The applications of large language models (LLMs) have expanded well beyond the confines of text processing, signaling a new era where LLMs are envisioned as generalist agents capable of operating within complex environments. These environments are often highly expansive, making it impossible for the LLM to process them within its short-term memory. Motivated by recent research on extending the capabilities of LLMs with tools, we seek to investigate the intriguing potential of tools to augment LLMs in handling such complexity by introducing a novel class of tools, termed *middleware*, to aid in the proactive exploration within these massive environments. Such specialized tools can serve as a middleware layer shielding the LLM from environmental complexity. In two representative complex environments—knowledge bases (KBs) and databases—we demonstrate the significant potential of augmenting language agents with tools in complex environments. Notably, equipped with the middleware, GPT-4 achieves **2.8**X the performance of the best baseline in tasks requiring access to database content and **2.2**X in KB tasks. Our findings illuminate the path for advancing language agents in real-world applications.

The emergence of personalized generation has made it possible to create texts or images that meet the unique needs of users. Recent advances mainly focus on style or scene transfer based on given keywords. However, in e-commerce and recommender systems, it is almost an untouched area to explore user historical interactions, automatically mine user interests with semantic associations, and create item representations that closely align with user individual interests.In this paper, we propose a brand new framework called **I**nterest-**A**ugmented **M**ultimodal **G**enerator (**I-AM-G**). The framework first extracts tags from the multimodal information of items that the user has interacted with, and the most frequently occurred ones are extracted to rewrite the text description of the item. Then, the framework uses a decoupled text-to-text and image-to-image retriever to search for the top-K similar item text and image embeddings from the item pool. Finally, the Attention module for user interests fuses the retrieved information in a cross-modal manner and further guides the personalized generation process in collaboration with the rewritten text.We conducted extensive and comprehensive experiments to demonstrate that our framework can effectively generate results aligned with user preferences, which potentially provides a new paradigm of **Rewrite and Retrieve** for personalized generation.

Web agents are emerging as powerful tools capable of performing complex tasks across diverse web environments. The rapid development of large multimodal models is further enhancing this advancement. However, there is a lack of standardized and user-friendly tools for research and development, as well as experimental platforms on live websites. To address this challenge, we present WebOlympus, an open platform for web agents operating on live websites. WebOlympus offers a Chrome extension-based UI, enabling users without programming experience to easily utilize the platform. It allows users to run web agents with various designs using only a few lines of code or simple clicks on the Chrome extension. To ensure the trustworthiness of web agents, a safety monitor module that prevents harmful actions through human supervision or model-based control is incorporated. WebOlympus supports diverse applications, including annotation interfaces for web agent trajectories and data crawling.

Language agents are autonomous agents, usually powered by large language models, that can follow language instructions to carry out diverse and complex tasks in real-world or simulated environments. It is one of the most heated discussion threads in AI and NLP at present with many proof-of-concept efforts, yet there lacks a systematic account of the conceptual definition, theoretical foundation, promising directions, and risks of language agents. This proposed tutorial aspires to fill this gap by providing a conceptual framework of language agents as well as giving a comprehensive discussion on important topic areas including tool augmentation, grounding, reasoning and planning, multi-agent systems, and rissk and societal impact. Language played a critical role in the evolution of biological intelligence, and now artificial intelligence may be following a similar evolutionary path. This is remarkable and concerning at the same time. We hope this tutorial will provide a timely framework to facilitate constructive discussion on this important emerging topic.

The gap between the trepidation of program reliability and the expense of repairs underscore the indispensability for Automated Program Repair (APR). APR is instrumental in transforming vulnerable programs into more robust ones, bolstering program reliability while simultaneously diminishing the financial burden of manual repairs. Commercial-scale language models (LM) have taken APR to unprecedented levels. However, due to the limitations of model capabilities by parameters, a one-step substantial modification may not achieve the desired effect for models with parameters less than 100B. Moreover, humans interact with the LLM through explicit prompts, which hinders the LLM from receiving feedback from compiler and test cases to automatically optimize its repair policies. Explicit prompts from humans not only increase additional manpower costs, but also pose potential misunderstandings between human’s intent and LMs.Based on the above considerations, we are exploring how to ensure small-scale LM still outperform through process supervision and feedback. We start by constructing a dataset named CodeNet4Repair, replete with multiple repair records, which supervises the fine-tuning of a foundational mode. Building upon the encouraging outcomes of reinforcement learning, we develop a reward model that serves as a critic, providing feedback for the fine-tuned LM’s action, progressively optimizing its policy. During inference, we require the LM to generate solutions iteratively until the repair effect no longer improves or hits the maximum step limit. The experimental results show that this process-based feedback not only outperforms larger outcome-based generation methods, but also nearly matches the performance of closed-source commercial large-scale LMs.

Tools are essential for large language models (LLMs) to acquire up-to-date information and take consequential actions in external environments. Existing work on tool-augmented LLMs primarily focuses on the broad coverage of tools and the flexibility of adding new tools. However, a critical aspect that has surprisingly been understudied is simply how accurately an LLM uses tools for which it has been trained. We find that existing LLMs, including GPT-4 and open-source LLMs specifically fine-tuned for tool use, only reach a correctness rate in the range of 30% to 60%, far from reliable use in practice. We propose a biologically inspired method for tool-augmented LLMs, simulated trial and error (STE), that orchestrates three key mechanisms for successful tool use behaviors in the biological system: trial and error, imagination, and memory. Specifically, STE leverages an LLM’s ‘imagination’ to simulate plausible scenarios for using a tool, after which the LLM interacts with the tool to learn from its execution feedback. Both short-term and long-term memory are employed to improve the depth and breadth of the exploration, respectively. Comprehensive experiments on ToolBench show that STE substantially improves tool learning for LLMs under both in-context learning and fine-tuning settings, bringing a boost of 46.7% to Mistral-Instruct-7B and enabling it to outperform GPT-4. We also show effective continual learning of tools via a simple experience replay strategy.

In this paper, we examine how large language models (LLMs) solve multi-step problems under a language agent framework with three components: a generator, a discriminator, and a planning method. We investigate the practical utility of two advanced planning methods, iterative correction and tree search. We present a comprehensive analysis of how discrimination accuracy affects the overall performance of agents when using these two methods or a simpler method, re-ranking. Experiments on two tasks, text-to-SQL parsing and mathematical reasoning, show that: (1) advanced planning methods demand discriminators with at least 90% accuracy to achieve significant improvements over re-ranking; (2) current LLMs’ discrimination abilities have not met the needs of advanced planning methods to achieve such improvements; (3) with LLM-based discriminators, advanced planning methods may not adequately balance accuracy and efficiency. For example, compared to the other two methods, tree search is at least 10–20 times slower but leads to negligible performance gains, which hinders its real-world applications.

A key missing capacity of current language models (LMs) is grounding to real-world environments. Most existing work for grounded language understanding uses LMs to directly generate plans that can be executed in the environment to achieve the desired effects. It thereby casts the burden of ensuring grammaticality, faithfulness, and controllability all on the LMs. We propose Pangu, a generic framework for grounded language understanding that capitalizes on the discriminative ability of LMs instead of their generative ability. Pangu consists of a symbolic agent and a neural LM working in a concerted fashion: The agent explores the environment to incrementally construct valid plans, and the LM evaluates the plausibility of the candidate plans to guide the search process. A case study on the challenging problem of knowledge base question answering (KBQA), which features a massive environment, demonstrates the remarkable effectiveness and flexibility of Pangu: A BERT-base LM is sufficient for setting a new record on standard KBQA datasets, and larger LMs further bring substantial gains.Pangu also enables, for the first time, effective few-shot in-context learning for KBQA with large LMs such as Codex.

Task-oriented dialogue systems often assist users with personal or confidential matters. For this reason, the developers of such a system are generally prohibited from observing actual usage. So how can they know where the system is failing and needs more training data or new functionality? In this work, we study ways in which realistic user utterances can be generated synthetically, to help increase the linguistic and functional coverage of the system, without compromising the privacy of actual users. To this end, we propose a two-stage Differentially Private (DP) generation method which first generates latent semantic parses, and then generates utterances based on the parses. Our proposed approach improves MAUVE by 2.5X and parse tree function-type overlap by 1.3X relative to current approaches for private synthetic data generation, improving both on fluency and semantic coverage. We further validate our approach on a realistic domain adaptation task of adding new functionality from private user data to a semantic parser, and show overall gains of 8.5% points on its accuracy with the new feature.

Question answering over knowledge bases is considered a difficult problem due to the challenge of generalizing to a wide variety of possible natural language questions. Additionally, the heterogeneity of knowledge base schema items between different knowledge bases often necessitates specialized training for different knowledge base question-answering (KBQA) datasets. To handle questions over diverse KBQA datasets with a unified training-free framework, we propose KB-BINDER, which for the first time enables few-shot in-context learning over KBQA tasks. Firstly, KB-BINDER leverages large language models like Codex to generate logical forms as the draft for a specific question by imitating a few demonstrations. Secondly, KB-BINDER grounds on the knowledge base to bind the generated draft to an executable one with BM25 score matching. The experimental results on four public heterogeneous KBQA datasets show that KB-BINDER can achieve a strong performance with only a few in-context demonstrations. Especially on GraphQA and 3-hop MetaQA, KB-BINDER can even outperform the state-of-the-art trained models. On GrailQA and WebQSP, our model is also on par with other fully-trained models. We believe KB-BINDER can serve as an important baseline for future research. We plan to release all the code and data. Our code is available at https://github.com/ltl3A87/KB-BINDER.

This paper studies a new task of federated learning (FL) for semantic parsing, where multiple clients collaboratively train one global model without sharing their semantic parsing data. By leveraging data from multiple clients, the FL paradigm can be especially beneficial for clients that have little training data to develop a data-hungry neural semantic parser on their own. We propose an evaluation setup to study this task, where we re-purpose widely-used single-domain text-to-SQL datasets as clients to form a realistic heterogeneous FL setting and collaboratively train a global model. As standard FL algorithms suffer from the high client heterogeneity in our realistic setup, we further propose a novel LOss Reduction Adjusted Re-weighting (Lorar) mechanism, which adjusts each client’s contribution to the global model update based on its training loss reduction during each round. Our intuition is that the larger the loss reduction, the further away the current global model is from the client’s local optimum, and the larger weight the client should get. By applying Lorar to three widely adopted FL algorithms (FedAvg, FedOPT and FedProx), we observe that their performance can be improved substantially on average (4%-20% absolute gain under MacroAvg) and that clients with smaller datasets enjoy larger performance gains. In addition, the global model converges faster for almost all the clients.

Despite recent progress in text-to-SQL parsing, current semantic parsers are still not accurate enough for practical use. In this paper, we investigate how to build automatic text-to-SQL error correction models. Noticing that token-level edits are out of context and sometimes ambiguous, we propose building clause-level edit models instead. Besides, while most language models of code are not specifically pre-trained for SQL, they know common data structures and their operations in programming languages such as Python. Thus, we propose a novel representation for SQL queries and their edits that adheres more closely to the pre-training corpora of language models of code. Our error correction model improves the exact set match accuracy of different parsers by 2.4-6.5 and obtains up to 4.3 point absolute improvement over two strong baselines.

As opposed to general English, many concepts in biomedical terminology have been designed in recent history by biomedical professionals with the goal of being precise and concise. This is often achieved by concatenating meaningful biomedical morphemes to create new semantic units. Nevertheless, most modern biomedical language models (LMs) are pre-trained using standard domain-specific tokenizers derived from large scale biomedical corpus statistics without explicitly leveraging the agglutinating nature of biomedical language. In this work, we first find that standard open-domain and biomedical tokenizers are largely unable to segment biomedical terms into meaningful components. Therefore, we hypothesize that using a tokenizer which segments biomedical terminology more accurately would enable biomedical LMs to improve their performance on downstream biomedical NLP tasks, especially ones which involve biomedical terms directly such as named entity recognition (NER) and entity linking. Surprisingly, we find that pre-training a biomedical LM using a more accurate biomedical tokenizer does not improve the entity representation quality of a language model as measured by several intrinsic and extrinsic measures such as masked language modeling prediction (MLM) accuracy as well as NER and entity linking performance. These quantitative findings, along with a case study which explores entity representation quality more directly, suggest that the biomedical pre-training process is quite robust to instances of sub-optimal tokenization.

Recent work has shown that fine-tuning large language models (LLMs) on large-scale instruction-following datasets substantially improves their performance on a wide range of NLP tasks, especially in the zero-shot setting. However, even advanced instruction-tuned LLMs still fail to outperform small LMs on relation extraction (RE), a fundamental information extraction task. We hypothesize that instruction-tuning has been unable to elicit strong RE capabilities in LLMs due to RE’s low incidence in instruction-tuning datasets, making up less than 1% of all tasks (Wang et al. 2022). To address this limitation, we propose QA4RE, a framework that aligns RE with question answering (QA), a predominant task in instruction-tuning datasets. Comprehensive zero-shot RE experiments over four datasets with two series of instruction-tuned LLMs (six LLMs in total) demonstrate that our QA4RE framework consistently improves LLM performance, strongly verifying our hypothesis and enabling LLMs to outperform strong zero-shot baselines by a large margin. Additionally, we provide thorough experiments and discussions to show the robustness, few-shot effectiveness, and strong transferability of our QA4RE framework. This work illustrates a promising way of adapting LLMs to challenging and underrepresented tasks by aligning these tasks with more common instruction-tuning tasks like QA.

As the immense opportunities enabled by large language models become more apparent, NLP systems will be increasingly expected to excel in real-world settings. However, in many instances, powerful models alone will not yield translational NLP solutions, especially if the formulated problem is not well aligned with the real-world task. In this work, we study the case of UMLS vocabulary insertion, an important real-world task in which hundreds of thousands of new terms, referred to as atoms, are added to the UMLS, one of the most comprehensive open-source biomedical knowledge bases. Previous work aimed to develop an automated NLP system to make this time-consuming, costly, and error-prone task more efficient. Nevertheless, practical progress in this direction has been difficult to achieve due to a problem formulation and evaluation gap between research output and the real-world task. In order to address this gap, we introduce a new formulation for UMLS vocabulary insertion which mirrors the real-world task, datasets which faithfully represent it and several strong baselines we developed through re-purposing existing solutions. Additionally, we propose an effective rule-enhanced biomedical language model which enables important new model behavior, outperforms all strong baselines and provides measurable qualitative improvements to editors who carry out the UVI task. We hope this case study provides insight into the considerable importance of problem formulation for the success of translational NLP solutions.

A recent focus of large language model (LLM) development, as exemplified by generative search engines, is to incorporate external references to generate and support its claims. However, evaluating the attribution, i.e., verifying whether the generated statement is fully supported by the cited reference, remains an open problem. Although human evaluation is common practice, it is costly and time-consuming. In this paper, we investigate automatic evaluation of attribution given by LLMs. We begin by defining different types of attribution errors, and then explore two approaches for automatic evaluation: prompting LLMs and fine-tuning smaller LMs. The fine-tuning data is repurposed from related tasks such as question answering, fact-checking, natural language inference, and summarization. We manually curate a set of test examples covering 12 domains from a generative search engine, New Bing. Our results on this curated test set and simulated examples from existing benchmarks highlight both promising signals and challenges. We hope our problem formulation, testbeds, and findings will help lay the foundation for future studies on this important problem.

Despite remarkable progress in text-to-SQL semantic parsing in recent years, the performance of existing parsers is still far from perfect. Specifically, modern text-to-SQL parsers based on deep learning are often over-confident, thus casting doubt on their trustworthiness when deployed for real use. In this paper, we propose a parser-independent error detection model for text-to-SQL semantic parsing. Using a language model of code as its bedrock, we enhance our error detection model with graph neural networks that learn structural features of both natural language questions and SQL queries. We train our model on realistic parsing errors collected from a cross-domain setting, which leads to stronger generalization ability. Experiments with three strong text-to-SQL parsers featuring different decoding mechanisms show that our approach outperforms parser-dependent uncertainty metrics. Our model could also effectively improve the performance and usability of text-to-SQL semantic parsers regardless of their architectures.

We introduce TacoBot, a user-centered task-oriented digital assistant designed to guide users through complex real-world tasks with multiple steps. Covering a wide range of cooking and how-to tasks, we aim to deliver a collaborative and engaging dialogue experience. Equipped with language understanding, dialogue management, and response generation components supported by a robust search engine, TacoBot ensures efficient task assistance. To enhance the dialogue experience, we explore a series of data augmentation strategies using LLMs to train advanced neural models continuously. TacoBot builds upon our successful participation in the inaugural Alexa Prize TaskBot Challenge, where our team secured third place among ten competing teams. We offer TacoBot as an open-source framework that serves as a practical example for deploying task-oriented dialogue systems.

Text-to-SQL parsers map natural language questions to programs that are executable over tables to generate answers, and are typically evaluated on large-scale datasets like Spider (Yu et al., 2018). We argue that existing benchmarks fail to capture a certain out-of-domain generalization problem that is of significant practical importance: matching domain specific phrases to composite operation over columns. To study this problem, we first propose a synthetic dataset along with a re-purposed train/test split of the Squall dataset (Shi et al., 2020) as new benchmarks to quantify domain generalization over column operations, and find existing state-of-the-art parsers struggle in these benchmarks. We propose to address this problem by incorporating prior domain knowledge by preprocessing table schemas, and design a method that consists of two components: schema expansion and schema pruning. This method can be easily applied to multiple existing base parsers, and we show that it significantly outperforms baseline parsers on this domain generalization problem, boosting the underlying parsers’ overall performance by up to 13.8% relative accuracy gain (5.1% absolute) on the new Squall data split.

In natural language understanding (NLU) production systems, users’ evolving needs necessitate the addition of new features over time, indexed by new symbols added to the meaning representation space. This requires additional training data and results in ever-growing datasets. We present the first systematic investigation into this incremental symbol learning scenario. Our analysis reveals a troubling quirk in building broad-coverage NLU systems: as the training dataset grows, performance on a small set of new symbols often decreases. We show that this trend holds for multiple mainstream models on two common NLU tasks: intent recognition and semantic parsing. Rejecting class imbalance as the sole culprit, we reveal that the trend is closely associated with an effect we call source signal dilution, where strong lexical cues for the new symbol become diluted as the training dataset grows. Selectively dropping training examples to prevent dilution often reverses the trend, showing the over-reliance of mainstream neural NLU models on simple lexical cues.

Large pre-trained language models (PLMs) such as GPT-3 have shown strong in-context learning capabilities, which are highly appealing for domains such as biomedicine that feature high and diverse demands of language technologies but also high data annotation costs. In this paper, we present the first systematic and comprehensive study to compare the few-shot performance of GPT-3 in-context learning with fine-tuning smaller (i.e., BERT-sized) PLMs on two representative biomedical information extraction (IE) tasks: named entity recognition and relation extraction. We follow the true few-shot setting to avoid overestimating models’ few-shot performance by model selection over a large validation set. We also optimize GPT-3’s performance with known techniques such as contextual calibration and dynamic in-context example retrieval. However, our results show that GPT-3 still significantly underperforms compared to simply fine-tuning a smaller PLM. In addition, GPT-3 in-context learning also yields smaller gains in accuracy when more training data becomes available. More in-depth analyses further reveal issues of in-context learning that may be detrimental to IE tasks in general. Given the high cost of experimenting with GPT-3, we hope our study provides helpful guidance for biomedical researchers and practitioners towards more practical solutions such as fine-tuning small PLMs before better in-context learning is available for biomedical IE.

Question answering on knowledge bases (KBQA) poses a unique challenge for semantic parsing research due to two intertwined challenges: large search space and ambiguities in schema linking. Conventional ranking-based KBQA models, which rely on a candidate enumeration step to reduce the search space, struggle with flexibility in predicting complicated queries and have impractical running time. In this paper, we present ArcaneQA, a novel generation-based model that addresses both the large search space and the schema linking challenges in a unified framework with two mutually boosting ingredients: dynamic program induction for tackling the large search space and dynamic contextualized encoding for schema linking. Experimental results on multiple popular KBQA datasets demonstrate the highly competitive performance of ArcaneQA in both effectiveness and efficiency.

This paper describes the winning system in the End-to-end Pipeline phase for the NLPContributionGraph task. The system is composed of three BERT-based models and the three models are used to extract sentences, entities and triples respectively. Experiments show that sampling and adversarial training can greatly boost the system. In End-to-end Pipeline phase, our system got an average F1 of 0.4703, significantly higher than the second-placed system which got an average F1 of 0.3828.

Knowledge bases (KBs) and text often contain complementary knowledge: KBs store structured knowledge that can support long range reasoning, while text stores more comprehensive and timely knowledge in an unstructured way. Separately embedding the individual knowledge sources into vector spaces has demonstrated tremendous successes in encoding the respective knowledge, but how to jointly embed and reason with both knowledge sources to fully leverage the complementary information is still largely an open problem. We conduct a large-scale, systematic investigation of aligning KB and text embeddings for joint reasoning. We set up a novel evaluation framework with two evaluation tasks, few-shot link prediction and analogical reasoning, and evaluate an array of KB-text embedding alignment methods. We also demonstrate how such alignment can infuse textual information into KB embeddings for more accurate link prediction on emerging entities and events, using COVID-19 as a case study.

We describe a span-level supervised attention loss that improves compositional generalization in semantic parsers. Our approach builds on existing losses that encourage attention maps in neural sequence-to-sequence models to imitate the output of classical word alignment algorithms. Where past work has used word-level alignments, we focus on spans; borrowing ideas from phrase-based machine translation, we align subtrees in semantic parses to spans of input sentences, and encourage neural attention mechanisms to mimic these alignments. This method improves the performance of transformers, RNNs, and structured decoders on three benchmarks of compositional generalization.

Pre-trained language models (PLMs) like BERT are being used for almost all language-related tasks, but interpreting their behavior still remains a significant challenge and many important questions remain largely unanswered. In this work, we re-purpose a sentence editing dataset, where faithful high-quality human rationales can be automatically extracted and compared with extracted model rationales, as a new testbed for interpretability. This enables us to conduct a systematic investigation on an array of questions regarding PLMs’ interpretability, including the role of pre-training procedure, comparison of rationale extraction methods, and different layers in the PLM. The investigation generates new insights, for example, contrary to the common understanding, we find that attention weights correlate well with human rationales and work better than gradient-based saliency in extracting model rationales. Both the dataset and code will be released to facilitate future interpretability research.

We present ReasonBert, a pre-training method that augments language models with the ability to reason over long-range relations and multiple, possibly hybrid contexts. Unlike existing pre-training methods that only harvest learning signals from local contexts of naturally occurring texts, we propose a generalized notion of distant supervision to automatically connect multiple pieces of text and tables to create pre-training examples that require long-range reasoning. Different types of reasoning are simulated, including intersecting multiple pieces of evidence, bridging from one piece of evidence to another, and detecting unanswerable cases. We conduct a comprehensive evaluation on a variety of extractive question answering datasets ranging from single-hop to multi-hop and from text-only to table-only to hybrid that require various reasoning capabilities and show that ReasonBert achieves remarkable improvement over an array of strong baselines. Few-shot experiments further demonstrate that our pre-training method substantially improves sample efficiency.

Neural natural language generation (NLG) models have recently shown remarkable progress in fluency and coherence. However, existing studies on neural NLG are primarily focused on surface-level realizations with limited emphasis on logical inference, an important aspect of human thinking and language. In this paper, we suggest a new NLG task where a model is tasked with generating natural language statements that can be logically entailed by the facts in an open-domain semi-structured table. To facilitate the study of the proposed logical NLG problem, we use the existing TabFact dataset~(CITATION) featured with a wide range of logical/symbolic inferences as our testbed, and propose new automatic metrics to evaluate the fidelity of generation models w.r.t. logical inference. The new task poses challenges to the existing monotonic generation frameworks due to the mismatch between sequence order and logical order. In our experiments, we comprehensively survey different generation architectures (LSTM, Transformer, Pre-Trained LM) trained with different algorithms (RL, Adversarial Training, Coarse-to-Fine) on the dataset and made following observations: 1) Pre-Trained LM can significantly boost both the fluency and logical fidelity metrics, 2) RL and Adversarial Training are trading fluency for fidelity, 3) Coarse-to-Fine generation can help partially alleviate the fidelity issue while maintaining high language fluency. The code and data are available at https://github.com/wenhuchen/LogicNLG.

The global pandemic has made it more important than ever to quickly and accurately retrieve relevant scientific literature for effective consumption by researchers in a wide range of fields. We provide an analysis of several multi-label document classification models on the LitCovid dataset. We find that pre-trained language models outperform other models in both low and high data regimes, achieving a maximum F1 score of around 86%. We note that even the highest performing models still struggle with label correlation, distraction from introductory text and CORD-19 generalization. Both data and code are available on GitHub.

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.

The global pandemic has made it more important than ever to quickly and accurately retrieve relevant scientific literature for effective consumption by researchers in a wide range of fields. We provide an analysis of several multi-label document classification models on the LitCovid dataset, a growing collection of 23,000 research papers regarding the novel 2019 coronavirus. We find that pre-trained language models fine-tuned on this dataset outperform all other baselines and that BioBERT surpasses the others by a small margin with micro-F1 and accuracy scores of around 86% and 75% respectively on the test set. We evaluate the data efficiency and generalizability of these models as essential features of any system prepared to deal with an urgent situation like the current health crisis. We perform a data ablation study to determine how important article titles are for achieving reasonable performance on this dataset. Finally, we explore 50 errors made by the best performing models on LitCovid documents and find that they often (1) correlate certain labels too closely together and (2) fail to focus on discriminative sections of the articles; both of which are important issues to address in future work. Both data and code are available on GitHub.

Despite the widely successful applications, bootstrapping and fine-tuning semantic parsers are still a tedious process with challenges such as costly data annotation and privacy risks. In this paper, we suggest an alternative, human-in-the-loop methodology for learning semantic parsers directly from users. A semantic parser should be introspective of its uncertainties and prompt for user demonstrations when uncertain. In doing so it also gets to imitate the user behavior and continue improving itself autonomously with the hope that eventually it may become as good as the user in interpreting their questions. To combat the sparsity of demonstrations, we propose a novel annotation-efficient imitation learning algorithm, which iteratively collects new datasets by mixing demonstrated states and confident predictions and retrains the semantic parser in a Dataset Aggregation fashion (Ross et al., 2011). We provide a theoretical analysis of its cost bound and also empirically demonstrate its promising performance on the text-to-SQL problem. Code will be available at https://github.com/sunlab-osu/MISP.

Data-to-text generation has recently attracted substantial interests due to its wide applications. Existing methods have shown impressive performance on an array of tasks. However, they rely on a significant amount of labeled data for each task, which is costly to acquire and thus limits their application to new tasks and domains. In this paper, we propose to leverage pre-training and transfer learning to address this issue. We propose a knowledge-grounded pre-training (KGPT), which consists of two parts, 1) a general knowledge-grounded generation model to generate knowledge-enriched text. 2) a pre-training paradigm on a massive knowledge-grounded text corpus crawled from the web. The pre-trained model can be fine-tuned on various data-to-text generation tasks to generate task-specific text. We adopt three settings, namely fully-supervised, zero-shot, few-shot to evaluate its effectiveness. Under the fully-supervised setting, our model can achieve remarkable gains over the known baselines. Under zero-shot setting, our model without seeing any examples achieves over 30 ROUGE-L on WebNLG while all other baselines fail. Under the few-shot setting, our model only needs about one-fifteenth as many labeled examples to achieve the same level of performance as baseline models. These experiments consistently prove the strong generalization ability of our proposed framework.

Pre-trained embeddings such as word embeddings and sentence embeddings are fundamental tools facilitating a wide range of downstream NLP tasks. In this work, we investigate how to learn a general-purpose embedding of textual relations, defined as the shortest dependency path between entities. Textual relation embedding provides a level of knowledge between word/phrase level and sentence level, and we show that it can facilitate downstream tasks requiring relational understanding of the text. To learn such an embedding, we create the largest distant supervision dataset by linking the entire English ClueWeb09 corpus to Freebase. We use global co-occurrence statistics between textual and knowledge base relations as the supervision signal to train the embedding. Evaluation on two relational understanding tasks demonstrates the usefulness of the learned textual relation embedding. The data and code can be found at https://github.com/czyssrs/GloREPlus

With the rapid development in deep learning, deep neural networks have been widely adopted in many real-life natural language applications. Under deep neural networks, a pre-defined vocabulary is required to vectorize text inputs. The canonical approach to select pre-defined vocabulary is based on the word frequency, where a threshold is selected to cut off the long tail distribution. However, we observed that such a simple approach could easily lead to under-sized vocabulary or over-sized vocabulary issues. Therefore, we are interested in understanding how the end-task classification accuracy is related to the vocabulary size and what is the minimum required vocabulary size to achieve a specific performance. In this paper, we provide a more sophisticated variational vocabulary dropout (VVD) based on variational dropout to perform vocabulary selection, which can intelligently select the subset of the vocabulary to achieve the required performance. To evaluate different algorithms on the newly proposed vocabulary selection problem, we propose two new metrics: Area Under Accuracy-Vocab Curve and Vocab Size under X% Accuracy Drop. Through extensive experiments on various NLP classification tasks, our variational framework is shown to significantly outperform the frequency-based and other selection baselines on these metrics.

As a promising paradigm, interactive semantic parsing has shown to improve both semantic parsing accuracy and user confidence in the results. In this paper, we propose a new, unified formulation of the interactive semantic parsing problem, where the goal is to design a model-based intelligent agent. The agent maintains its own state as the current predicted semantic parse, decides whether and where human intervention is needed, and generates a clarification question in natural language. A key part of the agent is a world model: it takes a percept (either an initial question or subsequent feedback from the user) and transitions to a new state. We then propose a simple yet remarkably effective instantiation of our framework, demonstrated on two text-to-SQL datasets (WikiSQL and Spider) with different state-of-the-art base semantic parsers. Compared to an existing interactive semantic parsing approach that treats the base parser as a black box, our approach solicits less user feedback but yields higher run-time accuracy.

We study the problem of textual relation embedding with distant supervision. To combat the wrong labeling problem of distant supervision, we propose to embed textual relations with global statistics of relations, i.e., the co-occurrence statistics of textual and knowledge base relations collected from the entire corpus. This approach turns out to be more robust to the training noise introduced by distant supervision. On a popular relation extraction dataset, we show that the learned textual relation embedding can be used to augment existing relation extraction models and significantly improve their performance. Most remarkably, for the top 1,000 relational facts discovered by the best existing model, the precision can be improved from 83.9% to 89.3%.

The recent advance in deep learning and semantic parsing has significantly improved the translation accuracy of natural language questions to structured queries. However, further improvement of the existing approaches turns out to be quite challenging. Rather than solely relying on algorithmic innovations, in this work, we introduce DialSQL, a dialogue-based structured query generation framework that leverages human intelligence to boost the performance of existing algorithms via user interaction. DialSQL is capable of identifying potential errors in a generated SQL query and asking users for validation via simple multi-choice questions. User feedback is then leveraged to revise the query. We design a generic simulator to bootstrap synthetic training dialogues and evaluate the performance of DialSQL on the WikiSQL dataset. Using SQLNet as a black box query generation tool, DialSQL improves its performance from 61.3% to 69.0% using only 2.4 validation questions per dialogue.

Task-oriented dialog systems are becoming pervasive, and many companies heavily rely on them to complement human agents for customer service in call centers. With globalization, the need for providing cross-lingual customer support becomes more urgent than ever. However, cross-lingual support poses great challenges—it requires a large amount of additional annotated data from native speakers. In order to bypass the expensive human annotation and achieve the first step towards the ultimate goal of building a universal dialog system, we set out to build a cross-lingual state tracking framework. Specifically, we assume that there exists a source language with dialog belief tracking annotations while the target languages have no annotated dialog data of any form. Then, we pre-train a state tracker for the source language as a teacher, which is able to exploit easy-to-access parallel data. We then distill and transfer its own knowledge to the student state tracker in target languages. We specifically discuss two types of common parallel resources: bilingual corpus and bilingual dictionary, and design different transfer learning strategies accordingly. Experimentally, we successfully use English state tracker as the teacher to transfer its knowledge to both Italian and German trackers and achieve promising results.

WikiSQL is a newly released dataset for studying the natural language sequence to SQL translation problem. The SQL queries in WikiSQL are simple: Each involves one relation and does not have any join operation. Despite of its simplicity, none of the publicly reported structured query generation models can achieve an accuracy beyond 62%, which is still far from enough for practical use. In this paper, we ask two questions, “Why is the accuracy still low for such simple queries?” and “What does it take to achieve 100% accuracy on WikiSQL?” To limit the scope of our study, we focus on the WHERE clause in SQL. The answers will help us gain insights about the directions we should explore in order to further improve the translation accuracy. We will then investigate alternative solutions to realize the potential ceiling performance on WikiSQL. Our proposed solution can reach up to 88.6% condition accuracy on the WikiSQL dataset.

The existing factoid QA systems often lack a post-inspection component that can help models recover from their own mistakes. In this work, we propose to crosscheck the corresponding KB relations behind the predicted answers and identify potential inconsistencies. Instead of developing a new model that accepts evidences collected from these relations, we choose to plug them back to the original questions directly and check if the revised question makes sense or not. A bidirectional LSTM is applied to encode revised questions. We develop a scoring mechanism over the revised question encodings to refine the predictions of a base QA system. This approach can improve the F1 score of STAGG (Yih et al., 2015), one of the leading QA systems, from 52.5% to 53.9% on WEBQUESTIONS data.

Existing studies on semantic parsing mainly focus on the in-domain setting. We formulate cross-domain semantic parsing as a domain adaptation problem: train a semantic parser on some source domains and then adapt it to the target domain. Due to the diversity of logical forms in different domains, this problem presents unique and intriguing challenges. By converting logical forms into canonical utterances in natural language, we reduce semantic parsing to paraphrasing, and develop an attentive sequence-to-sequence paraphrase model that is general and flexible to adapt to different domains. We discover two problems, small micro variance and large macro variance, of pre-trained word embeddings that hinder their direct use in neural networks, and propose standardization techniques as a remedy. On the popular Overnight dataset, which contains eight domains, we show that both cross-domain training and standardized pre-trained word embeddings can bring significant improvement.

Given a question and a set of answer candidates, answer triggering determines whether the candidate set contains any correct answers. If yes, it then outputs a correct one. In contrast to existing pipeline methods which first consider individual candidate answers separately and then make a prediction based on a threshold, we propose an end-to-end deep neural network framework, which is trained by a novel group-level objective function that directly optimizes the answer triggering performance. Our objective function penalizes three potential types of error and allows training the framework in an end-to-end manner. Experimental results on the WikiQA benchmark show that our framework outperforms the state of the arts by a 6.6% absolute gain under F1 measure.