Event causality identification (ECI), a process that extracts causal relations between events from text, is crucial for distinguishing causation from correlation. Traditional approaches to ECI have primarily utilized linguistic patterns and multi-hop relational inference, risking false causality identification due to informal usage of causality and specious graphical inference. In this paper, we adopt the Rubin Causal Model to identify event causality: given two temporally ordered events, we see the first event as the treatment and the second one as the observed outcome. Determining their causality involves manipulating the treatment and estimating the resultant change in the likelihood of the outcome. Given that it is only possible to implement manipulation conceptually in the text domain, as a work-around, we try to find a twin for the protagonist from existing corpora. This twin should have identical life experiences with the protagonist before the treatment but undergoes an intervention of treatment. However, the practical difficulty of locating such a match limits its feasibility. Addressing this issue, we use the synthetic control method to generate such a twin’ from relevant historical data, leveraging text embedding synthesis and inversion techniques. This approach allows us to identify causal relations more robustly than previous methods, including GPT-4, which is demonstrated on a causality benchmark, COPES-hard.
This study introduces a hypothesis-testing framework to assess whether large language models (LLMs) possess genuine reasoning abilities or primarily depend on token bias. We go beyond evaluating LLMs on accuracy; rather, we aim to investigate their token bias in solving logical reasoning tasks. Specifically, we develop carefully controlled synthetic datasets, featuring conjunction fallacy and syllogistic problems. Our framework outlines a list of hypotheses where token biases are readily identifiable, with all null hypotheses assuming genuine reasoning capabilities of LLMs. The findings in this study suggest, with statistical guarantee, that most LLMs still struggle with logical reasoning. While they may perform well on classic problems, their success largely depends on recognizing superficial patterns with strong token bias, thereby raising concerns about their actual reasoning and generalization abilities.
Language models, characterized by their black-box nature, often hallucinate and display sensitivity to input perturbations, causing concerns about trust. To enhance trust, it is imperative to gain a comprehensive understanding of the model’s failure modes and develop effective strategies to improve their performance. In this study, we introduce a methodology designed to examine how input perturbations affect language models across various scales, including pre-trained models and large language models (LLMs). Utilizing fine-tuning, we enhance the model’s robustness to input perturbations. Additionally, we investigate whether exposure to one perturbation enhances or diminishes the model’s performance with respect to other perturbations. To address robustness against multiple perturbations, we present three distinct fine-tuning strategies. Furthermore, we broaden the scope of our methodology to encompass large language models (LLMs) by leveraging a chain of thought (CoT) prompting approach augmented with exemplars. We employ the Tabular-NLI task to showcase how our proposed strategies adeptly train a robust model, enabling it to address diverse perturbations while maintaining accuracy on the original dataset.
General-purpose large language models (LLMs) are progressively expanding both in scale and access to unpublic training data. This has led to notable progress in a variety of AI problems. Nevertheless, two questions exist: i) Is scaling up the sole avenue of extending the capabilities of LLMs? ii) Instead of developing general-purpose LLMs, how to endow LLMs with specific knowledge? This tutorial targets researchers and practitioners who are interested in capability extension of LLMs that go beyond scaling up. To this end, we will discuss several lines of research that follow that direction, including (i) the adaptation of LLMs to assimilate new information in situations where conflicts arise, (ii) the adaptation of LLMs to address target problems with inherent constraints, (iii) the customization of LLMs to align with user-specific instructions and preference, (iv) the defense against potential attacks and threads by malicious users, and (v) the collaboration with external models directly or through APIs. At last, we will conclude the tutorial by outlining directions for further investigation.
In this work, we focus on a fundamental yet underexplored problem, event semantic classification in context, to help machines gain a deeper understanding of events. We classify events from six perspectives: modality, affirmation, specificity, telicity, durativity, and kinesis. These properties provide essential cues regarding the occurrence and grounding of events, changes of status that events can bring about, and the connection between events and time. To this end, this paper introduces a novel dataset collected for the semantic classification tasks and several effective models. By incorporating these event properties into downstream tasks, we demonstrate that understanding the fine-grained event semantics benefits downstream event understanding and reasoning via experiments on event extraction, temporal relation extraction, and subevent relation extraction.
Despite remarkable advancements in mitigating hallucinations in large language models (LLMs) by retrieval augmentation, it remains challenging to measure the reliability of LLMs using static question-answering (QA) data. Specifically, given the potential of data contamination (e.g., leading to memorization), good static benchmark performance does not ensure that model can reliably use the provided evidence for responding, which is essential to avoid hallucination when the required knowledge is new or private. Inspired by adversarial machine learning, we investigate the feasibility of automatically perturbing existing static one for dynamic evaluation. Specifically, this paper presents ReEval, an LLM-based framework using prompt chaining to perturb the original evidence for generating new test cases for evaluating the LLMs’ reliability in using new evidence for answering.We implement ReEval using ChatGPT and evaluate the resulting variants of two popular open-domain QA datasets on a collection ofLLMs under various prompting settings. Our generated data is human-readable and useful to trigger hallucination in LLM. Accurate models on static data are observed to produce unsupported answers from the perturbed evidence, with pronounced accuracy drops across LLMs including GPT-4. We find that our adversarial examples are transferable across all considered LLMs. The examples generated by a small model can be used to evaluate a much larger model, making our approach cost-effective.
To comprehensively gauge the capacity of current models for complex reasoning, it is crucial to assess their step-by-step reasoning in a scalable manner. Established reference-based evaluation metrics rely on human-annotated reasoning chains as references to assess the model-derived chains. However, such “gold-standard” human-written reasoning chains may not be unique and their acquisition is often labor-intensive. Existing reference-free reasoning evaluation metrics, while eliminating the need for human-crafted reasoning chains as references, often require fine-tuning with human-derived chains before evaluation, complicating the process and questioning their adaptability to other datasets. To address these challenges, we harness GPT-4 to automatically evaluate reasoning chain quality, thereby removing the dependency on human-written reasoning chains for both model fine-tuning and evaluative purposes. Leveraging the Socratic method, we develop SocREval (**Soc**ratic Method-Inspired **R**easoning **Eval**uation), a novel approach for prompt design in reference-free reasoning evaluation. Empirical results from four human annotated datasets reveal that SocREval significantly improves GPT-4’s performance, surpassing existing reference-free and reference-based reasoning evaluation metrics. Beyond its demonstrated efficacy, SocREval, proves to be both cost-efficient and robust to prompt writing and example selection, as substantiated by our in-depth analysis.
Existing benchmarks for visual question answering lack in visual grounding and complexity, particularly in evaluating spatial reasoning skills. We introduce FlowVQA, a novel benchmark aimed at assessing the capabilities of visual question-answering multimodal language models in reasoning with flowcharts as visual contexts. FlowVQA comprises 2,272 carefully generated and human-verified flowchart images from three distinct content sources, along with 22,413 diverse question-answer pairs, to test a spectrum of reasoning tasks, including information localization, decision-making, and logical progression. We conduct a thorough baseline evaluation on a suite of both open-source and proprietary multimodal language models using various strategies, followed by an analysis of directional bias. The results underscore the benchmark’s potential as a vital tool for advancing the field of multimodal modeling, providing a focused and challenging environment for enhancing model performance in visual and logical reasoning tasks.
Large Language Models (LLMs), excel in natural language understanding, but their capability for complex mathematical reasoning with a hybrid of structured tables and unstructured text remain uncertain. This study explores LLMs’ mathematical reasoning on four financial tabular question-answering datasets: TATQA, FinQA, ConvFinQA, and Multihiertt. Through extensive experiments with various models and prompting techniques, we assess how LLMs adapt to complex tables and mathematical tasks. We focus on sensitivity to table complexity and performance variations with an increasing number of arithmetic reasoning steps. The results provide insights into LLMs’ capabilities and limitations in handling complex mathematical scenarios for semi-structured tables. Ultimately, we introduce a novel prompting technique EEDP tailored to semi-structured documents, matching or outperforming baselines performance while providing a nuanced understanding of LLMs abilities.
In this work, we introduce a novel approach that equips LLM agents with introspection, enhancing consistency and adaptability in solving complex tasks. Our approach prompts LLM agents to decompose a given task into manageable subtasks (i.e., to make a plan), and to continuously introspect upon the suitability and results of their actions. We implement a three-fold introspective intervention: 1) anticipatory reflection on potential failures and alternative remedy before action execution, 2) post-action alignment with subtask objectives and backtracking with remedy to ensure utmost effort in plan execution, and 3) comprehensive review upon plan completion for future strategy refinement. By deploying and experimenting with this methodology—a zero-shot approach—within WebArena for practical tasks in web environments, our agent demonstrates superior performance with a success rate of 23.5% over existing zero-shot methods by 3.5%. The experimental results suggest that our introspection-driven approach not only enhances the agent’s ability to navigate unanticipated challenges through a robust mechanism of plan execution, but also improves efficiency by reducing the number of trials and plan revisions by 45% needed to achieve a task.
Existing datasets for tabular question answering typically focus exclusively on text within cells. However, real-world data is inherently multimodal, often blending images such as symbols, faces, icons, patterns, and charts with textual content in tables. With the evolution of AI models capable of multimodal reasoning, it is pertinent to assess their efficacy in handling such structured data. This study investigates whether current AI models can perform knowledge-aware reasoning on multimodal structured data. We explore their ability to reason on tables that integrate both images and text, introducing MMTabQA, a new dataset designed for this purpose. Our experiments highlight substantial challenges for current AI models in effectively integrating and interpreting multiple text and image inputs, understanding visual context, and comparing visual content across images. These findings establish our dataset as a robust benchmark for advancing AI’s comprehension and capabilities in analyzing multimodal structured data.
Chart question answering (CQA) is a crucial area of Visual Language Understanding. However, the robustness and consistency of current Visual Language Models (VLMs) in this field remain under-explored. This paper evaluates state-of-the-art VLMs on comprehensive datasets, developed specifically for this study, encompassing diverse question categories and chart formats. We investigate two key aspects: 1) the models’ ability to handle varying levels of chart and question complexity, and 2) their robustness across different visual representations of the same underlying data. Our analysis reveals significant performance variations based on question and chart types, highlighting both strengths and weaknesses of current models. Additionally, we identify areas for improvement and propose future research directions to build more robust and reliable CQA systems. This study sheds light on the limitations of current models and paves the way for future advancements in the field.
We introduce sub-sentence encoder, a contrastively-learned contextual embedding model for fine-grained semantic representation of text. In contrast to the standard practice with sentence embeddings, where the meaning of an entire sequence of text is encoded into a fixed-length vector, the sub-sentence encoder learns to produce distinct contextual embeddings corresponding to different atomic propositions, i.e. atomic units of meaning expressed within a text sequence. The sub-sentence embeddings are contrastively learned to recognize (inferred) semantic equivalence between propositions across different text sequences. Our experiments show the effectiveness of sub-sentence encoders in applications, such as retrieving supporting facts for fine-grained text attribution or recognizing the conditional semantic similarity between texts. In practice, we demonstrate that sub-sentence encoders keep the same level of inference cost and space complexity compared to sentence encoders.
As language models are adopted by a more sophisticated and diverse set of users, the importance of guaranteeing that they provide factually correct information supported by verifiable sources is critical across fields of study. This is especially the case for high-stakes fields, such as medicine and law, where the risk of propagating false information is high and can lead to undesirable societal consequences. Previous work studying attribution and factuality has not focused on analyzing these characteristics of language model outputs in domain-specific scenarios. In this work, we conduct human evaluation of responses from a few representative systems along various axes of attribution and factuality, by bringing domain experts in the loop. Specifically, we collect expert-curated questions from 484 participants across 32 fields of study, and then ask the same experts to evaluate generated responses to their own questions. In addition, we ask experts to improve upon responses from language models. The output of our analysis is ExpertQA, a high-quality long-form QA dataset with 2177 questions spanning 32 fields, along with verified answers and attributions for claims in the answers.
Eliciting feedback from end users of NLP models can be beneficial for improving models. However, how should we present model responses to users so they are most amenable to be corrected from user feedback? Further, what properties do users value to understand and trust responses? We answer these questions by analyzing the effect of rationales (or explanations) generated by QA models to support their answers. We specifically consider decomposed QA models that first extract an intermediate rationale based on a context and a question and then use solely this rationale to answer the question. A rationale outlines the approach followed by the model to answer the question. Our work considers various formats of these rationales that vary according to well-defined properties of interest. We sample rationales from language models using few-shot prompting for two datasets, and then perform two user studies. First, we present users with incorrect answers and corresponding rationales in various formats and ask them to provide natural language feedback to revise the rationale. We then measure the effectiveness of this feedback in patching these rationales through in-context learning. The second study evaluates how well different rationale formats enable users to understand and trust model answers, when they are correct. We find that rationale formats significantly affect how easy it is (1) for users to give feedback for rationales, and (2) for models to subsequently execute this feedback. In addition, formats with attributions to the context and in-depth reasoning significantly enhance user-reported understanding and trust of model outputs.
Despite the high performances of large language models (LLMs) across numerous benchmarks, recent research has unveiled their suffering from hallucinations and unfaithful reasoning. This work studies a type of hallucination induced by semantic associations. We investigate to what extent LLMs take shortcuts from certain keyword/entity biases in the prompt instead of following correct reasoning paths. To quantify this phenomenon, we propose a novel probing method and benchmark called EUREQA. EUREQA is an entity-searching task where a model finds a missing entity based on described multi-hop relations with other entities. These deliberately designed multi-hop relations create deceptive semantic associations, and models must stick to the correct reasoning path instead of incorrect shortcuts to find the correct answer.Experiments show that existing LLMs cannot follow correct reasoning paths and resist the attempt of greedy shortcuts, with GPT-4 only achieving 62% accuracy. Analyses provide further evidence that LLMs rely on semantic biases to solve the task instead of proper reasoning, questioning the validity and generalizability of current LLMs’ high performances.
In this position paper, we argue that human evaluation of generative large language models (LLMs) should be a multidisciplinary undertaking that draws upon the insights from disciplines such as user experience research and human behavioral psychology to ensure that the experimental design and results are reliable. The conclusions from these evaluations, therefore, must consider factors such as usability, aesthetics and cognitive biases. We highlight how cognitive biases can conflate fluent information and truthfulness, and how cognitive uncertainty affects the reliability of rating scores such as Likert. Furthermore, the evaluation should differentiate the capabilities and weaknesses of increasingly powerful large language models - which requires effective test sets. Scalability of human evaluation is also crucial to wider adoption. Hence, to design an effective human evaluation system in the age of generative NLP we propose the ConSiDERS-The-Human evaluation framework consisting of 6 pillars - Consistency, Scoring Criteria, Differentiating, User Experience, Responsible, and Scalability.
Retrieving relevant tables containing the necessary information to accurately answer a given question over tables is critical to open-domain question-answering (QA) systems. Previous methods assume the answer to such a question can be found either in a single table or multiple tables identified through question decomposition or rewriting. However, neither of these approaches is sufficient, as many questions require retrieving multiple tables and joining them through a join plan that cannot be discerned from the user query itself. If the join plan is not considered in the retrieval stage, the subsequent steps of reasoning and answering based on those retrieved tables are likely to be incorrect. To address this problem, we introduce a method that uncovers useful join relations for any query and database during table retrieval. We use a novel re-ranking method formulated as a mixed-integer program that considers not only table-query relevance but also table-table relevance that requires inferring join relationships. Our method outperforms the state-of-the-art approaches for table retrieval by up to 9.3% in F1 score and for end-to-end QA by up to 5.4% in accuracy.
While pre-trained language models (LM) for code have achieved great success in code completion, they generate code conditioned only on the contents within the file, i.e., in-file context, but ignore the rich semantics in other files within the same project, i.e., project-level cross-file context, a critical source of information that is especially useful in modern modular software development. Such overlooking constrains code LMs’ capacity in code completion, leading to unexpected behaviors such as generating hallucinated class member functions or function calls with unexpected arguments. In this work, we propose CoCoMIC, a novel framework that jointly learns the in-file and cross-file context on top of code LMs. To empower CoCoMIC, we develop CCFinder, a static-analysis-based tool that locates and retrieves the most relevant project-level cross-file context for code completion. CoCoMIC successfully improves the existing code LM with a 33.94% relative increase in exact match and 28.69% in identifier matching for code completion when the cross-file context is provided. Finally, we perform a series of ablation studies and share valuable insights for future research on integrating cross-file context into code LMs.
Named Entity Recognition (NER) is a core natural language processing task in which pre-trained language models have shown remarkable performance. However, standard benchmarks like CoNLL 2003 do not address many of the challenges that deployed NER systems face, such as having to classify emerging or complex entities in a fine-grained way. In this paper we present a novel NER cascade approach comprising three steps: first, identifying candidate entities in the input sentence; second, linking the each candidate to an existing knowledge base; third, predicting the fine-grained category for each entity candidate. We empirically demonstrate the significance of external knowledge bases in accurately classifying fine-grained and emerging entities. Our system exhibits robust performance in the MultiCoNER2 shared task, even in the low-resource language setting where we leverage knowledge bases of high-resource languages.
NLP models often degrade in performance when real world data distributions differ markedly from training data. However, existing dataset drift metrics in NLP have generally not considered specific dimensions of linguistic drift that affect model performance, and they have not been validated in their ability to predict model performance at the individual example level, where such metrics are often used in practice. In this paper, we propose three dimensions of linguistic dataset drift: vocabulary, structural, and semantic drift. These dimensions correspond to content word frequency divergences, syntactic divergences, and meaning changes not captured by word frequencies (e.g. lexical semantic change). We propose interpretable metrics for all three drift dimensions, and we modify past performance prediction methods to predict model performance at both the example and dataset level for English sentiment classification and natural language inference. We find that our drift metrics are more effective than previous metrics at predicting out-of-domain model accuracies (mean 16.8% root mean square error decrease), particularly when compared to popular fine-tuned embedding distances (mean 47.7% error decrease). Fine-tuned embedding distances are much more effective at ranking individual examples by expected performance, but decomposing into vocabulary, structural, and semantic drift produces the best example rankings of all considered model-agnostic drift metrics (mean 6.7% ROC AUC increase).
Language models have been shown to perform better with an increase in scale on a wide variety of tasks via the in-context learning paradigm. In this paper, we investigate the hypothesis that the ability of a large language model to in-context learn-perform a task is not uniformly spread across all of its underlying components. Using a 66 billion parameter language model (OPT-66B) across a diverse set of 14 downstream tasks, we find this is indeed the case: ~70% of the attention heads and ~20% of the feed forward networks can be removed with minimal decline in task performance. We find substantial overlap in the set of attention heads (un)important for in-context learning across tasks and number of in-context examples. We also address our hypothesis through a task-agnostic lens, finding that a small set of attention heads in OPT-66B score highly on their ability to perform primitive induction operations associated with in-context learning, namely, prefix matching and copying. These induction heads overlap with task-specific important heads, reinforcing arguments by Olsson et al. (2022) regarding induction head generality to more sophisticated behaviors associated with in-context learning. Overall, our study provides several insights that indicate large language models may be under-trained for in-context learning and opens up questions on how to pre-train language models to more effectively perform in-context learning.
Temporal reasoning is the task of predicting temporal relations of event pairs. While temporal reasoning models can perform reasonably well on in-domain benchmarks, we have little idea of these systems’ generalizability due to existing datasets’ limitations. In this work, we introduce a novel task named TODAY that bridges this gap with temporal differential analysis, which as the name suggests, evaluates whether systems can correctly understand the effect of incremental changes. Specifically, TODAY introduces slight contextual changes for given event pairs, and systems are asked to tell how this subtle contextual change would affect relevant temporal relation distributions. To facilitate learning, TODAY also annotates human explanations. We show that existing models, including GPT-3.5, drop to random guessing on TODAY, suggesting that they heavily rely on spurious information rather than proper reasoning for temporal predictions. On the other hand, we show that TODAY’s supervision style and explanation annotations can be used in joint learning, encouraging models to use more appropriate signals during training and thus outperform across several benchmarks. TODAY can also be used to train models to solicit incidental supervision from noisy sources such as GPT-3.5, thus moving us more toward the goal of generic temporal reasoning systems.
Code generation models have achieved impressive performance. However, they tend to be brittle as slight edits to a prompt could lead to very different generations; these robustness properties, critical for user experience when deployed in real-life applications, are not well understood. Most existing works on robustness in text or code tasks have focused on classification, while robustness in generation tasks is an uncharted area and to date there is no comprehensive benchmark for robustness in code generation. In this paper, we propose ReCode, a comprehensive robustness evaluation benchmark for code generation models. We customize over 30 transformations specifically for code on docstrings, function and variable names, code syntax, and code format. They are carefully designed to be natural in real-life coding practice, preserve the original semantic meaning, and thus provide multifaceted assessments of a model’s robustness performance. With human annotators, we verified that over 90% of the perturbed prompts do not alter the semantic meaning of the original prompt. In addition, we define robustness metrics for code generation models considering the worst-case behavior under each type of perturbation, taking advantage of the fact that executing the generated code can serve as objective evaluation. We demonstrate ReCode on SOTA models using HumanEval, MBPP, as well as function completion tasks derived from them. Interesting observations include: better robustness for CodeGen over InCoder and GPT-J; models are most sensitive to syntax perturbations; more challenging robustness evaluation on MBPP over HumanEval.
In this paper, we present a novel approach for data-to-text generation that addresses the limitations of current methods that primarily focus on specific types of structured data. Our proposed method aims to improve performance in multi-task training, zero-shot and few-shot scenarios by providing a unified representation that can handle various forms of structured data such as tables, knowledge graph triples, and meaning representations. We demonstrate that our proposed approach can effectively adapt to new structured forms, and can improve performance in comparison to current methods. For example, our method resulted in a 66% improvement in zero-shot BLEU scores when transferring models trained on table inputs to a knowledge graph dataset. Our proposed method is an important step towards a more general data-to-text generation framework.
Recently it has been shown that state-of-the-art NLP models are vulnerable to adversarial attacks, where the predictions of a model can be drastically altered by slight modifications to the input (such as synonym substitutions). While several defense techniques have been proposed, and adapted, to the discrete nature of text adversarial attacks, the benefits of general-purpose regularization methods such as label smoothing for language models, have not been studied. In this paper, we study the adversarial robustness provided by label smoothing strategies in foundational models for diverse NLP tasks in both in-domain and out-of-domain settings. Our experiments show that label smoothing significantly improves adversarial robustness in pre-trained models like BERT, against various popular attacks. We also analyze the relationship between prediction confidence and robustness, showing that label smoothing reduces over-confident errors on adversarial examples.
This tutorial targets researchers and practitioners who are interested in ML technologies for NLP from indirect supervision. In particular, we will present a diverse thread of indirect supervision studies that try to answer the following questions: (i) when and how can we provide supervision for a target task T, if all we have is data that corresponds to a “related” task T′? (ii) humans do not use exhaustive supervision; they rely on occasional feedback, and learn from incidental signals from various sources; how can we effectively incorporate such supervision in machine learning? (iii) how can we leverage multi-modal supervision to help NLP? To the end, we will discuss several lines of research that address those challenges, including (i) indirect supervision from T ′ that handles T with outputs spanning from a moderate size to an open space, (ii) the use of sparsely occurring and incidental signals, such as partial labels, noisy labels, knowledge-based constraints, and cross-domain or cross-task annotations—all having statistical associations with the task, (iii) principled ways to measure and understand why these incidental signals can contribute to our target tasks, and (iv) indirect supervision from vision-language signals. We will conclude the tutorial by outlining directions for further investigation.
We propose a new commonsense reasoning benchmark to motivate commonsense reasoning progress from two perspectives: (1) Evaluating whether models can distinguish knowledge quality by predicting if the knowledge is enough to answer the question; (2) Evaluating whether models can develop commonsense inference capabilities that generalize across tasks. We first extract supporting knowledge for each question and ask humans to annotate whether the auto-extracted knowledge is enough to answer the question or not. After that, we convert different tasks into a unified question-answering format to evaluate the models’ generalization capabilities. We name the benchmark Commonsense Inference with Knowledge-in-the-loop Question Answering (\name). Experiments show that with our learning paradigm, models demonstrate encouraging generalization capabilities. At the same time, we also notice that distinguishing knowledge quality remains challenging for current commonsense reasoning models.
What are the events involved in a pandemic outbreak? What steps should be taken when planning a wedding? The answers to these questions can be found by collecting many documents on the complex event of interest, extracting relevant information, and analyzing it. We present a new approach in which large language models are utilized to generate source documents that allow predicting, given a high-level event definition, the specific events, arguments, and relations between them to construct a schema that describes the complex event in its entirety. Using our model, complete schemas on any topic can be generated on-the-fly without any manual data collection, i.e., in a zero-shot manner. Moreover, we develop efficient methods to extract pertinent information from texts and demonstrate in a series of experiments that these schemas are considered to be more complete than human-curated ones in the majority of examined scenarios. Finally, we show that this framework is comparable in performance with previous supervised schema induction methods that rely on collecting real texts and even reaching the best score in the prediction task.
The open-ended Visual Question Answering (VQA) task requires AI models to jointly reason over visual and natural language inputs using world knowledge. Recently, pre-trained Language Models (PLM) such as GPT-3 have been applied to the task and shown to be powerful world knowledge sources. However, these methods suffer from low knowledge coverage caused by PLM bias – the tendency to generate certain tokens over other tokens regardless of prompt changes, and high dependency on the PLM quality – only models using GPT-3 can achieve the best result. To address the aforementioned challenges, we propose RASO: a new VQA pipeline that deploys a generate-then-select strategy guided by world knowledge for the first time. Rather than following the de facto standard to train a multi-modal model that directly generates the VQA answer, {pasted macro ‘MODEL’}name first adopts PLM to generate all the possible answers, and then trains a lightweight answer selection model for the correct answer. As proved in our analysis, RASO expands the knowledge coverage from in-domain training data by a large margin. We provide extensive experimentation and show the effectiveness of our pipeline by advancing the state-of-the-art by 4.1% on OK-VQA, without additional computation cost.
Open-domain question answering (ODQA) is a crucial task in natural language processing. A typical ODQA system relies on a retriever module to select relevant contexts from a large corpus for a downstream reading comprehension model. Existing ODQA datasets consist mainly of Wikipedia corpus, and are insufficient to study models’ generalizability across diverse domains as models are trained and evaluated on the same genre of data. We propose **RobustQA**, a novel benchmark consisting of datasets from 8 different domains, which facilitates the evaluation of ODQA’s domain robustness. To build **RobustQA**, we annotate QA pairs in retrieval datasets with rigorous quality control. We further examine improving QA performances by incorporating unsupervised learning methods with target-domain corpus and adopting large generative language models. These methods can effectively improve model performances on **RobustQA**. However, experimental results demonstrate a significant gap from in-domain training, suggesting that **RobustQA** is a challenging benchmark to evaluate ODQA domain robustness.
The widely studied task of Natural Language Inference (NLI) requires a system to recognize whether one piece of text is textually entailed by another, i.e. whether the entirety of its meaning can be inferred from the other. In current NLI datasets and models, textual entailment relations are typically defined on the sentence- or paragraph-level. However, even a simple sentence often contains multiple propositions, i.e. distinct units of meaning conveyed by the sentence. As these propositions can carry different truth values in the context of a given premise, we argue for the need to recognize the textual entailment relation of each proposition in a sentence individually. We propose PropSegmEnt, a corpus of over 45K propositions annotated by expert human raters. Our dataset structure resembles the tasks of (1) segmenting sentences within a document to the set of propositions, and (2) classifying the entailment relation of each proposition with respect to a different yet topically-aligned document, i.e. documents describing the same event or entity. We establish strong baselines for the segmentation and entailment tasks. Through case studies on summary hallucination detection and document-level NLI, we demonstrate that our conceptual framework is potentially useful for understanding and explaining the compositionality of NLI labels.
Understanding and characterizing the discus- sions around key events in news streams is important for analyzing political discourse. In this work, we study the problem of identification of such key events and the news articles associated with those events from news streams. We propose a generic framework for news stream clustering that analyzes the temporal trend of news articles to automatically extract the underlying key news events that draw significant media attention. We characterize such key events by generating event summaries, based on which we form document clusters in an unsupervised fashion. We evaluate our simple yet effective framework, and show that it produces more coherent event-focused clusters. To demonstrate the utility of our approach, and facilitate future research along the line, we use our framework to construct KeyEvents, a dataset of 40k articles with 611 key events from 11 topics.
BabyBERTa, a language model trained on small-scale child-directed speech while none of the words are unmasked during training, has been shown to achieve a level of grammaticality comparable to that of RoBERTa-base, which is trained on 6,000 times more words and 15 times more parameters. Relying on this promising result, we explore in this paper the performance of BabyBERTa-based models in downstream tasks, focusing on Semantic Role Labeling (SRL) and two Extractive Question Answering tasks, with the aim of building more efficient systems that rely on less data and smaller models. We investigate the influence of these models both alone and as a starting point to larger pre-trained models, separately examining the contribution of the pre-training data, the vocabulary, and the masking policy on the downstream task performance. Our results show that BabyBERTa trained with unmasking-removal policy is a much stronger starting point for downstream tasks compared to the use of RoBERTa masking policy when 10M words are used for training and that this tendency persists, although to a lesser extent, when adding more training data.
Natural language often describes events in different granularities, such that more coarse-grained (goal) events can often be decomposed into fine-grained sequences of (step) events. A critical but overlooked challenge in understanding an event process lies in the fact that the step events are not equally important to the central goal. In this paper, we seek to fill this gap by studying how well current models can understand the essentiality of different step events towards a goal event. As discussed by cognitive studies, such an ability enables the machine to mimic human’s commonsense reasoning about preconditions and necessary efforts of daily-life tasks. Our work contributes with a high-quality corpus of (goal, step) pairs from a community guideline website WikiHow, where the steps are manually annotated with their essentiality w.r.t. the goal. The high IAA indicates that humans have a consistent understanding of the events. Despite evaluating various statistical and massive pre-trained NLU models, we observe that existing SOTA models all perform drastically behind humans, indicating the need for future investigation of this crucial yet challenging task.
Training a Named Entity Recognition (NER) model often involves fixing a taxonomy of entity types. However, requirements evolve and we might need the NER model to recognize additional entity types. A simple approach is to re-annotate entire dataset with both existing and additional entity types and then train the model on the re-annotated dataset. However, this is an extremely laborious task. To remedy this, we propose a novel approach called Partial Label Model (PLM) that uses only partially annotated datasets. We experiment with 6 diverse datasets and show that PLM consistently performs better than most other approaches (0.5 - 2.5 F1), including in novel settings for taxonomy expansion not considered in prior work. The gap between PLM and all other approaches is especially large in settings where there is limited data available for the additional entity types (as much as 11 F1), thus suggesting a more cost effective approaches to taxonomy expansion.
Studies in bias and fairness in natural language processing have primarily examined social biases within a single language and/or across few attributes (e.g. gender, race). However, biases can manifest differently across various languages for individual attributes. As a result, it is critical to examine biases within each language and attribute. Of equal importance is to study how these biases compare across languages and how the biases are affected when training a model on multilingual data versus monolingual data. We present a bias analysis across Italian, Chinese, English, Hebrew, and Spanish on the downstream sentiment analysis task to observe whether specific demographics are viewed more positively. We study bias similarities and differences across these languages and investigate the impact of multilingual vs. monolingual training data. We adapt existing sentiment bias templates in English to Italian, Chinese, Hebrew, and Spanish for four attributes: race, religion, nationality, and gender. Our results reveal similarities in bias expression such as favoritism of groups that are dominant in each language’s culture (e.g. majority religions and nationalities). Additionally, we find an increased variation in predictions across protected groups, indicating bias amplification, after multilingual finetuning in comparison to multilingual pretraining.
In this paper, we seek to improve the faithfulness of TempRel extraction models from two perspectives. The first perspective is to extract genuinely based on contextual description. To achieve this, we propose to conduct counterfactual analysis to attenuate the effects of two significant types of training biases: the event trigger bias and the frequent label bias. We also add tense information into event representations to explicitly place an emphasis on the contextual description. The second perspective is to provide proper uncertainty estimation and abstain from extraction when no relation is described in the text. By parameterization of Dirichlet Prior over the model-predicted categorical distribution, we improve the model estimates of the correctness likelihood and make TempRel predictions more selective. We also employ temperature scaling to recalibrate the model confidence measure after bias mitigation. Through experimental analysis on MATRES, MATRES-DS, and TDDiscourse, we demonstrate that our model extracts TempRel and timelines more faithfully compared to SOTA methods, especially under distribution shifts.
In this work, we propose a method for incorporating question-answering (QA) signals into a summarization model. Our method identifies salient noun phrases (NPs) in the input document by automatically generating wh-questions that are answered by the NPs and automatically determining whether those questions are answered in the gold summaries. This QA-based signal is incorporated into a two-stage summarization model which first marks salient NPs in the input document using a classification model, then conditionally generates a summary. Our experiments demonstrate that the models trained using QA-based supervision generate higher-quality summaries than baseline methods of identifying salient spans on benchmark summarization datasets. Further, we show that the content of the generated summaries can be controlled based on which NPs are marked in the input document. Finally, we propose a method of augmenting the training data so the gold summaries are more consistent with the marked input spans used during training and show how this results in models which learn to better exclude unmarked document content.
Comprehending an article requires understanding its constituent events. However, the context where an event is mentioned often lacks the details of this event. A question arises: how can the reader obtain more knowledge about this particular event in addition to what is provided by the local context in the article? This work defines Event Linking, a new natural language understanding task at the event level. Event linking tries to link an event mention appearing in an article to the most appropriate Wikipedia page. This page is expected to provide rich knowledge about what the event mention refers to. To standardize the research in this new direction, we contribute in four-fold. First, this is the first work in the community that formally defines the Event Linking task. Second, we collect a dataset for this new task. Specifically, we automatically gather the training set from Wikipedia, and then create two evaluation sets: one from the Wikipedia domain, reporting the in-domain performance, and a second from the real-world news domain, to evaluate out-of-domain performance. Third, we retrain and evaluate two state-of-the-art (SOTA) entity linking models, showing the challenges of event linking, and we propose an event-specific linking system, EVELINK, to set a competitive result for the new task. Fourth, we conduct a detailed and insightful analysis to help understand the task and the limitations of the current model. Overall, as our analysis shows, Event Linking is a challenging and essential task requiring more effort from the community.
Aspect-based Sentiment Analysis (ABSA) is a fine-grained sentiment analysis task which involves four elements from user-generated texts:aspect term, aspect category, opinion term, and sentiment polarity. Most computational approaches focus on some of the ABSA sub-taskssuch as tuple (aspect term, sentiment polarity) or triplet (aspect term, opinion term, sentiment polarity) extraction using either pipeline or joint modeling approaches. Recently, generative approaches have been proposed to extract all four elements as (one or more) quadrupletsfrom text as a single task. In this work, we take a step further and propose a unified framework for solving ABSA, and the associated sub-tasksto improve the performance in few-shot scenarios. To this end, we fine-tune a T5 model with instructional prompts in a multi-task learning fashion covering all the sub-tasks, as well as the entire quadruple prediction task. In experiments with multiple benchmark datasets, we show that the proposed multi-task prompting approach brings performance boost (by absolute 8.29 F1) in the few-shot learning setting.
We present our system that participated in the shared task on the grammatical error correction of Ukrainian. We have implemented two approaches that make use of large pre-trained language models and synthetic data, that have been used for error correction of English as well as low-resource languages. The first approach is based on fine-tuning a large multilingual language model (mT5) in two stages: first, on synthetic data, and then on gold data. The second approach trains a (smaller) seq2seq Transformer model pre-trained on synthetic data and fine-tuned on gold data. Our mT5-based model scored first in “GEC only” track, and a very close second in the “GEC+Fluency” track. Our two key innovations are (1) finetuning in stages, first on synthetic, and then on gold data; and (2) a high-quality corruption method based on roundtrip machine translation to complement existing noisification approaches.
The Yes/No QA task (Clark et al., 2019) consists of “Yes” or “No” questions about a given context. However, in realistic scenarios, the information provided in the context is not always sufficient in order to answer the question. For example, given the context “She married a lawyer from New-York.”, we don’t know whether the answer to the question “Did she marry in New York?” is “Yes” or “No”. In this paper, we extend the Yes/No QA task, adding questions with an IDK answer, and show its considerable difficulty compared to the original 2-label task. For this purpose, we (i) enrich the BoolQ dataset (Clark et al., 2019) to include unanswerable questions and (ii) create out-of-domain test sets for the Yes/No/IDK QA task. We study the contribution of training on other Natural Language Understanding tasks. We focus in particular on Extractive QA (Rajpurkar et al., 2018) and Recognizing Textual Entailments (RTE; Dagan et al., 2013), analyzing the differences between 2 and 3 labels using the new data.
How reliably an automatic summarization evaluation metric replicates human judgments of summary quality is quantified by system-level correlations. We identify two ways in which the definition of the system-level correlation is inconsistent with how metrics are used to evaluate systems in practice and propose changes to rectify this disconnect. First, we calculate the system score for an automatic metric using the full test set instead of the subset of summaries judged by humans, which is currently standard practice. We demonstrate how this small change leads to more precise estimates of system-level correlations. Second, we propose to calculate correlations only on pairs of systems that are separated by small differences in automatic scores which are commonly observed in practice. This allows us to demonstrate that our best estimate of the correlation of ROUGE to human judgments is near 0 in realistic scenarios. The results from the analyses point to the need to collect more high-quality human judgments and to improve automatic metrics when differences in system scores are small.
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.
We introduce an open-domain topic classification system that accepts user-defined taxonomy in real time. Users will be able to classify a text snippet with respect to any candidate labels they want, and get instant response from our web interface. To obtain such flexibility, we build the backend model in a zero-shot way. By training on a new dataset constructed from Wikipedia, our label-aware text classifier can effectively utilize implicit knowledge in the pretrained language model to handle labels it has never seen before. We evaluate our model across four datasets from various domains with different label sets. Experiments show that the model significantly improves over existing zero-shot baselines in open-domain scenarios, and performs competitively with weakly-supervised models trained on in-domain data.
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.
Users often leave feedback on a myriad of aspects of a product which, if leveraged successfully, can help yield useful insights that can lead to further improvements down the line. Detecting actionable insights can be challenging owing to large amounts of data as well as the absence of labels in real-world scenarios. In this work, we present an aggregation and graph-based ranking strategy for unsupervised detection of these insights from real-world, noisy, user-generated feedback. Our proposed approach significantly outperforms strong baselines on two real-world user feedback datasets and one academic dataset.
A wealth of important clinical information lies untouched in the Electronic Health Record, often in the form of unstructured textual documents. For patients with Epilepsy, such information includes outcome measures like Seizure Frequency and Dates of Last Seizure, key parameters that guide all therapy for these patients. Transformer models have been able to extract such outcome measures from unstructured clinical note text as sentences with human-like accuracy; however, these sentences are not yet usable in a quantitative analysis for large-scale studies. In this study, we developed a pipeline to quantify these outcome measures. We used text summarization models to convert unstructured sentences into specific formats, and then employed rules-based quantifiers to calculate seizure frequencies and dates of last seizure. We demonstrated that our pipeline of models does not excessively propagate errors and we analyzed its mistakes. We anticipate that our methods can be generalized outside of epilepsy to other disorders to drive large-scale clinical research.
Images are often more significant than only the pixels to human eyes, as we can infer, associate, and reason with contextual information from other sources to establish a more complete picture. For example, in Figure 1, we can find a way to identify the news articles related to the picture through segment-wise understandings of the signs, the buildings, the crowds, and more. This reasoning could provide the time and place the image was taken, which will help us in subsequent tasks, such as automatic storyline construction, correction of image source in intended effect photographs, and upper-stream processing such as image clustering for certain location or time. In this work, we formulate this problem and introduce TARA: a dataset with 16k images with their associated news, time, and location, automatically extracted from New York Times, and an additional 61k examples as distant supervision from WIT. On top of the extractions, we present a crowdsourced subset in which we believe it is possible to find the images’ spatio-temporal information for evaluation purpose. We show that there exists a 70% gap between a state-of-the-art joint model and human performance, which is slightly filled by our proposed model that uses segment-wise reasoning, motivating higher-level vision-language joint models that can conduct open-ended reasoning with world knowledge. The data and code are publicly available at https://github.com/zeyofu/TARA.
In text classification tasks, useful information is encoded in the label names. Label semantic aware systems have leveraged this information for improved text classification performance during fine-tuning and prediction. However, use of label-semantics during pre-training has not been extensively explored. We therefore propose Label Semantic Aware Pre-training (LSAP) to improve the generalization and data efficiency of text classification systems. LSAP incorporates label semantics into pre-trained generative models (T5 in our case) by performing secondary pre-training on labeled sentences from a variety of domains. As domain-general pre-training requires large amounts of data, we develop a filtering and labeling pipeline to automatically create sentence-label pairs from unlabeled text. We perform experiments on intent (ATIS, Snips, TOPv2) and topic classification (AG News, Yahoo! Answers). LSAP obtains significant accuracy improvements over state-of-the-art models for few-shot text classification while maintaining performance comparable to state of the art in high-resource settings.
Large-scale pre-trained sequence-to-sequence models like BART and T5 achieve state-of-the-art performance on many generative NLP tasks. However, such models pose a great challenge in resource-constrained scenarios owing to their large memory requirements and high latency. To alleviate this issue, we propose to jointly distill and quantize the model, where knowledge is transferred from the full-precision teacher model to the quantized and distilled low-precision student model. Empirical analyses show that, despite the challenging nature of generative tasks, we were able to achieve a 16.5x model footprint compression ratio with little performance drop relative to the full-precision counterparts on multiple summarization and QA datasets. We further pushed the limit of compression ratio to 27.7x and presented the performance-efficiency trade-off for generative tasks using pre-trained models. To the best of our knowledge, this is the first work aiming to effectively distill and quantize sequence-to-sequence pre-trained models for language generation tasks.
Explicit decomposition modeling, which involves breaking down complex tasks into more straightforward and often more interpretable sub-tasks, has long been a central theme in developing robust and interpretable NLU systems. However, despite the many datasets and resources built as part of this effort, the majority have small-scale annotations and limited scope, which is insufficient to solve general decomposition tasks. In this paper, we look at large-scale intermediate pre-training of decomposition-based transformers using distant supervision from comparable texts, particularly large-scale parallel news. We show that with such intermediate pre-training, developing robust decomposition-based models for a diverse range of tasks becomes more feasible. For example, on semantic parsing, our model, DecompT5, improves 20% to 30% on two datasets, Overnight and TORQUE, over the baseline language model. We further use DecompT5 to build a novel decomposition-based QA system named DecompEntail, improving over state-of-the-art models, including GPT-3, on both HotpotQA and StrategyQA by 8% and 4%, respectively.
There is significant interest in developing evaluation metrics which accurately estimate the quality of generated text without the aid of a human-written reference text, which can be time consuming and expensive to collect or entirely unavailable in online applications. However, in this work, we demonstrate that these reference-free metrics are inherently biased and limited in their ability to evaluate generated text, and we argue that they should not be used to measure progress on tasks like machine translation or summarization. We show how reference-free metrics are equivalent to using one generation model to evaluate another, which has several limitations: (1) the metrics can be optimized at test time to find the approximate best-possible output, (2) they are inherently biased toward models which are more similar to their own, and (3) they can be biased against higher-quality outputs, including those written by humans. Therefore, we recommend that reference-free metrics should be used as diagnostic tools for analyzing and understanding model behavior instead of measures of how well models perform a task, in which the goal is to achieve as high of a score as possible.
We study the problem of few shot learning for named entity recognition. Specifically, we leverage the semantic information in the names of the labels as a way of giving the model additional signal and enriched priors. We propose a neural architecture that consists of two BERT encoders, one to encode the document and its tokens and another one to encode each of the labels in natural language format. Our model learns to match the representations of named entities computed by the first encoder with label representations computed by the second encoder. The label semantics signal is shown to support improved state-of-the-art results in multiple few shot NER benchmarks and on-par performance in standard benchmarks. Our model is especially effective in low resource settings.
Question answering-based summarization evaluation metrics must automatically determine whether the QA model’s prediction is correct or not, a task known as answer verification. In this work, we benchmark the lexical answer verification methods which have been used by current QA-based metrics as well as two more sophisticated text comparison methods, BERTScore and LERC. We find that LERC out-performs the other methods in some settings while remaining statistically indistinguishable from lexical overlap in others. However, our experiments reveal that improved verification performance does not necessarily translate to overall QA-based metric quality: In some scenarios, using a worse verification method — or using none at all — has comparable performance to using the best verification method, a result that we attribute to properties of the datasets.
Previous studies on question answering over knowledge graphs have typically operated over a single knowledge graph (KG). This KG is assumed to be known a priori and is lever- aged similarly for all users’ queries during inference. However, such an assumption is not applicable to real-world settings, such as health- care, where one needs to handle queries of new users over unseen KGs during inference. Furthermore, privacy concerns and high computational costs render it infeasible to query the single KG that has information about all users while answering a specific user’s query. The above concerns motivate our question answer- ing setting over personalized knowledge graphs (PERKGQA) where each user has restricted access to their KG. We observe that current state-of-the-art KGQA methods that require learning prior node representations fare poorly. We propose two complementary approaches, PATHCBR and PATHRGCN for PERKGQA. The former is a simple non-parametric technique that employs case-based reasoning, while the latter is a parametric approach using graph neural networks. Our proposed methods circumvent learning prior representations, can generalize to unseen KGs, and outperform strong baselines on an academic and an internal dataset by 6.5% and 10.5%.
Many users turn to document retrieval systems (e.g. search engines) to seek answers to controversial or open-ended questions. However, classical document retrieval systems fall short at delivering users a set of direct and diverse responses in such cases, which requires identifying responses within web documents in the context of the query, and aggregating the responses based on their different perspectives. The goal of this work is to survey and study the user information needs for building a multi-perspective search engine of such. We examine the challenges of synthesizing such language understanding objectives with document retrieval, and study a new perspective-oriented document retrieval paradigm. We discuss and assess the inherent natural language understanding challenges one needs to address in order to achieve the goal. Following the design challenges and principles, we propose and evaluate a practical prototype pipeline system. We use the prototype system to conduct a user survey in order to assess the utility of our paradigm, as well as understanding the user information needs when issuing controversial and open-ended queries to a search engine.
Large language models have achieved high performance on various question answering (QA) benchmarks, but the explainability of their output remains elusive. Structured explanations, called entailment trees, were recently suggested as a way to explain the reasoning behind a QA system’s answer. In order to better generate such entailment trees, we propose an architecture called Iterative Retrieval-Generation Reasoner (IRGR). Our model is able to explain a given hypothesis by systematically generating a step-by-step explanation from textual premises. The IRGR model iteratively searches for suitable premises, constructing a single entailment step at a time. Contrary to previous approaches, our method combines generation steps and retrieval of premises, allowing the model to leverage intermediate conclusions, and mitigating the input size limit of baseline encoder-decoder models. We conduct experiments using the EntailmentBank dataset, where we outperform existing benchmarks on premise retrieval and entailment tree generation, with around 300% gain in overall correctness.
Natural language inference has trended toward studying contexts beyond the sentence level. An important application area is law: past cases often do not foretell how they apply to new situations and implications must be inferred. This paper introduces LawngNLI, constructed from U.S. legal opinions with automatic labels with high human-validated accuracy. Premises are long and multigranular. Experiments show two use cases. First, LawngNLI can benchmark for in-domain generalization from short to long contexts. It has remained unclear if large-scale long-premise NLI datasets actually need to be constructed: near-top performance on long premises could be achievable by fine-tuning using short premises. Without multigranularity, benchmarks cannot distinguish lack of fine-tuning on long premises versus domain shift between short and long datasets. In contrast, our long and short premises share the same examples and domain. Models fine-tuned using several past NLI datasets and/or our short premises fall short of top performance on our long premises. So for at least certain domains (such as ours), large-scale long-premise datasets are needed. Second, LawngNLI can benchmark for implication-based retrieval. Queries are entailed or contradicted by target documents, allowing users to move between arguments and evidence. Leading retrieval models perform reasonably zero shot on a LawngNLI-derived retrieval task. We compare different systems for re-ranking, including lexical overlap and cross-encoders fine-tuned using a modified LawngNLI or past NLI datasets. LawngNLI can train and test systems for implication-based case retrieval and argumentation.
Natural Language Processing tasks such as resolving the coreference of events require understanding the relations between two text snippets. These tasks are typically formulated as (binary) classification problems over independently induced representations of the text snippets. In this work, we develop a Pairwise Representation Learning (PairwiseRL) scheme for the event mention pairs, in which we jointly encode a pair of text snippets so that the representation of each mention in the pair is induced in the context of the other one. Furthermore, our representation supports a finer, structured representation of the text snippet to facilitate encoding events and their arguments. We show that PairwiseRL, despite its simplicity, outperforms the prior state-of-the-art event coreference systems on both cross-document and within-document event coreference benchmarks. We also conduct in-depth analysis in terms of the improvement and the limitation of pairwise representation so as to provide insights for future work.
Granular events, instantiated in a document by predicates, can usually be grouped into more general events, called complex events. Together, they capture the major content of the document. Recent work grouped granular events by defining event regions, filtering out sentences that are irrelevant to the main content. However, this approach assumes that a given complex event is always described in consecutive sentences, which does not always hold in practice. In this paper, we introduce the task of complex event identification. We address this task as a pipeline, first predicting whether two granular events mentioned in the text belong to the same complex event, independently of their position in the text, and then using this to cluster them into complex events. Due to the difficulty of predicting whether two granular events belong to the same complex event in isolation, we propose a context-augmented representation learning approach CONTEXTRL that adds additional context to better model the pairwise relation between granular events. We show that our approach outperforms strong baselines on the complex event identification task and further present a promising case study exploring the effectiveness of using complex events as input for document-level argument extraction.
Coreference resolution is essential for natural language understanding and has been long studied in NLP. In recent years, as the format of Question Answering (QA) became a standard for machine reading comprehension (MRC), there have been data collection efforts, e.g., Dasigi et al. (2019), that attempt to evaluate the ability of MRC models to reason about coreference. However, as we show, coreference reasoning in MRC is a greater challenge than earlier thought; MRC datasets do not reflect the natural distribution and, consequently, the challenges of coreference reasoning. Specifically, success on these datasets does not reflect a model’s proficiency in coreference reasoning. We propose a methodology for creating MRC datasets that better reflect the challenges of coreference reasoning and use it to create a sample evaluation set. The results on our dataset show that state-of-the-art models still struggle with these phenomena. Furthermore, we develop an effective way to use naturally occurring coreference phenomena from existing coreference resolution datasets when training MRC models. This allows us to show an improvement in the coreference reasoning abilities of state-of-the-art models.
When evaluating an article and the claims it makes, a critical reader must be able to assess where the information presented comes from, and whether the various claims are mutually consistent and support the conclusion. This motivates the study of claim provenance, which seeks to trace and explain the origins of claims. In this paper, we introduce new techniques to model and reason about the provenance of multiple interacting claims, including how to capture fine-grained information about the context. Our solution hinges on first identifying the sentences that potentially contain important external information. We then develop a query generator with our novel rank-aware cross attention mechanism, which aims at generating metadata for the source article, based on the context and the signals collected from a search engine. This establishes relevant search queries, and it allows us to obtain source article candidates for each identified sentence and propose an ILP based algorithm to infer the best sources. We experiment with a newly created evaluation dataset, Politi-Prov, based on fact-checking articles from www.politifact.com; our experimental results show that our solution leads to a significant improvement over baselines.
Event extraction has long been a challenging task, addressed mostly with supervised methods that require expensive annotation and are not extensible to new event ontologies. In this work, we explore the possibility of zero-shot event extraction by formulating it as a set of Textual Entailment (TE) and/or Question Answering (QA) queries (e.g. “A city was attacked” entails “There is an attack”), exploiting pretrained TE/QA models for direct transfer. On ACE-2005 and ERE, our system achieves acceptable results, yet there is still a large gap from supervised approaches, showing that current QA and TE technologies fail in transferring to a different domain. To investigate the reasons behind the gap, we analyze the remaining key challenges, their respective impact, and possible improvement directions.
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.
A key limitation in current datasets for multi-hop reasoning is that the required steps for answering the question are mentioned in it explicitly. In this work, we introduce StrategyQA, a question answering (QA) benchmark where the required reasoning steps are implicit in the question, and should be inferred using a strategy. A fundamental challenge in this setup is how to elicit such creative questions from crowdsourcing workers, while covering a broad range of potential strategies. We propose a data collection procedure that combines term-based priming to inspire annotators, careful control over the annotator population, and adversarial filtering for eliminating reasoning shortcuts. Moreover, we annotate each question with (1) a decomposition into reasoning steps for answering it, and (2) Wikipedia paragraphs that contain the answers to each step. Overall, StrategyQA includes 2,780 examples, each consisting of a strategy question, its decomposition, and evidence paragraphs. Analysis shows that questions in StrategyQA are short, topic-diverse, and cover a wide range of strategies. Empirically, we show that humans perform well (87%) on this task, while our best baseline reaches an accuracy of ∼ 66%.
A desirable property of a reference-based evaluation metric that measures the content quality of a summary is that it should estimate how much information that summary has in common with a reference. Traditional text overlap based metrics such as ROUGE fail to achieve this because they are limited to matching tokens, either lexically or via embeddings. In this work, we propose a metric to evaluate the content quality of a summary using question-answering (QA). QA-based methods directly measure a summary’s information overlap with a reference, making them fundamentally different than text overlap metrics. We demonstrate the experimental benefits of QA-based metrics through an analysis of our proposed metric, QAEval. QAEval outperforms current state-of-the-art metrics on most evaluations using benchmark datasets, while being competitive on others due to limitations of state-of-the-art models. Through a careful analysis of each component of QAEval, we identify its performance bottlenecks and estimate that its potential upper-bound performance surpasses all other automatic metrics, approaching that of the gold-standard Pyramid Method.1
The quality of a summarization evaluation metric is quantified by calculating the correlation between its scores and human annotations across a large number of summaries. Currently, it is unclear how precise these correlation estimates are, nor whether differences between two metrics’ correlations reflect a true difference or if it is due to mere chance. In this work, we address these two problems by proposing methods for calculating confidence intervals and running hypothesis tests for correlations using two resampling methods, bootstrapping and permutation. After evaluating which of the proposed methods is most appropriate for summarization through two simulation experiments, we analyze the results of applying these methods to several different automatic evaluation metrics across three sets of human annotations. We find that the confidence intervals are rather wide, demonstrating high uncertainty in the reliability of automatic metrics. Further, although many metrics fail to show statistical improvements over ROUGE, two recent works, QAEval and BERTScore, do so in some evaluation settings.1
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.
Understanding and executing natural language instructions in a grounded domain is one of the hallmarks of artificial intelligence. In this paper, we focus on instruction understanding in the blocks world domain and investigate the language understanding abilities of two top-performing systems for the task. We aim to understand if the test performance of these models indicates an understanding of the spatial domain and of the natural language instructions relative to it, or whether they merely over-fit spurious signals in the dataset. We formulate a set of expectations one might have from an instruction following model and concretely characterize the different dimensions of robustness such a model should possess. Despite decent test performance, we find that state-of-the-art models fall short of these expectations and are extremely brittle. We then propose a learning strategy that involves data augmentation and show through extensive experiments that the proposed learning strategy yields models that are competitive on the original test set while satisfying our expectations much better.
We propose TRACIE, a novel temporal reasoning dataset that evaluates the degree to which systems understand implicit events—events that are not mentioned explicitly in natural language text but can be inferred from it. This introduces a new challenge in temporal reasoning research, where prior work has focused on explicitly mentioned events. Human readers can infer implicit events via commonsense reasoning, resulting in a more comprehensive understanding of the situation and, consequently, better reasoning about time. We find, however, that state-of-the-art models struggle when predicting temporal relationships between implicit and explicit events. To address this, we propose a neuro-symbolic temporal reasoning model, SymTime, which exploits distant supervision signals from large-scale text and uses temporal rules to combine start times and durations to infer end times. SymTime outperforms strong baseline systems on TRACIE by 5%, and by 11% in a zero prior knowledge training setting. Our approach also generalizes to other temporal reasoning tasks, as evidenced by a gain of 1%-9% on MATRES, an explicit event benchmark.
People rely on digital task management tools, such as email or to-do apps, to manage their tasks. Some of these tasks are large and complex, leading to action paralysis and feelings of being overwhelmed on the part of the user. The micro-productivity literature has shown that such tasks could benefit from being decomposed and organized, in order to reduce user cognitive load. Thus in this paper, we propose a novel end-to-end pipeline that consumes a complex task and induces a dependency graph from unstructured text to represent sub-tasks and their relationships. Our solution first finds nodes for sub-tasks from multiple ‘how-to’ articles on the web by injecting a neural text generator with three key desiderata – relevance, abstraction, and consensus. Then we resolve and infer edges between these subtask nodes by learning task dependency relations. We collect a new dataset of complex tasks with their sub-task graph to develop and evaluate our solutions. Both components of our graph induction solution are evaluated in experiments, demonstrating that our models outperform a state-of-the-art text generator significantly. Our generalizable and scalable end-to-end solution has important implications for boosting user productivity and assisting with digital task management.
We propose MultiOpEd, an open-domain news editorial corpus that supports various tasks pertaining to the argumentation structure in news editorials, focusing on automatic perspective discovery. News editorial is a genre of persuasive text, where the argumentation structure is usually implicit. However, the arguments presented in an editorial typically center around a concise, focused thesis, which we refer to as their perspective. MultiOpEd aims at supporting the study of multiple tasks relevant to automatic perspective discovery, where a system is expected to produce a single-sentence thesis statement summarizing the arguments presented. We argue that identifying and abstracting such natural language perspectives from editorials is a crucial step toward studying the implicit argumentation structure in news editorials. We first discuss the challenges and define a few conceptual tasks towards our goal. To demonstrate the utility of MultiOpEd and the induced tasks, we study the problem of perspective summarization in a multi-task learning setting, as a case study. We show that, with the induced tasks as auxiliary tasks, we can improve the quality of the perspective summary generated. We hope that MultiOpEd will be a useful resource for future studies on argumentation in the news editorial domain.
Despite significant progress in neural abstractive summarization, recent studies have shown that the current models are prone to generating summaries that are unfaithful to the original context. To address the issue, we study contrast candidate generation and selection as a model-agnostic post-processing technique to correct the extrinsic hallucinations (i.e. information not present in the source text) in unfaithful summaries. We learn a discriminative correction model by generating alternative candidate summaries where named entities and quantities in the generated summary are replaced with ones with compatible semantic types from the source document. This model is then used to select the best candidate as the final output summary. Our experiments and analysis across a number of neural summarization systems show that our proposed method is effective in identifying and correcting extrinsic hallucinations. We analyze the typical hallucination phenomenon by different types of neural summarization systems, in hope to provide insights for future work on the direction.
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.
Reference-based metrics such as ROUGE or BERTScore evaluate the content quality of a summary by comparing the summary to a reference. Ideally, this comparison should measure the summary’s information quality by calculating how much information the summaries have in common. In this work, we analyze the token alignments used by ROUGE and BERTScore to compare summaries and argue that their scores largely cannot be interpreted as measuring information overlap. Rather, they are better estimates of the extent to which the summaries discuss the same topics. Further, we provide evidence that this result holds true for many other summarization evaluation metrics. The consequence of this result is that the most frequently used summarization evaluation metrics do not align with the community’s research goal, to generate summaries with high-quality information. However, we conclude by demonstrating that a recently proposed metric, QAEval, which scores summaries using question-answering, appears to better capture information quality than current evaluations, highlighting a direction for future research.
Transformer-based language models have taken the NLP world by storm. However, their potential for addressing important questions in language acquisition research has been largely ignored. In this work, we examined the grammatical knowledge of RoBERTa (Liu et al., 2019) when trained on a 5M word corpus of language acquisition data to simulate the input available to children between the ages 1 and 6. Using the behavioral probing paradigm, we found that a smaller version of RoBERTa-base that never predicts unmasked tokens, which we term BabyBERTa, acquires grammatical knowledge comparable to that of pre-trained RoBERTa-base - and does so with approximately 15X fewer parameters and 6,000X fewer words. We discuss implications for building more efficient models and the learnability of grammar from input available to children. Lastly, to support research on this front, we release our novel grammar test suite that is compatible with the small vocabulary of child-directed input.
Much research effort has been put to multilingual knowledge graph (KG) embedding methods to address the entity alignment task, which seeks to match entities in different languagespecific KGs that refer to the same real-world object. Such methods are often hindered by the insufficiency of seed alignment provided between KGs. Therefore, we propose a new model, JEANS , which jointly represents multilingual KGs and text corpora in a shared embedding scheme, and seeks to improve entity alignment with incidental supervision signals from text. JEANS first deploys an entity grounding process to combine each KG with the monolingual text corpus. Then, two learning processes are conducted: (i) an embedding learning process to encode the KG and text of each language in one embedding space, and (ii) a self-learning based alignment learning process to iteratively induce the correspondence of entities and that of lexemes between embeddings. Experiments on benchmark datasets show that JEANS leads to promising improvement on entity alignment with incidental supervision, and significantly outperforms state-of-the-art methods that solely rely on internal information of KGs.
Standard evaluations of Grammatical Error Correction (GEC) systems make use of a fixed reference text generated relative to the original text; they show, even when using multiple references, that we have a long way to go. This analysis paper studies the performance of GEC systems relative to closest-gold – a gold reference text created relative to the output of a system. Surprisingly, we show that the real performance is 20-40 points better than standard evaluations show. Moreover, the performance remains high even when considering any of the top-10 hypotheses produced by a system. Importantly, the type of mistakes corrected by lower-ranked hypotheses differs in interesting ways from the top one, providing an opportunity to focus on a range of errors – local spelling and grammar edits vs. more complex lexical improvements. Our study shows these results in English and Russian, and thus provides a preliminary proposal for a more realistic evaluation of GEC systems.
Humans are capable of learning novel concepts from very few examples; in contrast, state-of-the-art machine learning algorithms typically need thousands of examples to do so. In this paper, we propose an algorithm for learning novel concepts by representing them as programs over existing concepts. This way the concept learning problem is naturally a program synthesis problem and our algorithm learns from a few examples to synthesize a program representing the novel concept. In addition, we perform a theoretical analysis of our approach for the case where the program defining the novel concept over existing ones is context-free. We show that given a learned grammar-based parser and a novel production rule, we can augment the parser with the production rule in a way that provably generalizes. We evaluate our approach by learning concepts in the semantic parsing domain extended to the few-shot novel concept learning setting, showing that our approach significantly outperforms end-to-end neural semantic parsers.
Executing natural language instructions in a physically grounded domain requires a model that understands both spatial concepts such as “left of” and “above”, and the compositional language used to identify landmarks and articulate instructions relative to them. In this paper, we study instruction understanding in the blocks world domain. Given an initial arrangement of blocks and a natural language instruction, the system executes the instruction by manipulating selected blocks. The highly compositional instructions are composed of atomic components and understanding these components is a necessary step to executing the instruction. We show that while end-to-end training (supervised only by the correct block location) fails to address the challenges of this task and performs poorly on instructions involving a single atomic component, knowledge-free auxiliary signals can be used to significantly improve performance by providing supervision for the instruction’s components. Specifically, we generate signals that aim at helping the model gradually understand components of the compositional instructions, as well as those that help it better understand spatial concepts, and show their benefit to the overall task for two datasets and two state-of-the-art (SOTA) models, especially when the training data is limited—which is usual in such tasks.
Large, pre-trained transformer language models, which are pervasive in natural language processing tasks, are notoriously expensive to train. To reduce the cost of training such large models, prior work has developed smaller, more compact models which achieves a significant speedup in training time while maintaining competitive accuracy to the original model on downstream tasks. Though these smaller pre-trained models have been widely adopted by the community, it is not known how well are they calibrated compared to their larger counterparts. In this paper, focusing on a wide range of tasks, we thoroughly investigate the calibration properties of pre-trained transformers, as a function of their size. We demonstrate that when evaluated in-domain, smaller models are able to achieve competitive, and often better, calibration compared to larger models, while achieving significant speedup in training time. Post-hoc calibration techniques further reduce calibration error for all models in-domain. However, when evaluated out-of-domain, larger models tend to be better calibrated, and label-smoothing instead is an effective strategy to calibrate models in this setting.
Understanding when a text snippet does not provide a sought after information is an essential part of natural language utnderstanding. Recent work (SQuAD 2.0; Rajpurkar et al., 2018) has attempted to make some progress in this direction by enriching the SQuAD dataset for the Extractive QA task with unanswerable questions. However, as we show, the performance of a top system trained on SQuAD 2.0 drops considerably in out-of-domain scenarios, limiting its use in practical situations. In order to study this we build an out-of-domain corpus, focusing on simple event-based questions and distinguish between two types of IDK questions: competitive questions, where the context includes an entity of the same type as the expected answer, and simpler, non-competitive questions where there is no entity of the same type in the context. We find that SQuAD 2.0-based models fail even in the case of the simpler questions. We then analyze the similarities and differences between the IDK phenomenon in Extractive QA and the Recognizing Textual Entailments task (RTE; Dagan et al., 2013) and investigate the extent to which the latter can be used to improve the performance.
Real-world applications often require improved models by leveraging *a range of cheap incidental supervision signals*. These could include partial labels, noisy labels, knowledge-based constraints, and cross-domain or cross-task annotations – all having statistical associations with gold annotations but not exactly the same. However, we currently lack a principled way to measure the benefits of these signals to a given target task, and the common practice of evaluating these benefits is through exhaustive experiments with various models and hyperparameters. This paper studies whether we can, *in a single framework, quantify the benefits of various types of incidental signals for a given target task without going through combinatorial experiments*. We propose a unified PAC-Bayesian motivated informativeness measure, PABI, that characterizes the uncertainty reduction provided by incidental supervision signals. We demonstrate PABI’s effectiveness by quantifying the value added by various types of incidental signals to sequence tagging tasks. Experiments on named entity recognition (NER) and question answering (QA) show that PABI’s predictions correlate well with learning performance, providing a promising way to determine, ahead of learning, which supervision signals would be beneficial.
Event mentions in text correspond to real-world events of varying degrees of granularity. The task of subevent detection aims to resolve this granularity issue, recognizing the membership of multi-granular events in event complexes. Since knowing the span of descriptive contexts of event complexes helps infer the membership of events, we propose the task of event-based text segmentation (EventSeg) as an auxiliary task to improve the learning for subevent detection. To bridge the two tasks together, we propose an approach to learning and enforcing constraints that capture dependencies between subevent detection and EventSeg prediction, as well as guiding the model to make globally consistent inference. Specifically, we adopt Rectifier Networks for constraint learning and then convert the learned constraints to a regularization term in the loss function of the neural model. Experimental results show that the proposed method outperforms baseline methods by 2.3% and 2.5% on benchmark datasets for subevent detection, HiEve and IC, respectively, while achieving a decent performance on EventSeg prediction.
Compositional, structured models are appealing because they explicitly decompose problems and provide interpretable intermediate outputs that give confidence that the model is not simply latching onto data artifacts. Learning these models is challenging, however, because end-task supervision only provides a weak indirect signal on what values the latent decisions should take. This often results in the model failing to learn to perform the intermediate tasks correctly. In this work, we introduce a way to leverage paired examples that provide stronger cues for learning latent decisions. When two related training examples share internal substructure, we add an additional training objective to encourage consistency between their latent decisions. Such an objective does not require external supervision for the values of the latent output, or even the end task, yet provides an additional training signal to that provided by individual training examples themselves. We apply our method to improve compositional question answering using neural module networks on the DROP dataset. We explore three ways to acquire paired questions in DROP: (a) discovering naturally occurring paired examples within the dataset, (b) constructing paired examples using templates, and (c) generating paired examples using a question generation model. We empirically demonstrate that our proposed approach improves both in- and out-of-distribution generalization and leads to correct latent decision predictions.
Understanding how events are semantically related to each other is the essence of reading comprehension. Recent event-centric reading comprehension datasets focus mostly on event arguments or temporal relations. While these tasks partially evaluate machines’ ability of narrative understanding, human-like reading comprehension requires the capability to process event-based information beyond arguments and temporal reasoning. For example, to understand causality between events, we need to infer motivation or purpose; to establish event hierarchy, we need to understand the composition of events. To facilitate these tasks, we introduce **ESTER**, a comprehensive machine reading comprehension (MRC) dataset for Event Semantic Relation Reasoning. The dataset leverages natural language queries to reason about the five most common event semantic relations, provides more than 6K questions, and captures 10.1K event relation pairs. Experimental results show that the current SOTA systems achieve 22.1%, 63.3% and 83.5% for token-based exact-match (**EM**), **F1** and event-based **HIT@1** scores, which are all significantly below human performances (36.0%, 79.6%, 100% respectively), highlighting our dataset as a challenging benchmark.
The Winograd Schema (WS) has been proposed as a test for measuring commonsense capabilities of models. Recently, pre-trained language model-based approaches have boosted performance on some WS benchmarks but the source of improvement is still not clear. This paper suggests that the apparent progress on WS may not necessarily reflect progress in commonsense reasoning. To support this claim, we first show that the current evaluation method of WS is sub-optimal and propose a modification that uses twin sentences for evaluation. We also propose two new baselines that indicate the existence of artifacts in WS benchmarks. We then develop a method for evaluating WS-like sentences in a zero-shot setting to account for the commonsense reasoning abilities acquired during the pretraining and observe that popular language models perform randomly in this setting when using our more strict evaluation. We conclude that the observed progress is mostly due to the use of supervision in training WS models, which is not likely to successfully support all the required commonsense reasoning skills and knowledge.
In low-resource natural language processing (NLP), the key problems are a lack of target language training data, and a lack of native speakers to create it. Cross-lingual methods have had notable success in addressing these concerns, but in certain common circumstances, such as insufficient pre-training corpora or languages far from the source language, their performance suffers. In this work we propose a complementary approach to building low-resource Named Entity Recognition (NER) models using “non-speaker” (NS) annotations, provided by annotators with no prior experience in the target language. We recruit 30 participants in a carefully controlled annotation experiment with Indonesian, Russian, and Hindi. We show that use of NS annotators produces results that are consistently on par or better than cross-lingual methods built on modern contextual representations, and have the potential to outperform with additional effort. We conclude with observations of common annotation patterns and recommended implementation practices, and motivate how NS annotations can be used in addition to prior methods for improved performance.
Identifying the key events in a document is critical to holistically understanding its important information. Although measuring the salience of events is highly contextual, most previous work has used a limited representation of events that omits essential information. In this work, we propose a highly contextual model of event salience that uses a rich representation of events, incorporates document-level information and allows for interactions between latent event encodings. Our experimental results on an event salience dataset demonstrate that our model improves over previous work by an absolute 2-4% on standard metrics, establishing a new state-of-the-art performance for the task. We also propose a new evaluation metric that addresses flaws in previous evaluation methodologies. Finally, we discuss the importance of salient event detection for the downstream task of summarization.
We propose a new semantic scheme for capturing predicate-argument relations for nominalizations, termed QANom. This scheme extends the QA-SRL formalism (He et al., 2015), modeling the relations between nominalizations and their arguments via natural language question-answer pairs. We construct the first QANom dataset using controlled crowdsourcing, analyze its quality and compare it to expertly annotated nominal-SRL annotations, as well as to other QA-driven annotations. In addition, we train a baseline QANom parser for identifying nominalizations and labeling their arguments with question-answer pairs. Finally, we demonstrate the extrinsic utility of our annotations for downstream tasks using both indirect supervision and zero-shot settings.
We present SacreROUGE, an open-source library for using and developing summarization evaluation metrics. SacreROUGE removes many obstacles that researchers face when using or developing metrics: (1) The library provides Python wrappers around the official implementations of existing evaluation metrics so they share a common, easy-to-use interface; (2) it provides functionality to evaluate how well any metric implemented in the library correlates to human-annotated judgments, so no additional code needs to be written for a new evaluation metric; and (3) it includes scripts for loading datasets that contain human judgments so they can easily be used for evaluation. This work describes the design of the library, including the core Metric interface, the command-line API for evaluating summarization models and metrics, and the scripts to load and reformat publicly available datasets. The development of SacreROUGE is ongoing and open to contributions from the community.
Recognizing spatial relations and reasoning about them is essential in multiple applications including navigation, direction giving and human-computer interaction in general. Spatial relations between objects can either be explicit – expressed as spatial prepositions, or implicit – expressed by spatial verbs such as moving, walking, shifting, etc. Both these, but implicit relations in particular, require significant common sense understanding. In this paper, we introduce the task of inferring implicit and explicit spatial relations between two entities in an image. We design a model that uses both textual and visual information to predict the spatial relations, making use of both positional and size information of objects and image embeddings. We contrast our spatial model with powerful language models and show how our modeling complements the power of these, improving prediction accuracy and coverage and facilitates dealing with unseen subjects, objects and relations.
Spatial Reasoning from language is essential for natural language understanding. Supporting it requires a representation scheme that can capture spatial phenomena encountered in language as well as in images and videos. Existing spatial representations are not sufficient for describing spatial configurations used in complex tasks. This paper extends the capabilities of existing spatial representation languages and increases coverage of the semantic aspects that are needed to ground spatial meaning of natural language text in the world. Our spatial relation language is able to represent a large, comprehensive set of spatial concepts crucial for reasoning and is designed to support composition of static and dynamic spatial configurations. We integrate this language with the Abstract Meaning Representation (AMR) annotation schema and present a corpus annotated by this extended AMR. To exhibit the applicability of our representation scheme, we annotate text taken from diverse datasets and show how we extend the capabilities of existing spatial representation languages with fine-grained decomposition of semantics and blend it seamlessly with AMRs of sentences and discourse representations as a whole.
In an era where generating content and publishing it is so easy, we are bombarded with information and are exposed to all kinds of claims, some of which do not always rank high on the truth scale. This paper suggests that the key to a longer-term, holistic, and systematic approach to navigating this information pollution is capturing the provenance of claims. To do that, we develop a formal definition of provenance graph for a given natural language claim, aiming to understand where the claim may come from and how it has evolved. To construct the graph, we model provenance inference, formulated mainly as an information extraction task and addressed via a textual entailment model. We evaluate our approach using two benchmark datasets, showing initial success in capturing the notion of provenance and its effectiveness on the application of claim verification.
Empirical research in Natural Language Processing (NLP) has adopted a narrow set of principles for assessing hypotheses, relying mainly on p-value computation, which suffers from several known issues. While alternative proposals have been well-debated and adopted in other fields, they remain rarely discussed or used within the NLP community. We address this gap by contrasting various hypothesis assessment techniques, especially those not commonly used in the field (such as evaluations based on Bayesian inference). Since these statistical techniques differ in the hypotheses they can support, we argue that practitioners should first decide their target hypothesis before choosing an assessment method. This is crucial because common fallacies, misconceptions, and misinterpretation surrounding hypothesis assessment methods often stem from a discrepancy between what one would like to claim versus what the method used actually assesses. Our survey reveals that these issues are omnipresent in the NLP research community. As a step forward, we provide best practices and guidelines tailored to NLP research, as well as an easy-to-use package for Bayesian assessment of hypotheses, complementing existing tools.
Temporal common sense (e.g., duration and frequency of events) is crucial for understanding natural language. However, its acquisition is challenging, partly because such information is often not expressed explicitly in text, and human annotation on such concepts is costly. This work proposes a novel sequence modeling approach that exploits explicit and implicit mentions of temporal common sense, extracted from a large corpus, to build TacoLM, a temporal common sense language model. Our method is shown to give quality predictions of various dimensions of temporal common sense (on UDST and a newly collected dataset from RealNews). It also produces representations of events for relevant tasks such as duration comparison, parent-child relations, event coreference and temporal QA (on TimeBank, HiEVE and MCTACO) that are better than using the standard BERT. Thus, it will be an important component of temporal NLP.
Question-answering (QA) data often encodes essential information in many facets. This paper studies a natural question: Can we get supervision from QA data for other tasks (typically, non-QA ones)? For example, can we use QAMR (Michael et al., 2017) to improve named entity recognition? We suggest that simply further pre-training BERT is often not the best option, and propose the question-answer driven sentence encoding (QuASE) framework. QuASE learns representations from QA data, using BERT or other state-of-the-art contextual language models. In particular, we observe the need to distinguish between two types of sentence encodings, depending on whether the target task is a single- or multi-sentence input; in both cases, the resulting encoding is shown to be an easy-to-use plugin for many downstream tasks. This work may point out an alternative way to supervise NLP tasks.
Commonsense knowledge, such as knowing that “bumping into people annoys them” or “rain makes the road slippery”, helps humans navigate everyday situations seamlessly. Yet, endowing machines with such human-like commonsense reasoning capabilities has remained an elusive goal of artificial intelligence research for decades. In recent years, commonsense knowledge and reasoning have received renewed attention from the natural language processing (NLP) community, yielding exploratory studies in automated commonsense understanding. We organize this tutorial to provide researchers with the critical foundations and recent advances in commonsense representation and reasoning, in the hopes of casting a brighter light on this promising area of future research. In our tutorial, we will (1) outline the various types of commonsense (e.g., physical, social), and (2) discuss techniques to gather and represent commonsense knowledge, while highlighting the challenges specific to this type of knowledge (e.g., reporting bias). We will then (3) discuss the types of commonsense knowledge captured by modern NLP systems (e.g., large pretrained language models), and (4) present ways to measure systems’ commonsense reasoning abilities. We will finish with (5) a discussion of various ways in which commonsense reasoning can be used to improve performance on NLP tasks, exemplified by an (6) interactive session on integrating commonsense into a downstream task.
This paper studies a new cognitively motivated semantic typing task,multi-axis event process typing, that, given anevent process, attempts to infer free-form typelabels describing (i) the type of action made bythe process and (ii) the type of object the pro-cess seeks to affect. This task is inspired bycomputational and cognitive studies of eventunderstanding, which suggest that understand-ing processes of events is often directed by rec-ognizing the goals, plans or intentions of theprotagonist(s). We develop a large dataset con-taining over 60k event processes, featuring ul-tra fine-grained typing on both the action andobject type axes with very large (10ˆ3∼10ˆ4)label vocabularies. We then propose a hybridlearning framework,P2GT, which addressesthe challenging typing problem with indirectsupervision from glosses1and a joint learning-to-rank framework. As our experiments indi-cate,P2GTsupports identifying the intent ofprocesses, as well as the fine semantic type ofthe affected object. It also demonstrates the ca-pability of handling few-shot cases, and stronggeneralizability on out-of-domain processes.
We describe an approach to task-oriented dialogue in which dialogue state is represented as a dataflow graph. A dialogue agent maps each user utterance to a program that extends this graph. Programs include metacomputation operators for reference and revision that reuse dataflow fragments from previous turns. Our graph-based state enables the expression and manipulation of complex user intents, and explicit metacomputation makes these intents easier for learned models to predict. We introduce a new dataset, SMCalFlow, featuring complex dialogues about events, weather, places, and people. Experiments show that dataflow graphs and metacomputation substantially improve representability and predictability in these natural dialogues. Additional experiments on the MultiWOZ dataset show that our dataflow representation enables an otherwise off-the-shelf sequence-to-sequence model to match the best existing task-specific state tracking model. The SMCalFlow dataset, code for replicating experiments, and a public leaderboard are available at https://www.microsoft.com/en-us/research/project/dataflow-based-dialogue-semantic-machines.
Traditional (unstructured) pruning methods for a Transformer model focus on regularizing the individual weights by penalizing them toward zero. In this work, we explore spectral-normalized identity priors (SNIP), a structured pruning approach which penalizes an entire residual module in a Transformer model toward an identity mapping. Our method identifies and discards unimportant non-linear mappings in the residual connections by applying a thresholding operator on the function norm, and is applicable to any structured module including a single attention head, an entire attention blocks, or a feed-forward subnetwork. Furthermore, we introduce spectral normalization to stabilize the distribution of the post-activation values of the Transformer layers, further improving the pruning effectiveness of the proposed methodology. We conduct experiments with BERT on 5 GLUE benchmark tasks to demonstrate that SNIP achieves effective pruning results while maintaining comparable performance. Specifically, we improve the performance over the state-of-the-art by 0.5 to 1.0% on average at 50% compression ratio.
Multilingual BERT (M-BERT) has been a huge success in both supervised and zero-shot cross-lingual transfer learning. However, this success is focused only on the top 104 languages in Wikipedia it was trained on. In this paper, we propose a simple but effective approach to extend M-BERT E-MBERT so it can benefit any new language, and show that our approach aids languages that are already in M-BERT as well. We perform an extensive set of experiments with Named Entity Recognition (NER) on 27 languages, only 16 of which are in M-BERT, and show an average increase of about 6% F1 on M-BERT languages and 23% F1 increase on new languages. We release models and code at http://cogcomp.org/page/publication_view/912.
The recent success of machine learning systems on various QA datasets could be interpreted as a significant improvement in models’ language understanding abilities. However, using various perturbations, multiple recent works have shown that good performance on a dataset might not indicate performance that correlates well with human’s expectations from models that “understand” language. In this work we consider a top performing model on several Multiple Choice Question Answering (MCQA) datasets, and evaluate it against a set of expectations one might have from such a model, using a series of zero-information perturbations of the model’s inputs. Our results show that the model clearly falls short of our expectations, and motivates a modified training approach that forces the model to better attend to the inputs. We show that the new training paradigm leads to a model that performs on par with the original model while better satisfying our expectations.
Pretrained Language Models (LMs) have been shown to possess significant linguistic, common sense and factual knowledge. One form of knowledge that has not been studied yet in this context is information about the scalar magnitudes of objects. We show that pretrained language models capture a significant amount of this information but are short of the capability required for general common-sense reasoning. We identify contextual information in pre-training and numeracy as two key factors affecting their performance, and show that a simple method of canonicalizing numbers can have a significant effect on the results.
Pretrained Language Models (LMs) have been shown to possess significant linguistic, common sense and factual knowledge. One form of knowledge that has not been studied yet in this context is information about the scalar magnitudes of objects. We show that pretrained language models capture a significant amount of this information but are short of the capability required for general common-sense reasoning. We identify contextual information in pre-training and numeracy as two key factors affecting their performance, and show that a simple method of canonicalizing numbers can have a significant effect on the results.
Understanding natural language involves recognizing how multiple event mentions structurally and temporally interact with each other. In this process, one can induce event complexes that organize multi-granular events with temporal order and membership relations interweaving among them. Due to the lack of jointly labeled data for these relational phenomena and the restriction on the structures they articulate, we propose a joint constrained learning framework for modeling event-event relations. Specifically, the framework enforces logical constraints within and across multiple temporal and subevent relations of events by converting these constraints into differentiable learning objectives. We show that our joint constrained learning approach effectively compensates for the lack of jointly labeled data, and outperforms SOTA methods on benchmarks for both temporal relation extraction and event hierarchy construction, replacing a commonly used but more expensive global inference process. We also present a promising case study to show the effectiveness of our approach to inducing event complexes on an external corpus.
A critical part of reading is being able to understand the temporal relationships between events described in a passage of text, even when those relationships are not explicitly stated. However, current machine reading comprehension benchmarks have practically no questions that test temporal phenomena, so systems trained on these benchmarks have no capacity to answer questions such as “what happened before/after [some event]?” We introduce TORQUE, a new English reading comprehension benchmark built on 3.2k news snippets with 21k human-generated questions querying temporal relationships. Results show that RoBERTa-large achieves an exact-match score of 51% on the test set of TORQUE, about 30% behind human performance.
Computational and cognitive studies of event understanding suggest that identifying, comprehending, and predicting events depend on having structured representations of a sequence of events and on conceptualizing (abstracting) its components into (soft) event categories. Thus, knowledge about a known process such as “buying a car” can be used in the context of a new but analogous process such as “buying a house”. Nevertheless, most event understanding work in NLP is still at the ground level and does not consider abstraction. In this paper, we propose an Analogous Process Structure Induction (APSI) framework, which leverages analogies among processes and conceptualization of sub-event instances to predict the whole sub-event sequence of previously unseen open-domain processes. As our experiments and analysis indicate, APSI supports the generation of meaningful sub-event sequences for unseen processes and can help predict missing events.
Cross-lingual Entity Linking (XEL), the problem of grounding mentions of entities in a foreign language text into an English knowledge base such as Wikipedia, has seen a lot of research in recent years, with a range of promising techniques. However, current techniques do not rise to the challenges introduced by text in low-resource languages (LRL) and, surprisingly, fail to generalize to text not taken from Wikipedia, on which they are usually trained. This paper provides a thorough analysis of low-resource XEL techniques, focusing on the key step of identifying candidate English Wikipedia titles that correspond to a given foreign language mention. Our analysis indicates that current methods are limited by their reliance on Wikipedia’s interlanguage links and thus suffer when the foreign language’s Wikipedia is small. We conclude that the LRL setting requires the use of outside-Wikipedia cross-lingual resources and present a simple yet effective zero-shot XEL system, QuEL, that utilizes search engines query logs. With experiments on 25 languages, QuEL shows an average increase of 25% in gold candidate recall and of 13% in end-to-end linking accuracy over state-of-the-art baselines.
We revisit a pragmatic inference problem in dialog: Understanding indirect responses to questions. Humans can interpret ‘I’m starving.’ in response to ‘Hungry?’, even without direct cue words such as ‘yes’ and ‘no’. In dialog systems, allowing natural responses rather than closed vocabularies would be similarly beneficial. However, today’s systems are only as sensitive to these pragmatic moves as their language model allows. We create and release the first large-scale English language corpus ‘Circa’ with 34,268 (polar question, indirect answer) pairs to enable progress on this task. The data was collected via elaborate crowdsourcing, and contains utterances with yes/no meaning, as well as uncertain, middle-ground, and conditional responses. We also present BERT-based neural models to predict such categories for a question-answer pair. We find that while transfer learning from entailment works reasonably, performance is not yet sufficient for robust dialog. Our models reach 82-88% accuracy for a 4-class distinction, and 74-85% for 6 classes.
In order for coreference resolution systems to be useful in practice, they must be able to generalize to new text. In this work, we demonstrate that the performance of the state-of-the-art system decreases when the names of PER and GPE named entities in the CoNLL dataset are changed to names that do not occur in the training set. We use the technique of adversarial gradient-based training to retrain the state-of-the-art system and demonstrate that the retrained system achieves higher performance on the CoNLL dataset (both with and without the change of named entities) and the GAP dataset.
The information revolution brought with it information pollution. Information retrieval and extraction help us cope with abundant information from diverse sources. But some sources are of anonymous authorship, and some are of uncertain accuracy, so how can we determine what we should actually believe? Not all information sources are equally trustworthy, and simply accepting the majority view is often wrong. This paper develops a general framework for estimating the trustworthiness of information sources in an environment where multiple sources provide claims and supporting evidence, and each claim can potentially be produced by multiple sources. We consider two settings: one in which information sources directly assert claims, and a more realistic and challenging one, in which claims are inferred from evidence provided by sources, via (possibly noisy) NLP techniques. Our key contribution is to develop a family of probabilistic models that jointly estimate the trustworthiness of sources, and the credibility of claims they assert. This is done while accounting for the (possibly noisy) NLP needed to infer claims from evidence supplied by sources. We evaluate our framework on several datasets, showing strong results and significant improvement over baselines.
Most current NLP systems have little knowledge about quantitative attributes of objects and events. We propose an unsupervised method for collecting quantitative information from large amounts of web data, and use it to create a new, very large resource consisting of distributions over physical quantities associated with objects, adjectives, and verbs which we call Distributions over Quantitative (DoQ). This contrasts with recent work in this area which has focused on making only relative comparisons such as “Is a lion bigger than a wolf?”. Our evaluation shows that DoQ compares favorably with state of the art results on existing datasets for relative comparisons of nouns and adjectives, and on a new dataset we introduce.
This work presents PerspectroScope, a web-based system which lets users query a discussion-worthy natural language claim, and extract and visualize various perspectives in support or against the claim, along with evidence supporting each perspective. The system thus lets users explore various perspectives that could touch upon aspects of the issue at hand. The system is built as a combination of retrieval engines and learned textual-entailment-like classifiers built using a few recent developments in natural language understanding. To make the system more adaptive, expand its coverage, and improve its decisions over time, our platform employs various mechanisms to get corrections from the users. PerspectroScope is available at github.com/CogComp/perspectroscope Web demo link: http://orwell.seas.upenn.edu:4002/ Link to demo video: https://www.youtube.com/watch?v=MXBTR1Sp3Bs
Until now, most of the research in grammar error correction focused on English, and the problem has hardly been explored for other languages. We address the task of correcting writing mistakes in morphologically rich languages, with a focus on Russian. We present a corrected and error-tagged corpus of Russian learner writing and develop models that make use of existing state-of-the-art methods that have been well studied for English. Although impressive results have recently been achieved for grammar error correction of non-native English writing, these results are limited to domains where plentiful training data are available. Because annotation is extremely costly, these approaches are not suitable for the majority of domains and languages. We thus focus on methods that use “minimal supervision”; that is, those that do not rely on large amounts of annotated training data, and show how existing minimal-supervision approaches extend to a highly inflectional language such as Russian. The results demonstrate that these methods are particularly useful for correcting mistakes in grammatical phenomena that involve rich morphology.
Inference in structured prediction involves finding the best output structure for an input, subject to certain constraints. Many current approaches use sequential inference, which constructs the output in a left-to-right manner. However, there is no general framework to specify constraints in these approaches. We present a principled approach for incorporating constraints into sequential inference algorithms. Our approach expresses constraints using an automaton, which is traversed in lock-step during inference, guiding the search to valid outputs. We show that automata can express commonly used constraints and are easily incorporated into sequential inference. When it is more natural to represent constraints as a set of automata, our algorithm uses an active set method for demonstrably fast and efficient inference. We experimentally show the benefits of our algorithm on constituency parsing and semantic role labeling. For parsing, unlike unconstrained approaches, our algorithm always generates valid output, incurring only a small drop in performance. For semantic role labeling, imposing constraints using our algorithm corrects common errors, improving F1 by 1.5 points. These benefits increase in low-resource settings. Our active set method achieves a 5.2x relative speed-up over a naive approach.
Story understanding requires developing expectations of what events come next in text. Prior knowledge – both statistical and declarative – is essential in guiding such expectations. While existing semantic language models (SemLM) capture event co-occurrence information by modeling event sequences as semantic frames, entities, and other semantic units, this paper aims at augmenting them with causal knowledge (i.e., one event is likely to lead to another). Such knowledge is modeled at the frame and entity level, and can be obtained either statistically from text or stated declaratively. The proposed method, KnowSemLM, infuses this knowledge into a semantic LM by joint training and inference, and is shown to be effective on both the event cloze test and story/referent prediction tasks.
Supervised machine learning assumes the availability of fully-labeled data, but in many cases, such as low-resource languages, the only data available is partially annotated. We study the problem of Named Entity Recognition (NER) with partially annotated training data in which a fraction of the named entities are labeled, and all other tokens, entities or otherwise, are labeled as non-entity by default. In order to train on this noisy dataset, we need to distinguish between the true and false negatives. To this end, we introduce a constraint-driven iterative algorithm that learns to detect false negatives in the noisy set and downweigh them, resulting in a weighted training set. With this set, we train a weighted NER model. We evaluate our algorithm with weighted variants of neural and non-neural NER models on data in 8 languages from several language and script families, showing strong ability to learn from partial data. Finally, to show real-world efficacy, we evaluate on a Bengali NER corpus annotated by non-speakers, outperforming the prior state-of-the-art by over 5 points F1.
Remarkable success has been achieved in the last few years on some limited machine reading comprehension (MRC) tasks. However, it is still difficult to interpret the predictions of existing MRC models. In this paper, we focus on extracting evidence sentences that can explain or support the answers of multiple-choice MRC tasks, where the majority of answer options cannot be directly extracted from reference documents. Due to the lack of ground truth evidence sentence labels in most cases, we apply distant supervision to generate imperfect labels and then use them to train an evidence sentence extractor. To denoise the noisy labels, we apply a recently proposed deep probabilistic logic learning framework to incorporate both sentence-level and cross-sentence linguistic indicators for indirect supervision. We feed the extracted evidence sentences into existing MRC models and evaluate the end-to-end performance on three challenging multiple-choice MRC datasets: MultiRC, RACE, and DREAM, achieving comparable or better performance than the same models that take as input the full reference document. To the best of our knowledge, this is the first work extracting evidence sentences for multiple-choice MRC.
One key consequence of the information revolution is a significant increase and a contamination of our information supply. The practice of fact checking won’t suffice to eliminate the biases in text data we observe, as the degree of factuality alone does not determine whether biases exist in the spectrum of opinions visible to us. To better understand controversial issues, one needs to view them from a diverse yet comprehensive set of perspectives. For example, there are many ways to respond to a claim such as “animals should have lawful rights”, and these responses form a spectrum of perspectives, each with a stance relative to this claim and, ideally, with evidence supporting it. Inherently, this is a natural language understanding task, and we propose to address it as such. Specifically, we propose the task of substantiated perspective discovery where, given a claim, a system is expected to discover a diverse set of well-corroborated perspectives that take a stance with respect to the claim. Each perspective should be substantiated by evidence paragraphs which summarize pertinent results and facts. We construct PERSPECTRUM, a dataset of claims, perspectives and evidence, making use of online debate websites to create the initial data collection, and augmenting it using search engines in order to expand and diversify our dataset. We use crowd-sourcing to filter out noise and ensure high-quality data. Our dataset contains 1k claims, accompanied with pools of 10k and 8k perspective sentences and evidence paragraphs, respectively. We provide a thorough analysis of the dataset to highlight key underlying language understanding challenges, and show that human baselines across multiple subtasks far outperform ma-chine baselines built upon state-of-the-art NLP techniques. This poses a challenge and opportunity for the NLP community to address.
For many structured learning tasks, the data annotation process is complex and costly. Existing annotation schemes usually aim at acquiring completely annotated structures, under the common perception that partial structures are of low quality and could hurt the learning process. This paper questions this common perception, motivated by the fact that structures consist of interdependent sets of variables. Thus, given a fixed budget, partly annotating each structure may provide the same level of supervision, while allowing for more structures to be annotated. We provide an information theoretic formulation for this perspective and use it, in the context of three diverse structured learning tasks, to show that learning from partial structures can sometimes outperform learning from complete ones. Our findings may provide important insights into structured data annotation schemes and could support progress in learning protocols for structured tasks.
Training data for text classification is often limited in practice, especially for applications with many output classes or involving many related classification problems. This means classifiers must generalize from limited evidence, but the manner and extent of generalization is task dependent. Current practice primarily relies on pre-trained word embeddings to map words unseen in training to similar seen ones. Unfortunately, this squishes many components of meaning into highly restricted capacity. Our alternative begins with sparse pre-trained representations derived from unlabeled parsed corpora; based on the available training data, we select features that offers the relevant generalizations. This produces task-specific semantic vectors; here, we show that a feed-forward network over these vectors is especially effective in low-data scenarios, compared to existing state-of-the-art methods. By further pairing this network with a convolutional neural network, we keep this edge in low data scenarios and remain competitive when using full training sets.
Understanding time is crucial for understanding events expressed in natural language. Because people rarely say the obvious, it is often necessary to have commonsense knowledge about various temporal aspects of events, such as duration, frequency, and temporal order. However, this important problem has so far received limited attention. This paper systematically studies this temporal commonsense problem. Specifically, we define five classes of temporal commonsense, and use crowdsourcing to develop a new dataset, MCTACO, that serves as a test set for this task. We find that the best current methods used on MCTACO are still far behind human performance, by about 20%, and discuss several directions for improvement. We hope that the new dataset and our study here can foster more future research on this topic.
A key challenge in topic-focused summarization is determining what information should be included in the summary, a problem known as content selection. In this work, we propose a new method for studying content selection in topic-focused summarization called the summary cloze task. The goal of the summary cloze task is to generate the next sentence of a summary conditioned on the beginning of the summary, a topic, and a reference document(s). The main challenge is deciding what information in the references is relevant to the topic and partial summary and should be included in the summary. Although the cloze task does not address all aspects of the traditional summarization problem, the more narrow scope of the task allows us to collect a large-scale datset of nearly 500k summary cloze instances from Wikipedia. We report experimental results on this new dataset using various extractive models and a two-step abstractive model that first extractively selects a small number of sentences and then abstractively summarizes them. Our results show that the topic and partial summary help the models identify relevant content, but the task remains a significant challenge.
Zero-shot text classification (0Shot-TC) is a challenging NLU problem to which little attention has been paid by the research community. 0Shot-TC aims to associate an appropriate label with a piece of text, irrespective of the text domain and the aspect (e.g., topic, emotion, event, etc.) described by the label. And there are only a few articles studying 0Shot-TC, all focusing only on topical categorization which, we argue, is just the tip of the iceberg in 0Shot-TC. In addition, the chaotic experiments in literature make no uniform comparison, which blurs the progress. This work benchmarks the 0Shot-TC problem by providing unified datasets, standardized evaluations, and state-of-the-art baselines. Our contributions include: i) The datasets we provide facilitate studying 0Shot-TC relative to conceptually different and diverse aspects: the “topic” aspect includes “sports” and “politics” as labels; the “emotion” aspect includes “joy” and “anger”; the “situation” aspect includes “medical assistance” and “water shortage”. ii) We extend the existing evaluation setup (label-partially-unseen) – given a dataset, train on some labels, test on all labels – to include a more challenging yet realistic evaluation label-fully-unseen 0Shot-TC (Chang et al., 2008), aiming at classifying text snippets without seeing task specific training data at all. iii) We unify the 0Shot-TC of diverse aspects within a textual entailment formulation and study it this way.
Determining temporal relations (e.g., before or after) between events has been a challenging natural language understanding task, partly due to the difficulty to generate large amounts of high-quality training data. Consequently, neural approaches have not been widely used on it, or showed only moderate improvements. This paper proposes a new neural system that achieves about 10% absolute improvement in accuracy over the previous best system (25% error reduction) on two benchmark datasets. The proposed system is trained on the state-of-the-art MATRES dataset and applies contextualized word embeddings, a Siamese encoder of a temporal common sense knowledge base, and global inference via integer linear programming (ILP). We suggest that the new approach could serve as a strong baseline for future research in this area.
For those languages which use it, capitalization is an important signal for the fundamental NLP tasks of Named Entity Recognition (NER) and Part of Speech (POS) tagging. In fact, it is such a strong signal that model performance on these tasks drops sharply in common lowercased scenarios, such as noisy web text or machine translation outputs. In this work, we perform a systematic analysis of solutions to this problem, modifying only the casing of the train or test data using lowercasing and truecasing methods. While prior work and first impressions might suggest training a caseless model, or using a truecaser at test time, we show that the most effective strategy is a concatenation of cased and lowercased training data, producing a single model with high performance on both cased and uncased text. As shown in our experiments, this result holds across tasks and input representations. Finally, we show that our proposed solution gives an 8% F1 improvement in mention detection on noisy out-of-domain Twitter data.
To ensure readability, text is often written and presented with due formatting. These text formatting devices help the writer to effectively convey the narrative. At the same time, these help the readers pick up the structure of the discourse and comprehend the conveyed information. There have been a number of linguistic theories on discourse structure of text. However, these theories only consider unformatted text. Multimedia text contains rich formatting features that can be leveraged for various NLP tasks. In this article, we study some of these discourse features in multimedia text and what communicative function they fulfill in the context. As a case study, we use these features to harvest structured subject knowledge of geometry from textbooks. We conclude that the discourse and text layout features provide information that is complementary to lexical semantic information. Finally, we show that the harvested structured knowledge can be used to improve an existing solver for geometry problems, making it more accurate as well as more explainable.
In many NLP applications like search and information extraction for named entities, it is necessary to find all the mentions of a named entity, some of which appear as pronouns (she, his, etc.) or nominals (the professor, the German chancellor, etc.). It is therefore important that coreference resolution systems are able to link these different types of mentions to the correct entity name. We evaluate state-of-the-art coreference resolution systems for the task of resolving all mentions to named entities. Our analysis reveals that standard coreference metrics do not reflect adequately the requirements in this task: they do not penalize systems for not identifying any mentions by name to an entity and they reward systems even if systems find correctly mentions to the same entity but fail to link these to a proper name (she–the student–no name). We introduce new metrics for evaluating named entity coreference that address these discrepancies and show that for the comparisons of competitive systems, standard coreference evaluations could give misleading results for this task. We are, however, able to confirm that the state-of-the art system according to traditional evaluations also performs vastly better than other systems on the named entity coreference task.
This paper describes the Cognitive Computation (CogComp) Group’s submissions to the multilingual named entity recognition shared task at the Balto-Slavic Natural Language Processing (BSNLP) Workshop. The final model submitted is a multi-source neural NER system with multilingual BERT embeddings, trained on the concatenation of training data in various Slavic languages (as well as English). The performance of our system on the official testing data suggests that multi-source approaches consistently outperform single-source approaches for this task, even with the noise of mismatching tagsets.
We present a reading comprehension challenge in which questions can only be answered by taking into account information from multiple sentences. We solicit and verify questions and answers for this challenge through a 4-step crowdsourcing experiment. Our challenge dataset contains 6,500+ questions for 1000+ paragraphs across 7 different domains (elementary school science, news, travel guides, fiction stories, etc) bringing in linguistic diversity to the texts and to the questions wordings. On a subset of our dataset, we found human solvers to achieve an F1-score of 88.1%. We analyze a range of baselines, including a recent state-of-art reading comprehension system, and demonstrate the difficulty of this challenge, despite a high human performance. The dataset is the first to study multi-sentence inference at scale, with an open-ended set of question types that requires reasoning skills.
Cross-lingual Hypernymy Detection involves determining if a word in one language (“fruit”) is a hypernym of a word in another language (“pomme” i.e. apple in French). The ability to detect hypernymy cross-lingually can aid in solving cross-lingual versions of tasks such as textual entailment and event coreference. We propose BiSparse-Dep, a family of unsupervised approaches for cross-lingual hypernymy detection, which learns sparse, bilingual word embeddings based on dependency contexts. We show that BiSparse-Dep can significantly improve performance on this task, compared to approaches based only on lexical context. Our approach is also robust, showing promise for low-resource settings: our dependency-based embeddings can be learned using a parser trained on related languages, with negligible loss in performance. We also crowd-source a challenging dataset for this task on four languages – Russian, French, Arabic, and Chinese. Our embeddings and datasets are publicly available.
Extracting temporal relations (before, after, overlapping, etc.) is a key aspect of understanding events described in natural language. We argue that this task would gain from the availability of a resource that provides prior knowledge in the form of the temporal order that events usually follow. This paper develops such a resource – a probabilistic knowledge base acquired in the news domain – by extracting temporal relations between events from the New York Times (NYT) articles over a 20-year span (1987–2007). We show that existing temporal extraction systems can be improved via this resource. As a byproduct, we also show that interesting statistics can be retrieved from this resource, which can potentially benefit other time-aware tasks. The proposed system and resource are both publicly available.
People can identify correspondences between narratives in everyday life. For example, an analogy with the Cinderella story may be made in describing the unexpected success of an underdog in seemingly different stories. We present a new task and dataset for story understanding: identifying instances of similar narratives from a collection of narrative texts. We present an initial approach for this problem, which finds correspondences between narratives in terms of plot events, and resemblances between characters and their social relationships. Our approach yields an 8% absolute improvement in performance over a competitive information-retrieval baseline on a novel dataset of plot summaries of 577 movie remakes from Wikipedia.
Existing temporal relation (TempRel) annotation schemes often have low inter-annotator agreements (IAA) even between experts, suggesting that the current annotation task needs a better definition. This paper proposes a new multi-axis modeling to better capture the temporal structure of events. In addition, we identify that event end-points are a major source of confusion in annotation, so we also propose to annotate TempRels based on start-points only. A pilot expert annotation effort using the proposed scheme shows significant improvement in IAA from the conventional 60’s to 80’s (Cohen’s Kappa). This better-defined annotation scheme further enables the use of crowdsourcing to alleviate the labor intensity for each annotator. We hope that this work can foster more interesting studies towards event understanding.
Modeling derivational morphology to generate words with particular semantics is useful in many text generation tasks, such as machine translation or abstractive question answering. In this work, we tackle the task of derived word generation. That is, we attempt to generate the word “runner” for “someone who runs.” We identify two key problems in generating derived words from root words and transformations. We contribute a novel aggregation model of derived word generation that learns derivational transformations both as orthographic functions using sequence-to-sequence models and as functions in distributional word embedding space. The model then learns to choose between the hypothesis of each system. We also present two ways of incorporating corpus information into derived word generation.
Understanding temporal and causal relations between events is a fundamental natural language understanding task. Because a cause must occur earlier than its effect, temporal and causal relations are closely related and one relation often dictates the value of the other. However, limited attention has been paid to studying these two relations jointly. This paper presents a joint inference framework for them using constrained conditional models (CCMs). Specifically, we formulate the joint problem as an integer linear programming (ILP) problem, enforcing constraints that are inherent in the nature of time and causality. We show that the joint inference framework results in statistically significant improvement in the extraction of both temporal and causal relations from text.
This work deals with SciTail, a natural entailment challenge derived from a multi-choice question answering problem. The premises and hypotheses in SciTail were generated with no awareness of each other, and did not specifically aim at the entailment task. This makes it more challenging than other entailment data sets and more directly useful to the end-task – question answering. We propose DEISTE (deep explorations of inter-sentence interactions for textual entailment) for this entailment task. Given word-to-word interactions between the premise-hypothesis pair (P, H), DEISTE consists of: (i) a parameter-dynamic convolution to make important words in P and H play a dominant role in learnt representations; and (ii) a position-aware attentive convolution to encode the representation and position information of the aligned word pairs. Experiments show that DEISTE gets ≈5% improvement over prior state of the art and that the pretrained DEISTE on SciTail generalizes well on RTE-5.
We present a new web-based interface, TALEN, designed for named entity annotation in low-resource settings where the annotators do not speak the language. To address this non-traditional scenario, TALEN includes such features as in-place lexicon integration, TF-IDF token statistics, Internet search, and entity propagation, all implemented so as to make this difficult task efficient and frictionless. We conduct a small user study to compare against a popular annotation tool, showing that TALEN achieves higher precision and recall against ground-truth annotations, and that users strongly prefer it over the alternative. TALEN is available at: github.com/CogComp/talen.
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.
This paper describes the augmentation of an existing corpus of child-directed speech. The resulting corpus is a gold-standard labeled corpus for supervised learning of semantic role labels in adult-child dialogues. Semantic role labeling (SRL) models assign semantic roles to sentence constituents, thus indicating who has done what to whom (and in what way). The current corpus is derived from the Adam files in the Brown corpus (Brown 1973) of the CHILDES corpora, and augments the partial annotation described in Connor et al. (2010). It provides labels for both semantic arguments of verbs and semantic arguments of prepositions. The semantic role labels and senses of verbs follow Propbank guidelines Kingsbury and Palmer, 2002; Gildea and Palmer 2002; Palmer et al., 2005) and those for prepositions follow Srikumar and Roth (2011). The corpus was annotated by two annotators. Inter-annotator agreement is given separately for prepositions and verbs, and for adult speech and child speech. Overall, across child and adult samples, including verbs and prepositions, the kappa score for sense is 72.6, for the number of semantic-role-bearing arguments, the kappa score is 77.4, for identical semantic role labels on a given argument, the kappa score is 91.1, for the span of semantic role labels, and the kappa for agreement is 93.9. The sense and number of arguments was often open to multiple interpretations in child speech, due to the rapidly changing discourse and omission of constituents in production. Annotators used a discourse context window of ten sentences before and ten sentences after the target utterance to determine the annotation labels. The derived corpus is available for use in CHAT (MacWhinney, 2000) and XML format.
Math word problems form a natural abstraction to a range of quantitative reasoning problems, such as understanding financial news, sports results, and casualties of war. Solving such problems requires the understanding of several mathematical concepts such as dimensional analysis, subset relationships, etc. In this paper, we develop declarative rules which govern the translation of natural language description of these concepts to math expressions. We then present a framework for incorporating such declarative knowledge into word problem solving. Our method learns to map arithmetic word problem text to math expressions, by learning to select the relevant declarative knowledge for each operation of the solution expression. This provides a way to handle multiple concepts in the same problem while, at the same time, supporting interpretability of the answer expression. Our method models the mapping to declarative knowledge as a latent variable, thus removing the need for expensive annotations. Experimental evaluation suggests that our domain knowledge based solver outperforms all other systems, and that it generalizes better in the realistic case where the training data it is exposed to is biased in a different way than the test data.
Determining whether a given claim is supported by evidence is a fundamental NLP problem that is best modeled as Textual Entailment. However, given a large collection of text, finding evidence that could support or refute a given claim is a challenge in itself, amplified by the fact that different evidence might be needed to support or refute a claim. Nevertheless, most prior work decouples evidence finding from determining the truth value of the claim given the evidence. We propose to consider these two aspects jointly. We develop TwoWingOS (two-wing optimization strategy), a system that, while identifying appropriate evidence for a claim, also determines whether or not the claim is supported by the evidence. Given the claim, TwoWingOS attempts to identify a subset of the evidence candidates; given the predicted evidence, it then attempts to determine the truth value of the corresponding claim entailment problem. We treat this problem as coupled optimization problems, training a joint model for it. TwoWingOS offers two advantages: (i) Unlike pipeline systems it facilitates flexible-size evidence set, and (ii) Joint training improves both the claim entailment and the evidence identification. Experiments on a benchmark dataset show state-of-the-art performance.
Generating the English transliteration of a name written in a foreign script is an important and challenging step in multilingual knowledge acquisition and information extraction. Existing approaches to transliteration generation require a large (>5000) number of training examples. This difficulty contrasts with transliteration discovery, a somewhat easier task that involves picking a plausible transliteration from a given list. In this work, we present a bootstrapping algorithm that uses constrained discovery to improve generation, and can be used with as few as 500 training examples, which we show can be sourced from annotators in a matter of hours. This opens the task to languages for which large number of training examples are unavailable. We evaluate transliteration generation performance itself, as well the improvement it brings to cross-lingual candidate generation for entity linking, a typical downstream task. We present a comprehensive evaluation of our approach on nine languages, each written in a unique script.
The problem of entity-typing has been studied predominantly as a supervised learning problems, mostly with task-specific annotations (for coarse types) and sometimes with distant supervision (for fine types). While such approaches have strong performance within datasets they often lack the flexibility to transfer across text genres and to generalize to new type taxonomies. In this work we propose a zero-shot entity typing approach that requires no annotated data and can flexibly identify newly defined types. Given a type taxonomy, the entries of which we define as Boolean functions of freebase “types,” we ground a given mention to a set of type-compatible Wikipedia entries, and then infer the target mention’s type using an inference algorithm that makes use of the types of these entries. We evaluate our system on a broad range of datasets, including standard fine-grained and coarse-grained entity typing datasets, and on a dataset in the biological domain. Our system is shown to be competitive with state-of-the-art supervised NER systems, and to outperform them on out-of-training datasets. We also show that our system significantly outperforms other zero-shot fine typing systems.
Cross-lingual Entity Linking (XEL) aims to ground entity mentions written in any language to an English Knowledge Base (KB), such as Wikipedia. XEL for most languages is challenging, owing to limited availability of resources as supervision. We address this challenge by developing the first XEL approach that combines supervision from multiple languages jointly. This enables our approach to: (a) augment the limited supervision in the target language with additional supervision from a high-resource language (like English), and (b) train a single entity linking model for multiple languages, improving upon individually trained models for each language. Extensive evaluation on three benchmark datasets across 8 languages shows that our approach significantly improves over the current state-of-the-art. We also provide analyses in two limited resource settings: (a) zero-shot setting, when no supervision in the target language is available, and in (b) low-resource setting, when some supervision in the target language is available. Our analysis provides insights into the limitations of zero-shot XEL approaches in realistic scenarios, and shows the value of joint supervision in low-resource settings.
Character-level patterns have been widely used as features in English Named Entity Recognition (NER) systems. However, to date there has been no direct investigation of the inherent differences between name and nonname tokens in text, nor whether this property holds across multiple languages. This paper analyzes the capabilities of corpus-agnostic Character-level Language Models (CLMs) in the binary task of distinguishing name tokens from non-name tokens. We demonstrate that CLMs provide a simple and powerful model for capturing these differences, identifying named entity tokens in a diverse set of languages at close to the performance of full NER systems. Moreover, by adding very simple CLM-based features we can significantly improve the performance of an off-the-shelf NER system for multiple languages.
Automatic extraction of temporal information is important for natural language understanding. It involves two basic tasks: (1) Understanding time expressions that are mentioned explicitly in text (e.g., February 27, 1998 or tomorrow), and (2) Understanding temporal information that is conveyed implicitly via relations. This paper introduces CogCompTime, a system that has these two important functionalities. It incorporates the most recent progress, achieves state-of-the-art performance, and is publicly available at http://cogcomp.org/page/publication_view/844.
Annotating temporal relations (TempRel) between events described in natural language is known to be labor intensive, partly because the total number of TempRels is quadratic in the number of events. As a result, only a small number of documents are typically annotated, limiting the coverage of various lexical/semantic phenomena. In order to improve existing approaches, one possibility is to make use of the readily available, partially annotated data (P as in partial) that cover more documents. However, missing annotations in P are known to hurt, rather than help, existing systems. This work is a case study in exploring various usages of P for TempRel extraction. Results show that despite missing annotations, P is still a useful supervision signal for this task within a constrained bootstrapping learning framework. The system described in this system is publicly available.
Existing methods of hypernymy detection mainly rely on statistics over a big corpus, either mining some co-occurring patterns like “animals such as cats” or embedding words of interest into context-aware vectors. These approaches are therefore limited by the availability of a large enough corpus that can cover all terms of interest and provide sufficient contextual information to represent their meaning. In this work, we propose a new paradigm, HyperDef, for hypernymy detection – expressing word meaning by encoding word definitions, along with context driven representation. This has two main benefits: (i) Definitional sentences express (sense-specific) corpus-independent meanings of words, hence definition-driven approaches enable strong generalization – once trained, the model is expected to work well in open-domain testbeds; (ii) Global context from a large corpus and definitions provide complementary information for words. Consequently, our model, HyperDef, once trained on task-agnostic data, gets state-of-the-art results in multiple benchmarks
Words are polysemous and multi-faceted, with many shades of meanings. We suggest that sparse distributed representations are more suitable than other, commonly used, (dense) representations to express these multiple facets, and present Category Builder, a working system that, as we show, makes use of sparse representations to support multi-faceted lexical representations. We argue that the set expansion task is well suited to study these meaning distinctions since a word may belong to multiple sets with a different reason for membership in each. We therefore exhibit the performance of Category Builder on this task, while showing that our representation captures at the same time analogy problems such as “the Ganga of Egypt” or “the Voldemort of Tolkien”. Category Builder is shown to be a more expressive lexical representation and to outperform dense representations such as Word2Vec in some analogy classes despite being shown only two of the three input terms.
Question answering (QA) systems are easily distracted by irrelevant or redundant words in questions, especially when faced with long or multi-sentence questions in difficult domains. This paper introduces and studies the notion of essential question terms with the goal of improving such QA solvers. We illustrate the importance of essential question terms by showing that humans’ ability to answer questions drops significantly when essential terms are eliminated from questions. We then develop a classifier that reliably (90% mean average precision) identifies and ranks essential terms in questions. Finally, we use the classifier to demonstrate that the notion of question term essentiality allows state-of-the-art QA solver for elementary-level science questions to make better and more informed decisions,improving performance by up to 5%.We also introduce a new dataset of over 2,200 crowd-sourced essential terms annotated science questions.
Understanding stories – sequences of events – is a crucial yet challenging natural language understanding task. These events typically carry multiple aspects of semantics including actions, entities and emotions. Not only does each individual aspect contribute to the meaning of the story, so does the interaction among these aspects. Building on this intuition, we propose to jointly model important aspects of semantic knowledge – frames, entities and sentiments – via a semantic language model. We achieve this by first representing these aspects’ semantic units at an appropriate level of abstraction and then using the resulting vector representations for each semantic aspect to learn a joint representation via a neural language model. We show that the joint semantic language model is of high quality and can generate better semantic sequences than models that operate on the word level. We further demonstrate that our joint model can be applied to story cloze test and shallow discourse parsing tasks with improved performance and that each semantic aspect contributes to the model.
This article considers the problem of correcting errors made by English as a Second Language writers from a machine learning perspective, and addresses an important issue of developing an appropriate training paradigm for the task, one that accounts for error patterns of non-native writers using minimal supervision. Existing training approaches present a trade-off between large amounts of cheap data offered by the native-trained models and additional knowledge of learner error patterns provided by the more expensive method of training on annotated learner data. We propose a novel training approach that draws on the strengths offered by the two standard training paradigms—of training either on native or on annotated learner data—and that outperforms both of these standard methods. Using the key observation that parameters relating to error regularities exhibited by non-native writers are relatively simple, we develop models that can incorporate knowledge about error regularities based on a small annotated sample but that are otherwise trained on native English data. The key contribution of this article is the introduction and analysis of two methods for adapting the learned models to error patterns of non-native writers; one method that applies to generative classifiers and a second that applies to discriminative classifiers. Both methods demonstrated state-of-the-art performance in several text correction competitions. In particular, the Illinois system that implements these methods ranked at the top in two recent CoNLL shared tasks on error correction.1 We conduct further evaluation of the proposed approaches studying the effect of using error data from speakers of the same native language, languages that are closely related linguistically, and unrelated languages.
Identifying temporal relations between events is an essential step towards natural language understanding. However, the temporal relation between two events in a story depends on, and is often dictated by, relations among other events. Consequently, effectively identifying temporal relations between events is a challenging problem even for human annotators. This paper suggests that it is important to take these dependencies into account while learning to identify these relations and proposes a structured learning approach to address this challenge. As a byproduct, this provides a new perspective on handling missing relations, a known issue that hurts existing methods. As we show, the proposed approach results in significant improvements on the two commonly used data sets for this problem.
Automatic story comprehension is a fundamental challenge in Natural Language Understanding, and can enable computers to learn about social norms, human behavior and commonsense. In this paper, we present a story comprehension model that explores three distinct semantic aspects: (i) the sequence of events described in the story, (ii) its emotional trajectory, and (iii) its plot consistency. We judge the model’s understanding of real-world stories by inquiring if, like humans, it can develop an expectation of what will happen next in a given story. Specifically, we use it to predict the correct ending of a given short story from possible alternatives. The model uses a hidden variable to weigh the semantic aspects in the context of the story. Our experiments demonstrate the potential of our approach to characterize these semantic aspects, and the strength of the hidden variable based approach. The model outperforms the state-of-the-art approaches and achieves best results on a publicly available dataset.
Recent work in NLP has attempted to deal with low-resource languages but still assumed a resource level that is not present for most languages, e.g., the availability of Wikipedia in the target language. We propose a simple method for cross-lingual named entity recognition (NER) that works well in settings with very minimal resources. Our approach makes use of a lexicon to “translate” annotated data available in one or several high resource language(s) into the target language, and learns a standard monolingual NER model there. Further, when Wikipedia is available in the target language, our method can enhance Wikipedia based methods to yield state-of-the-art NER results; we evaluate on 7 diverse languages, improving the state-of-the-art by an average of 5.5% F1 points. With the minimal resources required, this is an extremely portable cross-lingual NER approach, as illustrated using a truly low-resource language, Uyghur.
For accurate entity linking, we need to capture various information aspects of an entity, such as its description in a KB, contexts in which it is mentioned, and structured knowledge. Additionally, a linking system should work on texts from different domains without requiring domain-specific training data or hand-engineered features. In this work we present a neural, modular entity linking system that learns a unified dense representation for each entity using multiple sources of information, such as its description, contexts around its mentions, and its fine-grained types. We show that the resulting entity linking system is effective at combining these sources, and performs competitively, sometimes out-performing current state-of-the-art systems across datasets, without requiring any domain-specific training data or hand-engineered features. We also show that our model can effectively “embed” entities that are new to the KB, and is able to link its mentions accurately.
Making decisions in natural language processing problems often involves assigning values to sets of interdependent variables where the expressive dependency structure can influence, or even dictate what assignments are possible. This setting includes a broad range of structured prediction problems such as semantic role labeling, named entity and relation recognition, co-reference resolution, dependency parsing and semantic parsing. The setting is also appropriate for cases that may require making global decisions that involve multiple components, possibly pre-designed or pre-learned, as in event recognition and analysis, summarization, paraphrasing, textual entailment and question answering. In all these cases, it is natural to formulate the decision problem as a constrained optimization problem, with an objective function that is composed of learned models, subject to domain or problem specific constraints.Over the last few years, starting with a couple of papers written by (Roth & Yih, 2004, 2005), dozens of papers have been using the Integer linear programming (ILP) formulation developed there, including several award-winning papers (e.g., (Martins, Smith, & Xing, 2009; Koo, Rush, Collins, Jaakkola, & Sontag., 2010; Berant, Dagan, & Goldberger, 2011)).This tutorial will present the key ingredients of ILP formulations of natural language processing problems, aiming at guiding readers through the key modeling steps, explaining the learning and inference paradigms and exemplifying these by providing examples from the literature. We will cover a range of topics, from the theoretical foundations of learning and inference with ILP models, to practical modeling guides, to software packages and applications.The goal of this tutorial is to introduce the computational framework to broader ACL community, motivate it as a generic framework for learning and inference in global NLP decision problems, present some of the key theoretical and practical issues involved and survey some of the existing applications of it as a way to promote further development of the framework and additional applications. We will also make connections with some of the “hot” topics in current NLP research and show how they can be used within the general framework proposed here. The tutorial will thus be useful for many of the senior and junior researchers that have interest in global decision problems in NLP, providing a concise overview of recent perspectives and research results.
We propose to move from Open Information Extraction (OIE) ahead to Open Knowledge Representation (OKR), aiming to represent information conveyed jointly in a set of texts in an open text-based manner. We do so by consolidating OIE extractions using entity and predicate coreference, while modeling information containment between coreferring elements via lexical entailment. We suggest that generating OKR structures can be a useful step in the NLP pipeline, to give semantic applications an easy handle on consolidated information across multiple texts.
Agents that communicate back and forth with humans to help them execute non-linguistic tasks are a long sought goal of AI. These agents need to translate between utterances and actionable meaning representations that can be interpreted by task-specific problem solvers in a context-dependent manner. They should also be able to learn such actionable interpretations for new predicates on the fly. We define an agent architecture for this scenario and present a series of experiments in the Blocks World domain that illustrate how our architecture supports language learning and problem solving in this domain.
We consider the problem of disambiguating concept mentions appearing in documents and grounding them in multiple knowledge bases, where each knowledge base addresses some aspects of the domain. This problem poses a few additional challenges beyond those addressed in the popular Wikification problem. Key among them is that most knowledge bases do not contain the rich textual and structural information Wikipedia does; consequently, the main supervision signal used to train Wikification rankers does not exist anymore. In this work we develop an algorithmic approach that, by carefully examining the relations between various related knowledge bases, generates an indirect supervision signal it uses to train a ranking model that accurately chooses knowledge base entries for a given mention; moreover, it also induces prior knowledge that can be used to support a global coherent mapping of all the concepts in a given document to the knowledge bases. Using the biomedical domain as our application, we show that our indirectly supervised ranking model outperforms other unsupervised baselines and that the quality of this indirect supervision scheme is very close to a supervised model. We also show that considering multiple knowledge bases together has an advantage over grounding concepts to each knowledge base individually.
When designing Natural Language Processing (NLP) applications that use Machine Learning (ML) techniques, feature extraction becomes a significant part of the development effort, whether developing a new application or attempting to reproduce results reported for existing NLP tasks. We present EDISON, a Java library of feature generation functions used in a suite of state-of-the-art NLP tools, based on a set of generic NLP data structures. These feature extractors populate simple data structures encoding the extracted features, which the package can also serialize to an intuitive JSON file format that can be easily mapped to formats used by ML packages. EDISON can also be used programmatically with JVM-based (Java/Scala) NLP software to provide the feature extractor input. The collection of feature extractors is organised hierarchically and a simple search interface is provided. In this paper we include examples that demonstrate the versatility and ease-of-use of the EDISON feature extraction suite to show that this can significantly reduce the time spent by developers on feature extraction design for NLP systems. The library is publicly hosted at https://github.com/IllinoisCogComp/illinois-cogcomp-nlp/, and we hope that other NLP researchers will contribute to the set of feature extractors. In this way, the community can help simplify reproduction of published results and the integration of ideas from diverse sources when developing new and improved NLP applications.
Cross document event coreference (CDEC) is an important task that aims at aggregating event-related information across multiple documents. We revisit the evaluation for CDEC, and discover that past works have adopted different, often inconsistent, evaluation settings, which either overlook certain mistakes in coreference decisions, or make assumptions that simplify the coreference task considerably. We suggest a new evaluation methodology which overcomes these limitations, and allows for an accurate assessment of CDEC systems. Our new evaluation setting better reflects the corpus-wide information aggregation ability of CDEC systems by separating event-coreference decisions made across documents from those made within a document. In addition, we suggest a better baseline for the task and semi-automatically identify several inconsistent annotations in the evaluation dataset.
We present a novel way for designing complex joint inference and learning models using Saul (Kordjamshidi et al., 2015), a recently-introduced declarative learning-based programming language (DeLBP). We enrich Saul with components that are necessary for a broad range of learning based Natural Language Processing tasks at various levels of granularity. We illustrate these advances using three different, well-known NLP problems, and show how these generic learning and inference modules can directly exploit Saul’s graph-based data representation. These properties allow the programmer to easily switch between different model formulations and configurations, and consider various kinds of dependencies and correlations among variables of interest with minimal programming effort. We argue that Saul provides an extremely useful paradigm both for the design of advanced NLP systems and for supporting advanced research in NLP.
We release a cross-lingual wikification system for all languages in Wikipedia. Given a piece of text in any supported language, the system identifies names of people, locations, organizations, and grounds these names to the corresponding English Wikipedia entries. The system is based on two components: a cross-lingual named entity recognition (NER) model and a cross-lingual mention grounding model. The cross-lingual NER model is a language-independent model which can extract named entity mentions in the text of any language in Wikipedia. The extracted mentions are then grounded to the English Wikipedia using the cross-lingual mention grounding model. The only resources required to train the proposed system are the multilingual Wikipedia dump and existing training data for English NER. The system is online at http://cogcomp.cs.illinois.edu/page/demo_view/xl_wikifier
Little work from the Natural Language Processing community has targeted the role of quantities in Natural Language Understanding. This paper takes some key steps towards facilitating reasoning about quantities expressed in natural language. We investigate two different tasks of numerical reasoning. First, we consider Quantity Entailment, a new task formulated to understand the role of quantities in general textual inference tasks. Second, we consider the problem of automatically understanding and solving elementary school math word problems. In order to address these quantitative reasoning problems we first develop a computational approach which we show to successfully recognize and normalize textual expressions of quantities. We then use these capabilities to further develop algorithms to assist reasoning in the context of the aforementioned tasks.
Natural Language Processing (NLP) continues to grow in popularity in a range of research and commercial applications. However, installing, maintaining, and running NLP tools can be time consuming, and many commercial and research end users have only intermittent need for large processing capacity. This paper describes ILLINOISCLOUDNLP, an on-demand framework built around NLPCURATOR and Amazon Web Services Elastic Compute Cloud (EC2). This framework provides a simple interface to end users via which they can deploy one or more NLPCURATOR instances on EC2, upload plain text documents, specify a set of Text Analytics tools (NLP annotations) to apply, and process and store or download the processed data. It can also allow end users to use a model trained on their own data: ILLINOISCLOUDNLP takes care of training, hosting, and applying it to new data just as it does with existing models within NLPCURATOR. As a representative use case, we describe our use of ILLINOISCLOUDNLP to process 3.05 million documents used in the 2012 and 2013 Text Analysis Conference Knowledge Base Population tasks at a relatively deep level of processing, in approximately 20 hours, at an approximate cost of US$500; this is about 20 times faster than doing so on a single server and requires no human supervision and no NLP or Machine Learning expertise.
This paper identifies and examines the key principles underlying building a state-of-the-art grammatical error correction system. We do this by analyzing the Illinois system that placed first among seventeen teams in the recent CoNLL-2013 shared task on grammatical error correction. The system focuses on five different types of errors common among non-native English writers. We describe four design principles that are relevant for correcting all of these errors, analyze the system along these dimensions, and show how each of these dimensions contributes to the performance.
This paper introduces the problem of predicting semantic relations expressed by prepositions and develops statistical learning models for predicting the relations, their arguments and the semantic types of the arguments. We define an inventory of 32 relations, building on the word sense disambiguation task for prepositions and collapsing related senses across prepositions. Given a preposition in a sentence, our computational task to jointly model the preposition relation and its arguments along with their semantic types, as a way to support the relation prediction. The annotated data, however, only provides labels for the relation label, and not the arguments and types. We address this by presenting two models for preposition relation labeling. Our generalization of latent structure SVM gives close to 90% accuracy on relation labeling. Further, by jointly predicting the relation, arguments, and their types along with preposition sense, we show that we can not only improve the relation accuracy, but also significantly improve sense prediction accuracy.
Natural Language Processing continues to grow in popularity in a range of research and commercial applications, yet managing the wide array of potential NLP components remains a difficult problem. This paper describes Curator, an NLP management framework designed to address some common problems and inefficiencies associated with building NLP process pipelines; and Edison, an NLP data structure library in Java that provides streamlined interactions with Curator and offers a range of useful supporting functionality.
Today's natural language processing systems are growing more complex with the need to incorporate a wider range of language resources and more sophisticated statistical methods. In many cases, it is necessary to learn a component with input that includes the predictions of other learned components or to assign simultaneously the values that would be assigned by multiple components with an expressive, data dependent structure among them. As a result, the design of systems with multiple learning components is inevitably quite technically complex, and implementations of conceptually simple NLP systems can be time consuming and prone to error. Our new modeling language, Learning Based Java (LBJ), facilitates the rapid development of systems that learn and perform inference. LBJ has already been used to build state of the art NLP systems. In this paper, we first demonstrate that there exists a theoretical model that describes most NLP approaches adeptly. Second, we show how our improvements to the LBJ language enable the programmer to describe the theoretical model succinctly. Finally, we introduce the concept of data driven compilation, a translation process in which the efficiency of the generated code benefits from the data given as input to the learning algorithms.