first benchmark and collect a dataset of 245 multimedia news articles with extensively annotated events and arguments. We propose a novel method, Weakly Aligned Structured Embedding (WASE), that encodes structured representations of semantic information from textual and visual data into a common embedding space. The structures are aligned across modalities by employing a weakly supervised training strategy, which enables exploiting available resources without explicit cross-media annotation. Compared to uni-modal state-of-the-art methods, our approach achieves 4.0% and 9.8% absolute F-score gains on text event argument role labeling and visual event extraction. Compared to state-of-the-art multimedia unstructured representations, we achieve 8.3% and 5.0% absolute F-score gains on multimedia event extraction and argument role labeling, respectively. By utilizing images, we extract 21.4% more event mentions than traditional text-only methods.
Most existing joint neural models for Information Extraction (IE) use local task-specific classifiers to predict labels for individual instances (e.g., trigger, relation) regardless of their interactions. For example, a victim of a die event is likely to be a victim of an attack event in the same sentence. In order to capture such cross-subtask and cross-instance inter-dependencies, we propose a joint neural framework, OneIE, that aims to extract the globally optimal IE result as a graph from an input sentence. OneIE performs end-to-end IE in four stages: (1) Encoding a given sentence as contextualized word representations; (2) Identifying entity mentions and event triggers as nodes; (3) Computing label scores for all nodes and their pairwise links using local classifiers; (4) Searching for the globally optimal graph with a beam decoder. At the decoding stage, we incorporate global features to capture the cross-subtask and cross-instance interactions. Experiments show that adding global features improves the performance of our model and achieves new state of-the-art on all subtasks. In addition, as OneIE does not use any language-specific feature, we prove it can be easily applied to new languages or trained in a multilingual manner.
We present the first comprehensive, open source multimedia knowledge extraction system that takes a massive stream of unstructured, heterogeneous multimedia data from various sources and languages as input, and creates a coherent, structured knowledge base, indexing entities, relations, and events, following a rich, fine-grained ontology. Our system, GAIA, enables seamless search of complex graph queries, and retrieves multimedia evidence including text, images and videos. GAIA achieves top performance at the recent NIST TAC SM-KBP2019 evaluation. The system is publicly available at GitHub and DockerHub, with a narrated video that documents the system.
Joint entity and relation extraction aims to extract relation triplets from plain text directly. Prior work leverages Sequence-to-Sequence (Seq2Seq) models for triplet sequence generation. However, Seq2Seq enforces an unnecessary order on the unordered triplets and involves a large decoding length associated with error accumulation. These methods introduce exposure bias, which may cause the models overfit to the frequent label combination, thus limiting the generalization ability. We propose a novel Sequence-to-Unordered-Multi-Tree (Seq2UMTree) model to minimize the effects of exposure bias by limiting the decoding length to three within a triplet and removing the order among triplets. We evaluate our model on two datasets, DuIE and NYT, and systematically study how exposure bias alters the performance of Seq2Seq models. Experiments show that the state-of-the-art Seq2Seq model overfits to both datasets while Seq2UMTree shows significantly better generalization. Our code is available at https://github.com/WindChimeRan/OpenJERE.
Linguistic steganography studies how to hide secret messages in natural language cover texts. Traditional methods aim to transform a secret message into an innocent text via lexical substitution or syntactical modification. Recently, advances in neural language models (LMs) enable us to directly generate cover text conditioned on the secret message. In this study, we present a new linguistic steganography method which encodes secret messages using self-adjusting arithmetic coding based on a neural language model. We formally analyze the statistical imperceptibility of this method and empirically show it outperforms the previous state-of-the-art methods on four datasets by 15.3% and 38.9% in terms of bits/word and KL metrics, respectively. Finally, human evaluations show that 51% of generated cover texts can indeed fool eavesdroppers.
Event schemas can guide our understanding and ability to make predictions with respect to what might happen next. We propose a new Event Graph Schema, where two event types are connected through multiple paths involving entities that fill important roles in a coherent story. We then introduce Path Language Model, an auto-regressive language model trained on event-event paths, and select salient and coherent paths to probabilistically construct these graph schemas. We design two evaluation metrics, instance coverage and instance coherence, to evaluate the quality of graph schema induction, by checking when coherent event instances are covered by the schema graph. Intrinsic evaluations show that our approach is highly effective at inducing salient and coherent schemas. Extrinsic evaluations show the induced schema repository provides significant improvement to downstream end-to-end Information Extraction over a state-of-the-art joint neural extraction model, when used as additional global features to unfold instance graphs.
Most previous event extraction studies assume a set of target event types and corresponding event annotations are given, which could be very expensive. In this paper, we work on a new task of semi-supervised event type induction, aiming to automatically discover a set of unseen types from a given corpus by leveraging annotations available for a few seen types. We design a Semi-Supervised Vector Quantized Variational Autoencoder framework to automatically learn a discrete latent type representation for each seen and unseen type and optimize them using seen type event annotations. A variational autoencoder is further introduced to enforce the reconstruction of each event mention conditioned on its latent type distribution. Experiments show that our approach can not only achieve state-of-the-art performance on supervised event detection but also discover high-quality new event types.
Aspect-based sentiment analysis of review texts is of great value for understanding user feedback in a fine-grained manner. It has in general two sub-tasks: (i) extracting aspects from each review, and (ii) classifying aspect-based reviews by sentiment polarity. In this paper, we propose a weakly-supervised approach for aspect-based sentiment analysis, which uses only a few keywords describing each aspect/sentiment without using any labeled examples. Existing methods are either designed only for one of the sub-tasks, or are based on topic models that may contain overlapping concepts. We propose to first learn <sentiment, aspect> joint topic embeddings in the word embedding space by imposing regularizations to encourage topic distinctiveness, and then use neural models to generalize the word-level discriminative information by pre-training the classifiers with embedding-based predictions and self-training them on unlabeled data. Our comprehensive performance analysis shows that our method generates quality joint topics and outperforms the baselines significantly (7.4% and 5.1% F1-score gain on average for aspect and sentiment classification respectively) on benchmark datasets.
Current text classification methods typically require a good number of human-labeled documents as training data, which can be costly and difficult to obtain in real applications. Humans can perform classification without seeing any labeled examples but only based on a small set of words describing the categories to be classified. In this paper, we explore the potential of only using the label name of each class to train classification models on unlabeled data, without using any labeled documents. We use pre-trained neural language models both as general linguistic knowledge sources for category understanding and as representation learning models for document classification. Our method (1) associates semantically related words with the label names, (2) finds category-indicative words and trains the model to predict their implied categories, and (3) generalizes the model via self-training. We show that our model achieves around 90% accuracy on four benchmark datasets including topic and sentiment classification without using any labeled documents but learning from unlabeled data supervised by at most 3 words (1 in most cases) per class as the label name.
Word embeddings are widely used on a variety of tasks and can substantially improve the performance. However, their quality is not consistent throughout the vocabulary due to the long-tail distribution of word frequency. Without sufficient contexts, rare word embeddings are usually less reliable than those of common words. However, current models typically trust all word embeddings equally regardless of their reliability and thus may introduce noise and hurt the performance. Since names often contain rare and uncommon words, this problem is particularly critical for name tagging. In this paper, we propose a novel reliability-aware name tagging model to tackle this issue. We design a set of word frequency-based reliability signals to indicate the quality of each word embedding. Guided by the reliability signals, the model is able to dynamically select and compose features such as word embedding and character-level representation using gating mechanisms. For example, if an input word is rare, the model relies less on its word embedding and assigns higher weights to its character and contextual features. Experiments on OntoNotes 5.0 show that our model outperforms the baseline model by 2.7% absolute gain in F-score. In cross-genre experiments on five genres in OntoNotes, our model improves the performance for most genre pairs and obtains up to 5% absolute F-score gain.
We present a PaperRobot who performs as an automatic research assistant by (1) conducting deep understanding of a large collection of human-written papers in a target domain and constructing comprehensive background knowledge graphs (KGs); (2) creating new ideas by predicting links from the background KGs, by combining graph attention and contextual text attention; (3) incrementally writing some key elements of a new paper based on memory-attention networks: from the input title along with predicted related entities to generate a paper abstract, from the abstract to generate conclusion and future work, and finally from future work to generate a title for a follow-on paper. Turing Tests, where a biomedical domain expert is asked to compare a system output and a human-authored string, show PaperRobot generated abstracts, conclusion and future work sections, and new titles are chosen over human-written ones up to 30%, 24% and 12% of the time, respectively.
Transcripts of natural, multi-person meetings differ significantly from documents like news articles, which can make Natural Language Generation models for generating summaries unfocused. We develop an abstractive meeting summarizer from both videos and audios of meeting recordings. Specifically, we propose a multi-modal hierarchical attention across three levels: segment, utterance and word. To narrow down the focus into topically-relevant segments, we jointly model topic segmentation and summarization. In addition to traditional text features, we introduce new multi-modal features derived from visual focus of attention, based on the assumption that the utterance is more important if the speaker receives more attention. Experiments show that our model significantly outperforms the state-of-the-art with both BLEU and ROUGE measures.
Event extraction for the biomedical domain is more challenging than that in the general news domain since it requires broader acquisition of domain-specific knowledge and deeper understanding of complex contexts. To better encode contextual information and external background knowledge, we propose a novel knowledge base (KB)-driven tree-structured long short-term memory networks (Tree-LSTM) framework, incorporating two new types of features: (1) dependency structures to capture wide contexts; (2) entity properties (types and category descriptions) from external ontologies via entity linking. We evaluate our approach on the BioNLP shared task with Genia dataset and achieve a new state-of-the-art result. In addition, both quantitative and qualitative studies demonstrate the advancement of the Tree-LSTM and the external knowledge representation for biomedical event extraction.
Unsupervised part of speech (POS) tagging is often framed as a clustering problem, but practical taggers need to ground their clusters as well. Grounding generally requires reference labeled data, a luxury a low-resource language might not have. In this work, we describe an approach for low-resource unsupervised POS tagging that yields fully grounded output and requires no labeled training data. We find the classic method of Brown et al. (1992) clusters well in our use case and employ a decipherment-based approach to grounding. This approach presumes a sequence of cluster IDs is a ‘ciphertext’ and seeks a POS tag-to-cluster ID mapping that will reveal the POS sequence. We show intrinsically that, despite the difficulty of the task, we obtain reasonable performance across a variety of languages. We also show extrinsically that incorporating our POS tagger into a name tagger leads to state-of-the-art tagging performance in Sinhalese and Kinyarwanda, two languages with nearly no labeled POS data available. We further demonstrate our tagger’s utility by incorporating it into a true ‘zero-resource’ variant of the MALOPA (Ammar et al., 2016) dependency parser model that removes the current reliance on multilingual resources and gold POS tags for new languages. Experiments show that including our tagger makes up much of the accuracy lost when gold POS tags are unavailable.
We focus on improving name tagging for low-resource languages using annotations from related languages. Previous studies either directly project annotations from a source language to a target language using cross-lingual representations or use a shared encoder in a multitask network to transfer knowledge. These approaches inevitably introduce noise to the target language annotation due to mismatched source-target sentence structures. To effectively transfer the resources, we develop a new neural architecture that leverages multi-level adversarial transfer: (1) word-level adversarial training, which projects source language words into the same semantic space as those of the target language without using any parallel corpora or bilingual gazetteers, and (2) sentence-level adversarial training, which yields language-agnostic sequential features. Our neural architecture outperforms previous approaches on CoNLL data sets. Moreover, on 10 low-resource languages, our approach achieves up to 16% absolute F-score gain over all high-performing baselines on cross-lingual transfer without using any target-language resources.
This paper demonstrates a state-of-the-art end-to-end multilingual (English, Russian, and Ukrainian) knowledge extraction system that can perform entity discovery and linking, relation extraction, event extraction, and coreference. It extracts and aggregates knowledge elements across multiple languages and documents as well as provides visualizations of the results along three dimensions: temporal (as displayed in an event timeline), spatial (as displayed in an event heatmap), and relational (as displayed in entity-relation networks). For our system to further support users’ analyses of causal sequences of events in complex situations, we also integrate a wide range of human moral value measures, independently derived from region-based survey, into the event heatmap. This system is publicly available as a docker container and a live demo.
Name tagging in low-resource languages or domains suffers from inadequate training data. Existing work heavily relies on additional information, while leaving those noisy annotations unexplored that extensively exist on the web. In this paper, we propose a novel neural model for name tagging solely based on weakly labeled (WL) data, so that it can be applied in any low-resource settings. To take the best advantage of all WL sentences, we split them into high-quality and noisy portions for two modules, respectively: (1) a classification module focusing on the large portion of noisy data can efficiently and robustly pretrain the tag classifier by capturing textual context semantics; and (2) a costly sequence labeling module focusing on high-quality data utilizes Partial-CRFs with non-entity sampling to achieve global optimum. Two modules are combined via shared parameters. Extensive experiments involving five low-resource languages and fine-grained food domain demonstrate our superior performance (6% and 7.8% F1 gains on average) as well as efficiency.
The identification of complex semantic structures such as events and entity relations, already a challenging Information Extraction task, is doubly difficult from sources written in under-resourced and under-annotated languages. We investigate the suitability of cross-lingual structure transfer techniques for these tasks. We exploit relation- and event-relevant language-universal features, leveraging both symbolic (including part-of-speech and dependency path) and distributional (including type representation and contextualized representation) information. By representing all entity mentions, event triggers, and contexts into this complex and structured multilingual common space, using graph convolutional networks, we can train a relation or event extractor from source language annotations and apply it to the target language. Extensive experiments on cross-lingual relation and event transfer among English, Chinese, and Arabic demonstrate that our approach achieves performance comparable to state-of-the-art supervised models trained on up to 3,000 manually annotated mentions: up to 62.6% F-score for Relation Extraction, and 63.1% F-score for Event Argument Role Labeling. The event argument role labeling model transferred from English to Chinese achieves similar performance as the model trained from Chinese. We thus find that language-universal symbolic and distributional representations are complementary for cross-lingual structure transfer.
We propose a fine-grained entity typing model with a novel attention mechanism and a hybrid type classifier. We advance existing methods in two aspects: feature extraction and type prediction. To capture richer contextual information, we adopt contextualized word representations instead of fixed word embeddings used in previous work. In addition, we propose a two-step mention-aware attention mechanism to enable the model to focus on important words in mentions and contexts. We also present a hybrid classification method beyond binary relevance to exploit type inter-dependency with latent type representation. Instead of independently predicting each type, we predict a low-dimensional vector that encodes latent type features and reconstruct the type vector from this latent representation. Experiment results on multiple data sets show that our model significantly advances the state-of-the-art on fine-grained entity typing, obtaining up to 6.1% and 5.5% absolute gains in macro averaged F-score and micro averaged F-score respectively.
We focus on multiple-choice question answering (QA) tasks in subject areas such as science, where we require both broad background knowledge and the facts from the given subject-area reference corpus. In this work, we explore simple yet effective methods for exploiting two sources of external knowledge for subject-area QA. The first enriches the original subject-area reference corpus with relevant text snippets extracted from an open-domain resource (i.e., Wikipedia) that cover potentially ambiguous concepts in the question and answer options. As in other QA research, the second method simply increases the amount of training data by appending additional in-domain subject-area instances. Experiments on three challenging multiple-choice science QA tasks (i.e., ARC-Easy, ARC-Challenge, and OpenBookQA) demonstrate the effectiveness of our methods: in comparison to the previous state-of-the-art, we obtain absolute gains in accuracy of up to 8.1%, 13.0%, and 12.8%, respectively. While we observe consistent gains when we introduce knowledge from Wikipedia, we find that employing additional QA training instances is not uniformly helpful: performance degrades when the added instances exhibit a higher level of difficulty than the original training data. As one of the first studies on exploiting unstructured external knowledge for subject-area QA, we hope our methods, observations, and discussion of the exposed limitations may shed light on further developments in the area.
Entities, which refer to distinct objects in the real world, can be viewed as language universals and used as effective signals to generate less ambiguous semantic representations and align multiple languages. We propose a novel method, CLEW, to generate cross-lingual data that is a mix of entities and contextual words based on Wikipedia. We replace each anchor link in the source language with its corresponding entity title in the target language if it exists, or in the source language otherwise. A cross-lingual joint entity and word embedding learned from this kind of data not only can disambiguate linkable entities but can also effectively represent unlinkable entities. Because this multilingual common space directly relates the semantics of contextual words in the source language to that of entities in the target language, we leverage it for unsupervised cross-lingual entity linking. Experimental results show that CLEW significantly advances the state-of-the-art: up to 3.1% absolute F-score gain for unsupervised cross-lingual entity linking. Moreover, it provides reliable alignment on both the word/entity level and the sentence level, and thus we use it to mine parallel sentences for all (302, 2) language pairs in Wikipedia.
In this paper we address a challenging cross-lingual name retrieval task. Given an English named entity query, we aim to find all name mentions in documents in low-resource languages. We present a novel method which relies on zero annotation or resources from the target language. By leveraging freely available, cross-lingual resources and a small amount of training data from another language, we are able to perform name retrieval on a new language without any additional training data. Our method proceeds in a multi-step process: first, we pre-train a language-independent orthographic encoder using Wikipedia inter-lingual links from dozens of languages. Next, we gather user expectations about important entities in an English comparable document and compare those expected entities with actual spans of the target language text in order to perform name finding. Our method shows 11.6% absolute F-score improvement over state-of-the-art methods.
In this paper we tackle two unique challenges in biomedical relation extraction. The first challenge is that the contextual information between two entity mentions often involves sophisticated syntactic structures. We propose a novel graph convolutional networks model that incorporates dependency parsing and contextualized embedding to effectively capture comprehensive contextual information. The second challenge is that most of the benchmark data sets for this task are quite imbalanced because more than 80% mention pairs are negative instances (i.e., no relations). We propose a multi-task learning framework to jointly model relation identification and classification tasks to propagate supervision signals from each other and apply a focal loss to focus training on ambiguous mention pairs. By applying these two strategies, experiments show that our model achieves state-of-the-art F-score on the 2013 drug-drug interaction extraction task.
Clustering unlinkable entity mentions across documents in multiple languages (cross-lingual NIL Clustering) is an important task as part of Entity Discovery and Linking (EDL). This task has been largely neglected by the EDL community because it is challenging to outperform simple edit distance or other heuristics based baselines. We propose a novel approach based on encoding the orthographic similarity of the mentions using a Recurrent Neural Network (RNN) architecture. Our model adapts a training procedure from the one-shot facial recognition literature in order to achieve this. We also perform several exploratory probing tasks on our name encodings in order to determine what specific types of information are likely to be encoded by our model. Experiments show our approach provides up to a 6.6% absolute CEAFm F-Score improvement over state-of-the-art methods and successfully captures phonological relations across languages.
We demonstrate ELISA-EDL, a state-of-the-art re-trainable system to extract entity mentions from low-resource languages, link them to external English knowledge bases, and visualize locations related to disaster topics on a world heatmap. We make all of our data sets, resources and system training and testing APIs publicly available for research purpose.
Many name tagging approaches use local contextual information with much success, but can fail when the local context is ambiguous or limited. We present a new framework to improve name tagging by utilizing local, document-level, and corpus-level contextual information. For each word, we retrieve document-level context from other sentences within the same document and corpus-level context from sentences in other documents. We propose a model that learns to incorporate document-level and corpus-level contextual information alongside local contextual information via document-level and corpus-level attentions, which dynamically weight their respective contextual information and determines the influence of this information through gating mechanisms. Experiments on benchmark datasets show the effectiveness of our approach, which achieves state-of-the-art results for Dutch, German, and Spanish on the CoNLL-2002 and CoNLL-2003 datasets. We will make our code and pre-trained models publicly available for research purposes.
We propose a multi-lingual multi-task architecture to develop supervised models with a minimal amount of labeled data for sequence labeling. In this new architecture, we combine various transfer models using two layers of parameter sharing. On the first layer, we construct the basis of the architecture to provide universal word representation and feature extraction capability for all models. On the second level, we adopt different parameter sharing strategies for different transfer schemes. This architecture proves to be particularly effective for low-resource settings, when there are less than 200 training sentences for the target task. Using Name Tagging as a target task, our approach achieved 4.3%-50.5% absolute F-score gains compared to the mono-lingual single-task baseline model.
Everyday billions of multimodal posts containing both images and text are shared in social media sites such as Snapchat, Twitter or Instagram. This combination of image and text in a single message allows for more creative and expressive forms of communication, and has become increasingly common in such sites. This new paradigm brings new challenges for natural language understanding, as the textual component tends to be shorter, more informal, and often is only understood if combined with the visual context. In this paper, we explore the task of name tagging in multimodal social media posts. We start by creating two new multimodal datasets: the first based on Twitter posts and the second based on Snapchat captions (exclusively submitted to public and crowd-sourced stories). We then propose a novel model architecture based on Visual Attention that not only provides deeper visual understanding on the decisions of the model, but also significantly outperforms other state-of-the-art baseline methods for this task.
Most previous supervised event extraction methods have relied on features derived from manual annotations, and thus cannot be applied to new event types without extra annotation effort. We take a fresh look at event extraction and model it as a generic grounding problem: mapping each event mention to a specific type in a target event ontology. We design a transferable architecture of structural and compositional neural networks to jointly represent and map event mentions and types into a shared semantic space. Based on this new framework, we can select, for each event mention, the event type which is semantically closest in this space as its type. By leveraging manual annotations available for a small set of existing event types, our framework can be applied to new unseen event types without additional manual annotations. When tested on 23 unseen event types, our zero-shot framework, without manual annotations, achieved performance comparable to a supervised model trained from 3,000 sentences annotated with 500 event mentions.
We present a paper abstract writing system based on an attentive neural sequence-to-sequence model that can take a title as input and automatically generate an abstract. We design a novel Writing-editing Network that can attend to both the title and the previously generated abstract drafts and then iteratively revise and polish the abstract. With two series of Turing tests, where the human judges are asked to distinguish the system-generated abstracts from human-written ones, our system passes Turing tests by junior domain experts at a rate up to 30% and by non-expert at a rate up to 80%.
We demonstrate two annotation platforms that allow an English speaker to annotate names for any language without knowing the language. These platforms provided high-quality ’‘silver standard” annotations for low-resource language name taggers (Zhang et al., 2017) that achieved state-of-the-art performance on two surprise languages (Oromo and Tigrinya) at LoreHLT20171 and ten languages at TAC-KBP EDL2017 (Ji et al., 2017). We discuss strengths and limitations and compare other methods of creating silver- and gold-standard annotations using native speakers. We will make our tools publicly available for research use.
The primary goals of this tutorial are to review the framework of cross-lingual EL and motivate it as a broad paradigm for the Information Extraction task. We will start by discussing the traditional EL techniques and metrics and address questions relevant to the adequacy of these to across domains and languages. We will then present more recent approaches such as Neural EL, discuss the basic building blocks of a state-of-the-art neural EL system and analyze some of the current results on English EL. We will then proceed to Cross-lingual EL and discuss methods that work across languages. In particular, we will discuss and compare multiple methods that make use of multi-lingual word embeddings. We will also present EL methods that work for both name tagging and linking in very low resource languages. Finally, we will discuss the uses of cross-lingual EL in a variety of applications like search engines and commercial product selling applications. Also, contrary to the 2014 EL tutorial, we will also focus on Entity Discovery which is an essential component of EL.
We present a neural recommendation model for Chengyu, which is a special type of Chinese idiom. Given a query, which is a sentence with an empty slot where the Chengyu is taken out, our model will recommend the best Chengyu candidate that best fits the slot context. The main challenge lies in that the literal meaning of a Chengyu is usually very different from it’s figurative meaning. We propose a new neural approach to leverage the definition of each Chengyu and incorporate it as background knowledge. Experiments on both Chengyu cloze test and coherence checking in college entrance exams show that our system achieves 89.5% accuracy on cloze test and outperforms human subjects who attended competitive universities in China. We will make all of our data sets and resources publicly available as a new benchmark for research purposes.
People often create obfuscated language for online communication to avoid Internet censorship, share sensitive information, express strong sentiment or emotion, plan for secret actions, trade illegal products, or simply hold interesting conversations. In this position paper we systematically categorize human-created obfuscated language on various levels, investigate their basic mechanisms, give an overview on automated techniques needed to simulate human encoding. These encoders have potential to frustrate and evade, co-evolve with dynamic human or automated decoders, and produce interesting and adoptable code words. We also summarize remaining challenges for future research on the interaction between Natural Language Processing (NLP) and encryption, and leveraging NLP techniques for encoding and decoding.
We aim to automatically generate natural language descriptions about an input structured knowledge base (KB). We build our generation framework based on a pointer network which can copy facts from the input KB, and add two attention mechanisms: (i) slot-aware attention to capture the association between a slot type and its corresponding slot value; and (ii) a new table position self-attention to capture the inter-dependencies among related slots. For evaluation, besides standard metrics including BLEU, METEOR, and ROUGE, we propose a KB reconstruction based metric by extracting a KB from the generation output and comparing it with the input KB. We also create a new data set which includes 106,216 pairs of structured KBs and their corresponding natural language descriptions for two distinct entity types. Experiments show that our approach significantly outperforms state-of-the-art methods. The reconstructed KB achieves 68.8% - 72.6% F-score.
We construct a multilingual common semantic space based on distributional semantics, where words from multiple languages are projected into a shared space via which all available resources and knowledge can be shared across multiple languages. Beyond word alignment, we introduce multiple cluster-level alignments and enforce the word clusters to be consistently distributed across multiple languages. We exploit three signals for clustering: (1) neighbor words in the monolingual word embedding space; (2) character-level information; and (3) linguistic properties (e.g., apposition, locative suffix) derived from linguistic structure knowledge bases available for thousands of languages. We introduce a new cluster-consistent correlational neural network to construct the common semantic space by aligning words as well as clusters. Intrinsic evaluation on monolingual and multilingual QVEC tasks shows our approach achieves significantly higher correlation with linguistic features which are extracted from manually crafted lexical resources than state-of-the-art multi-lingual embedding learning methods do. Using low-resource language name tagging as a case study for extrinsic evaluation, our approach achieves up to 14.6% absolute F-score gain over the state of the art on cross-lingual direct transfer. Our approach is also shown to be robust even when the size of bilingual dictionary is small.
Relation Extraction suffers from dramatical performance decrease when training a model on one genre and directly applying it to a new genre, due to the distinct feature distributions. Previous studies address this problem by discovering a shared space across genres using manually crafted features, which requires great human effort. To effectively automate this process, we design a genre-separation network, which applies two encoders, one genre-independent and one genre-shared, to explicitly extract genre-specific and genre-agnostic features. Then we train a relation classifier using the genre-agnostic features on the source genre and directly apply to the target genre. Experiment results on three distinct genres of the ACE dataset show that our approach achieves up to 6.1% absolute F1-score gain compared to previous methods. By incorporating a set of external linguistic features, our approach outperforms the state-of-the-art by 1.7% absolute F1 gain. We make all programs of our model publicly available for research purpose
This paper proposes to study fine-grained coordinated cross-lingual text stream alignment through a novel information network decipherment paradigm. We use Burst Information Networks as media to represent text streams and present a simple yet effective network decipherment algorithm with diverse clues to decipher the networks for accurate text stream alignment. Experiments on Chinese-English news streams show our approach not only outperforms previous approaches on bilingual lexicon extraction from coordinated text streams but also can harvest high-quality alignments from large amounts of streaming data for endless language knowledge mining, which makes it promising to be a new paradigm for automatic language knowledge acquisition.
Most previous efforts toward video captioning focus on generating generic descriptions, such as, “A man is talking.” We collect a news video dataset to generate enriched descriptions that include important background knowledge, such as named entities and related events, which allows the user to fully understand the video content. We develop an approach that uses video meta-data to retrieve topically related news documents for a video and extracts the events and named entities from these documents. Then, given the video as well as the extracted events and entities, we generate a description using a Knowledge-aware Video Description network. The model learns to incorporate entities found in the topically related documents into the description via an entity pointer network and the generation procedure is guided by the event and entity types from the topically related documents through a knowledge gate, which is a gating mechanism added to the model’s decoder that takes a one-hot vector of these types. We evaluate our approach on the new dataset of news videos we have collected, establishing the first benchmark for this dataset as well as proposing a new metric to evaluate these descriptions.
Current image captioning approaches generate descriptions which lack specific information, such as named entities that are involved in the images. In this paper we propose a new task which aims to generate informative image captions, given images and hashtags as input. We propose a simple but effective approach to tackle this problem. We first train a convolutional neural networks - long short term memory networks (CNN-LSTM) model to generate a template caption based on the input image. Then we use a knowledge graph based collective inference algorithm to fill in the template with specific named entities retrieved via the hashtags. Experiments on a new benchmark dataset collected from Flickr show that our model generates news-style image descriptions with much richer information. Our model outperforms unimodal baselines significantly with various evaluation metrics.
Group discussions are usually aimed at sharing opinions, reaching consensus and making good decisions based on group knowledge. During a discussion, participants might adjust their own opinions as well as tune their attitudes towards others’ opinions, based on the unfolding interactions. In this paper, we demonstrate a framework to visualize such dynamics; at each instant of a conversation, the participants’ opinions and potential influence on their counterparts is easily visualized. We use multi-party meeting opinion mining based on bipartite graphs to extract opinions and calculate mutual influential factors, using the Lunar Survival Task as a study case.
Current supervised name tagging approaches are inadequate for most low-resource languages due to the lack of annotated data and actionable linguistic knowledge. All supervised learning methods (including deep neural networks (DNN)) are sensitive to noise and thus they are not quite portable without massive clean annotations. We found that the F-scores of DNN-based name taggers drop rapidly (20%-30%) when we replace clean manual annotations with noisy annotations in the training data. We propose a new solution to incorporate many non-traditional language universal resources that are readily available but rarely explored in the Natural Language Processing (NLP) community, such as the World Atlas of Linguistic Structure, CIA names, PanLex and survival guides. We acquire and encode various types of non-traditional linguistic resources into a DNN name tagger. Experiments on three low-resource languages show that feeding linguistic knowledge can make DNN significantly more robust to noise, achieving 8%-22% absolute F-score gains on name tagging without using any human annotation
Previous open Relation Extraction (open RE) approaches mainly rely on linguistic patterns and constraints to extract important relational triples from large-scale corpora. However, they lack of abilities to cover diverse relation expressions or measure the relative importance of candidate triples within a sentence. It is also challenging to name the relation type of a relational triple merely based on context words, which could limit the usefulness of open RE in downstream applications. We propose a novel importance-based open RE approach by exploiting the global structure of a dependency tree to extract salient triples. We design an unsupervised relation type naming method by grounding relational triples to a large-scale Knowledge Base (KB) schema, leveraging KB triples and weighted context words associated with relational triples. Experiments on the English Slot Filling 2013 dataset demonstrate that our approach achieves 8.1% higher F-score over state-of-the-art open RE methods.
Relation extraction is a fundamental task in information extraction. Most existing methods have heavy reliance on annotations labeled by human experts, which are costly and time-consuming. To overcome this drawback, we propose a novel framework, REHession, to conduct relation extractor learning using annotations from heterogeneous information source, e.g., knowledge base and domain heuristics. These annotations, referred as heterogeneous supervision, often conflict with each other, which brings a new challenge to the original relation extraction task: how to infer the true label from noisy labels for a given instance. Identifying context information as the backbone of both relation extraction and true label discovery, we adopt embedding techniques to learn the distributed representations of context, which bridges all components with mutual enhancement in an iterative fashion. Extensive experimental results demonstrate the superiority of REHession over the state-of-the-art.
We study the problem of identifying the topics and sentiments and tracking their shifts from social media texts in different geographical regions during emergencies and disasters. We propose a location-based dynamic sentiment-topic model (LDST) which can jointly model topic, sentiment, time and Geolocation information. The experimental results demonstrate that LDST performs very well at discovering topics and sentiments from social media and tracking their shifts in different geographical regions during emergencies and disasters. We will release the data and source code after this work is published.
Slot Filling (SF) aims to extract the values of certain types of attributes (or slots, such as person:cities_of_residence) for a given entity from a large collection of source documents. In this paper we propose an effective DNN architecture for SF with the following new strategies: (1). Take a regularized dependency graph instead of a raw sentence as input to DNN, to compress the wide contexts between query and candidate filler; (2). Incorporate two attention mechanisms: local attention learned from query and candidate filler, and global attention learned from external knowledge bases, to guide the model to better select indicative contexts to determine slot type. Experiments show that this framework outperforms state-of-the-art on both relation extraction (16% absolute F-score gain) and slot filling validation for each individual system (up to 8.5% absolute F-score gain).
Learning phrase representations has been widely explored in many Natural Language Processing tasks (e.g., Sentiment Analysis, Machine Translation) and has shown promising improvements. Previous studies either learn non-compositional phrase representations with general word embedding learning techniques or learn compositional phrase representations based on syntactic structures, which either require huge amounts of human annotations or cannot be easily generalized to all phrases. In this work, we propose to take advantage of large-scaled paraphrase database and present a pairwise-GRU framework to generate compositional phrase representations. Our framework can be re-used to generate representations for any phrases. Experimental results show that our framework achieves state-of-the-art results on several phrase similarity tasks.
Integrating text and knowledge into a unified semantic space has attracted significant research interests recently. However, the ambiguity in the common space remains a challenge, namely that the same mention phrase usually refers to various entities. In this paper, to deal with the ambiguity of entity mentions, we propose a novel Multi-Prototype Mention Embedding model, which learns multiple sense embeddings for each mention by jointly modeling words from textual contexts and entities derived from a knowledge base. In addition, we further design an efficient language model based approach to disambiguate each mention to a specific sense. In experiments, both qualitative and quantitative analysis demonstrate the high quality of the word, entity and multi-prototype mention embeddings. Using entity linking as a study case, we apply our disambiguation method as well as the multi-prototype mention embeddings on the benchmark dataset, and achieve state-of-the-art performance.
The ambitious goal of this work is to develop a cross-lingual name tagging and linking framework for 282 languages that exist in Wikipedia. Given a document in any of these languages, our framework is able to identify name mentions, assign a coarse-grained or fine-grained type to each mention, and link it to an English Knowledge Base (KB) if it is linkable. We achieve this goal by performing a series of new KB mining methods: generating “silver-standard” annotations by transferring annotations from English to other languages through cross-lingual links and KB properties, refining annotations through self-training and topic selection, deriving language-specific morphology features from anchor links, and mining word translation pairs from cross-lingual links. Both name tagging and linking results for 282 languages are promising on Wikipedia data and on-Wikipedia data.
Traditional Entity Linking (EL) technologies rely on rich structures and properties in the target knowledge base (KB). However, in many applications, the KB may be as simple and sparse as lists of names of the same type (e.g., lists of products). We call it as List-only Entity Linking problem. Fortunately, some mentions may have more cues for linking, which can be used as seed mentions to bridge other mentions and the uninformative entities. In this work, we select most linkable mentions as seed mentions and disambiguate other mentions by comparing them with the seed mentions rather than directly with the entities. Our experiments on linking mentions to seven automatically mined lists show promising results and demonstrate the effectiveness of our approach.
We present a novel method of comparable corpora construction. Unlike the traditional methods which heavily rely on linguistic features, our method only takes image similarity into consid-eration. We use an image-image search engine to obtain similar images, together with the cap-tions in source language and target language. On the basis, we utilize captions of similar imag-es to construct sentence-level bilingual corpora. Experiments on 10,371 target captions show that our method achieves a precision of 0.85 in the top search results.
Annotation projection is a practical method to deal with the low resource problem in incident languages (IL) processing. Previous methods on annotation projection mainly relied on word alignment results without any training process, which led to noise propagation caused by word alignment errors. In this paper, we focus on the named entity recognition (NER) task and propose a weakly-supervised framework to project entity annotations from English to IL through bitexts. Instead of directly relying on word alignment results, this framework combines advantages of rule-based methods and deep learning methods by implementing two steps: First, generates a high-confidence entity annotation set on IL side with strict searching methods; Second, uses this high-confidence set to weakly supervise the model training. The model is finally used to accomplish the projecting process. Experimental results on two low-resource ILs show that the proposed method can generate better annotations projected from English-IL parallel corpora. The performance of IL name tagger can also be improved significantly by training on the newly projected IL annotation set.
Word Segmentation is usually considered an essential step for many Chinese and Japanese Natural Language Processing tasks, such as name tagging. This paper presents several new observations and analysis on the impact of word segmentation on name tagging; (1). Due to the limitation of current state-of-the-art Chinese word segmentation performance, a character-based name tagger can outperform its word-based counterparts for Chinese but not for Japanese; (2). It is crucial to keep segmentation settings (e.g. definitions, specifications, methods) consistent between training and testing for name tagging; (3). As long as (2) is ensured, the performance of word segmentation does not have appreciable impact on Chinese and Japanese name tagging.
To advance information extraction and question answering technologies toward a more realistic path, the U.S. NIST (National Institute of Standards and Technology) initiated the KBP (Knowledge Base Population) task as one of the TAC (Text Analysis Conference) evaluation tracks. It aims to encourage research in automatic information extraction of named entities from unstructured texts with the ultimate goal of integrating such information into a structured Knowledge Base. The KBP track consists of two types of evaluation: Named Entity Linking (NEL) and Slot Filling. This paper describes the linguistic resource creation efforts at the Linguistic Data Consortium (LDC) in support of Named Entity Linking evaluation of KBP, focusing on annotation methodologies, process, and features of corpora from 2009 to 2011, with a highlighted analysis of the cross-lingual NEL data. Progressing from monolingual to cross-lingual Entity Linking technologies, the 2011 cross-lingual NEL evaluation targeted multilingual capabilities. Annotation accuracy is presented in comparison with system performance, with promising results from cross-lingual entity linking systems.
While the web provides a fantastic linguistic resource, collecting and processing data at web-scale is beyond the reach of most academic laboratories. Previous research has relied on search engines to collect online information, but this is hopelessly inefficient for building large-scale linguistic resources, such as lists of named-entity types or clusters of distributionally similar words. An alternative to processing web-scale text directly is to use the information provided in an N-gram corpus. An N-gram corpus is an efficient compression of large amounts of text. An N-gram corpus states how often each sequence of words (up to length N) occurs. We propose tools for working with enhanced web-scale N-gram corpora that include richer levels of source annotation, such as part-of-speech tags. We describe a new set of search tools that make use of these tags, and collectively lower the barrier for lexical learning and ambiguity resolution at web-scale. They will allow novel sources of information to be applied to long-standing natural language challenges.
In this paper we present a project of annotating event chains for an important scientific domain ― carbon sequestration. This domain aims to reduce carbon emissions and has been identified by the U.S. National Academy of Engineering (NAE) as a grand challenge problem for the 21st century. Given a collection of scientific literature, we identify a set of centroid experiments; and then link and order the observations and events centered around these experiments on temporal or causal chains. We describe the fundamental challenges on annotations and our general solutions to address them. We expect that our annotation efforts will produce significant advances in inter-operability through new information extraction techniques and permit scientists to build knowledge that will provide better understanding of important scientific challenges in this domain, share and re-use of diverse data sets and experimental results in a more efficient manner. In addition, the annotations of metadata and ontology for these literature will provide important support for data lifecycle activities.