A crucial issue of current text generation models is that they often uncontrollably generate text that is factually inconsistent with inputs. Due to lack of annotated data, existing factual consistency metrics usually train evaluation models on synthetic texts or directly transfer from other related tasks, such as question answering (QA) and natural language inference (NLI).Bias in synthetic text or upstream tasks makes them perform poorly on text actually generated by language models, especially for general evaluation for various tasks. To alleviate this problem, we propose a weakly supervised framework named WeCheck that is directly trained on actual generated samples from language models with weakly annotated labels.WeCheck first utilizes a generative model to infer the factual labels of generated samples by aggregating weak labels from multiple resources.Next, we train a simple noise-aware classification model as the target metric using the inferred weakly supervised information.Comprehensive experiments on various tasks demonstrate the strong performance of WeCheck, achieving an average absolute improvement of 3.3% on the TRUE benchmark over 11B state-of-the-art methods using only 435M parameters.Furthermore, it is up to 30 times faster than previous evaluation methods, greatly improving the accuracy and efficiency of factual consistency evaluation.

Various datasets have been proposed to promote the development of Table Question Answering (TQA) technique. However, the problem setting of existing TQA benchmarks suffers from two limitations. First, they directly provide models with explicit table structures where row headers and column headers of the table are explicitly annotated and treated as model input during inference. Second, they only consider tables of limited types and ignore other tables especially complex tables with flexible header locations. Such simplified problem setting cannot cover practical scenarios where models need to process tables without header annotations in the inference phase or tables of different types. To address above issues, we construct a new TQA dataset with implicit and multi-type table structures, named IM-TQA, which not only requires the model to understand tables without directly available header annotations but also to handle multi-type tables including previously neglected complex tables. We investigate the performance of recent methods on our dataset and find that existing methods struggle in processing implicit and multi-type table structures. Correspondingly, we propose an RGCN-RCI framework outperforming recent baselines. We will release our dataset to facilitate future research.

Current relation extraction methods suffer from the inadequacy of large-scale annotated data. While distant supervision alleviates the problem of data quantities, there still exists domain disparity in data qualities due to its reliance on domain-restrained knowledge bases. In this work, we propose S2ynRE, a framework of two-stage Self-training with Synthetic data for Relation Extraction.We first leverage the capability of large language models to adapt to the target domain and automatically synthesize large quantities of coherent, realistic training data. We then propose an accompanied two-stage self-training algorithm that iteratively and alternately learns from synthetic and golden data together. We conduct comprehensive experiments and detailed ablations on popular relation extraction datasets to demonstrate the effectiveness of the proposed framework.

Tabular mathematical reasoning task requires models to perform multi-step operations including information look-up and numerical calculation, based on heterogeneous data from tables and questions. Existing solutions tend to extend chain-of-thought (CoT) reasoning into powerful large language models (LLMs) to promote multi-hop mathematical reasoning. However, such LLM-based approaches are not a viable solution in the scenario of privatization deployment or limited resources. To address this problem, we revisit small-scale tabular language models (TaLMs) and extend chain-of-thought reasoning into TaLMs for the first time. Specifically, we propose a novel framework, TaCo, which coordinates two TaLMs responsible for CoT generation and answer inference, respectively. Besides, our framework can be combined with an external calculator to enhance accurate numerical calculation. On the TABMWP dataset, TaCo outperforms the state-of-the-art ChatGPT by 9.55% (82.60%→92.15% in accuracy) with much less parameters (0.8B). The code will be released along with the paper.

Multi-triple extraction is a challenging task due to the existence of informative inter-triple correlations, and consequently rich interactions across the constituent entities and relations. While existing works only explore entity representations, we propose to explicitly introduce relation representation, jointly represent it with entities, and novelly align them to identify valid triples.We perform comprehensive experiments on document-level relation extraction and joint entity and relation extraction along with ablations to demonstrate the advantage of the proposed method.

Existing video question answering (video QA) models lack the capacity for deep video understanding and flexible multistep reasoning. We propose for video QA a novel model which performs dynamic multistep reasoning between questions and videos. It creates video semantic representation based on the video scene graph composed of semantic elements of the video and semantic relations among these elements. Then, it performs multistep reasoning for better answer decision between the representations of the question and the video, and dynamically integrate the reasoning results. Experiments show the significant advantage of the proposed model against previous methods in accuracy and interpretability. Against the existing state-of-the-art model, the proposed model dramatically improves more than 4%/3.1%/2% on the three widely used video QA datasets, MSRVTT-QA, MSRVTT multi-choice, and TGIF-QA, and displays better interpretability by backtracing along with the attention mechanisms to the video scene graphs.

A Temporal Knowledge Graph (TKG) is a sequence of KGs corresponding to different timestamps. TKG reasoning aims to predict potential facts in the future given the historical KG sequences. One key of this task is to mine and understand evolutional patterns of facts from these sequences. The evolutional patterns are complex in two aspects, length-diversity and time-variability. Existing models for TKG reasoning focus on modeling fact sequences of a fixed length, which cannot discover complex evolutional patterns that vary in length. Furthermore, these models are all trained offline, which cannot well adapt to the changes of evolutional patterns from then on. Thus, we propose a new model, called Complex Evolutional Network (CEN), which uses a length-aware Convolutional Neural Network (CNN) to handle evolutional patterns of different lengths via an easy-to-difficult curriculum learning strategy. Besides, we propose to learn the model under the online setting so that it can adapt to the changes of evolutional patterns over time. Extensive experiments demonstrate that CEN obtains substantial performance improvement under both the traditional offline and the proposed online settings.

Multi-hop Question Answering is an agent task for testing the reasoning ability. With the development of pre-trained models, the implicit reasoning ability has been surprisingly improved and can even surpass human performance. However, the nature of the black box hinders the construction of explainable intelligent systems. Several researchers have explored explainable neural-symbolic reasoning methods based on question decomposition techniques. The undifferentiable symbolic operations and the error propagation in the reasoning process lead to poor performance. To alleviate it, we propose a simple yet effective Global Differentiable Learning strategy to explore optimal reasoning paths from the latent probability space so that the model learns to solve intermediate reasoning processes without expert annotations. We further design a Dynamic Adaptive Reasoner to enhance the generalization of unseen questions. Our method achieves 17% improvements in F1-score against BreakRC and shows better interpretability. We take a step forward in building interpretable reasoning methods.

Though model robustness has been extensively studied in language understanding, the robustness of Seq2Seq generation remains understudied.In this paper, we conduct the first quantitative analysis on the robustness of pre-trained Seq2Seq models. We find that even current SOTA pre-trained Seq2Seq model (BART) is still vulnerable, which leads to significant degeneration in faithfulness and informativeness for text generation tasks.This motivated us to further propose a novel adversarial augmentation framework, namely AdvSeq, for generally improving faithfulness and informativeness of Seq2Seq models via enhancing their robustness. AdvSeq automatically constructs two types of adversarial augmentations during training, including implicit adversarial samples by perturbing word representations and explicit adversarial samples by word swapping, both of which effectively improve Seq2Seq robustness.Extensive experiments on three popular text generation tasks demonstrate that AdvSeq significantly improves both the faithfulness and informativeness of Seq2Seq generation under both automatic and human evaluation settings.

Traditional methods for named entity recognition (NER) classify mentions into a fixed set of pre-defined entity types. However, in many real-world scenarios, new entity types are incrementally involved. To investigate this problem, continual learning is introduced for NER. However, the existing method depends on the relevance between tasks and is prone to inter-type confusion. In this paper, we propose a novel two-stage framework Learn-and-Review (L&R) for continual NER under the type-incremental setting to alleviate the above issues. Specifically, for the learning stage, we distill the old knowledge from teacher to a student on the current dataset. For the reviewing stage, we first generate synthetic samples of old types to augment the dataset. Then, we further distill new knowledge from the above student and old knowledge from the teacher to get an enhanced student on the augmented dataset. This stage has the following advantages: (1) The synthetic samples mitigate the gap between the old and new task and thus enhance the further distillation; (2) Different types of entities are jointly seen during training which alleviates the inter-type confusion. Experimental results show that L&R outperforms the state-of-the-art method on CoNLL-03 and OntoNotes-5.0.

A Temporal Knowledge Graph (TKG) is a sequence of KGs with respective timestamps, which adopts quadruples in the form of (subject, relation, object, timestamp) to describe dynamic facts. TKG reasoning has facilitated many real-world applications via answering such queries as (query entity, query relation, ?, future timestamp) about future. This is actually a matching task between a query and candidate entities based on their historical structures, which reflect behavioral trends of the entities at different timestamps. In addition, recent KGs provide background knowledge of all the entities, which is also helpful for the matching. Thus, in this paper, we propose the Historical Structure Matching (HiSMatch) model. It applies two structure encoders to capture the semantic information contained in the historical structures of the query and candidate entities. Besides, it adopts another encoder to integrate the background knowledge into the model. TKG reasoning experiments on six benchmark datasets demonstrate the significant improvement of the proposed HiSMatch model, with up to 5.6% performance improvement in MRR, compared to the state-of-the-art baselines.

Recently, Biomedical Question Answering (BQA) has attracted growing attention due to its application value and technical challenges. Most existing works treat it as a semantic matching task that predicts answers by computing confidence among questions, options and evidence sentences, which is insufficient for scenarios that require complex reasoning based on a deep understanding of biomedical evidences. We propose a novel model termed Hierarchical Representation-based Dynamic Reasoning Network (HDRN) to tackle this problem. It first constructs the hierarchical representations for biomedical evidences to learn semantics within and among evidences. It then performs dynamic reasoning based on the hierarchical representations of evidences to solve complex biomedical problems. Against the existing state-of-the-art model, the proposed model significantly improves more than 4.5%, 3% and 1.3% on three mainstream BQA datasets, PubMedQA, MedQA-USMLE and NLPEC. The ablation study demonstrates the superiority of each improvement of our model. The code will be released after the paper is published.

Complex Question Understanding (CQU) parses complex questions to Question Decomposition Meaning Representation (QDMR) which is a sequence of atomic operators. Existing works are based on end-to-end neural models which do not explicitly model the intermediate states and lack interpretability for the parsing process. Besides, they predict QDMR in a mismatched granularity and do not model the step-wise information which is an essential characteristic of QDMR. To alleviate the issues, we treat QDMR as a computational graph and propose a transition-based method where a decider predicts a sequence of actions to build the graph node-by-node. In this way, the partial graph at each step enables better representation of the intermediate states and better interpretability. At each step, the decider encodes the intermediate state with specially designed encoders and predicts several candidates of the next action and its confidence. For inference, a searcher seeks the optimal graph based on the predictions of the decider to alleviate the error propagation. Experimental results demonstrate the parsing accuracy of our method against several strong baselines. Moreover, our method has transparent and human-readable intermediate results, showing improved interpretability.

This paper presents our winning system at the Radiology Report Summarization track of the MEDIQA 2021 shared task. Radiology report summarization automatically summarizes radiology findings into free-text impressions. This year’s task emphasizes the generalization and transfer ability of participating systems. Our system is built upon a pre-trained Transformer encoder-decoder architecture, i.e., PEGASUS, deployed with an additional domain adaptation module to particularly handle the transfer and generalization issue. Heuristics like ensemble and text normalization are also used. Our system is conceptually simple yet highly effective, achieving a ROUGE-2 score of 0.436 on test set and ranked the 1st place among all participating systems.

Most previous work on knowledge graph completion conducted single-view prediction or calculation for candidate triple evaluation, based only on the content information of the candidate triples. This paper describes a novel multi-view classification model for knowledge graph completion, where multiple classification views are performed based on both content and context information for candidate triple evaluation. Each classification view evaluates the validity of a candidate triple from a specific viewpoint, based on the content information inside the candidate triple and the context information nearby the triple. These classification views are implemented by a unified neural network and the classification predictions are weightedly integrated to obtain the final evaluation. Experiments show that, the multi-view model brings very significant improvements over previous methods, and achieves the new state-of-the-art on two representative datasets. We believe that, the flexibility and the scalability of the multi-view classification model facilitates the introduction of additional information and resources for better performance.

Named entity disambiguation is an important task that plays the role of bridge between text and knowledge. However, the performance of existing methods drops dramatically for short text, which is widely used in actual application scenarios, such as information retrieval and question answering. In this work, we propose a novel knowledge-enhanced method for named entity disambiguation. Considering the problem of information ambiguity and incompleteness for short text, two kinds of knowledge, factual knowledge graph and conceptual knowledge graph, are introduced to provide additional knowledge for the semantic matching between candidate entity and mention context. Our proposed method achieves significant improvement over previous methods on a large manually annotated short-text dataset, and also achieves the state-of-the-art on three standard datasets. The short-text dataset and the proposed model will be publicly available for research use.

Event extraction, which aims to identify event triggers of pre-defined event types and their arguments of specific roles, is a challenging task in NLP. Most traditional approaches formulate this task as classification problems, with event types or argument roles taken as golden labels. Such approaches fail to model rich interactions among event types and arguments of different roles, and cannot generalize to new types or roles. This work proposes a new paradigm that formulates event extraction as multi-turn question answering. Our approach, MQAEE, casts the extraction task into a series of reading comprehension problems, by which it extracts triggers and arguments successively from a given sentence. A history answer embedding strategy is further adopted to model question answering history in the multi-turn process. By this new formulation, MQAEE makes full use of dependency among arguments and event types, and generalizes well to new types with new argument roles. Empirical results on ACE 2005 shows that MQAEE outperforms current state-of-the-art, pushing the final F1 of argument extraction to 53.4% (+2.0%). And it also has a good generalization ability, achieving competitive performance on 13 new event types even if trained only with a few samples of them.

Machine reading comprehension (MRC) is a crucial and challenging task in NLP. Recently, pre-trained language models (LMs), especially BERT, have achieved remarkable success, presenting new state-of-the-art results in MRC. In this work, we investigate the potential of leveraging external knowledge bases (KBs) to further improve BERT for MRC. We introduce KT-NET, which employs an attention mechanism to adaptively select desired knowledge from KBs, and then fuses selected knowledge with BERT to enable context- and knowledge-aware predictions. We believe this would combine the merits of both deep LMs and curated KBs towards better MRC. Experimental results indicate that KT-NET offers significant and consistent improvements over BERT, outperforming competitive baselines on ReCoRD and SQuAD1.1 benchmarks. Notably, it ranks the 1st place on the ReCoRD leaderboard, and is also the best single model on the SQuAD1.1 leaderboard at the time of submission (March 4th, 2019).

Leveraging external knowledge is an emerging trend in machine comprehension task. Previous work usually utilizes knowledge graphs such as ConceptNet as external knowledge, and extracts triples from them to enhance the initial representation of the machine comprehension context. However, such method cannot capture the structural information in the knowledge graph. To this end, we propose a Structural Knowledge Graph-aware Network(SKG) model, constructing sub-graphs for entities in the machine comprehension context. Our method dynamically updates the representation of the knowledge according to the structural information of the constructed sub-graph. Experiments show that SKG achieves state-of-the-art performance on the ReCoRD dataset.

While sophisticated neural-based techniques have been developed in reading comprehension, most approaches model the answer in an independent manner, ignoring its relations with other answer candidates. This problem can be even worse in open-domain scenarios, where candidates from multiple passages should be combined to answer a single question. In this paper, we formulate reading comprehension as an extract-then-select two-stage procedure. We first extract answer candidates from passages, then select the final answer by combining information from all the candidates. Furthermore, we regard candidate extraction as a latent variable and train the two-stage process jointly with reinforcement learning. As a result, our approach has improved the state-of-the-art performance significantly on two challenging open-domain reading comprehension datasets. Further analysis demonstrates the effectiveness of our model components, especially the information fusion of all the candidates and the joint training of the extract-then-select procedure.

Machine reading comprehension (MRC) on real web data usually requires the machine to answer a question by analyzing multiple passages retrieved by search engine. Compared with MRC on a single passage, multi-passage MRC is more challenging, since we are likely to get multiple confusing answer candidates from different passages. To address this problem, we propose an end-to-end neural model that enables those answer candidates from different passages to verify each other based on their content representations. Specifically, we jointly train three modules that can predict the final answer based on three factors: the answer boundary, the answer content and the cross-passage answer verification. The experimental results show that our method outperforms the baseline by a large margin and achieves the state-of-the-art performance on the English MS-MARCO dataset and the Chinese DuReader dataset, both of which are designed for MRC in real-world settings.

This paper introduces DuReader, a new large-scale, open-domain Chinese machine reading comprehension (MRC) dataset, designed to address real-world MRC. DuReader has three advantages over previous MRC datasets: (1) data sources: questions and documents are based on Baidu Search and Baidu Zhidao; answers are manually generated. (2) question types: it provides rich annotations for more question types, especially yes-no and opinion questions, that leaves more opportunity for the research community. (3) scale: it contains 200K questions, 420K answers and 1M documents; it is the largest Chinese MRC dataset so far. Experiments show that human performance is well above current state-of-the-art baseline systems, leaving plenty of room for the community to make improvements. To help the community make these improvements, both DuReader and baseline systems have been posted online. We also organize a shared competition to encourage the exploration of more models. Since the release of the task, there are significant improvements over the baselines.

Current evaluation metrics to question answering based machine reading comprehension (MRC) systems generally focus on the lexical overlap between candidate and reference answers, such as ROUGE and BLEU. However, bias may appear when these metrics are used for specific question types, especially questions inquiring yes-no opinions and entity lists. In this paper, we make adaptations on the metrics to better correlate n-gram overlap with the human judgment for answers to these two question types. Statistical analysis proves the effectiveness of our approach. Our adaptations may provide positive guidance for the development of real-scene MRC systems.

Information selection is the most important component in document summarization task. In this paper, we propose to extend the basic neural encoding-decoding framework with an information selection layer to explicitly model and optimize the information selection process in abstractive document summarization. Specifically, our information selection layer consists of two parts: gated global information filtering and local sentence selection. Unnecessary information in the original document is first globally filtered, then salient sentences are selected locally while generating each summary sentence sequentially. To optimize the information selection process directly, distantly-supervised training guided by the golden summary is also imported. Experimental results demonstrate that the explicit modeling and optimizing of the information selection process improves document summarization performance significantly, which enables our model to generate more informative and concise summaries, and thus significantly outperform state-of-the-art neural abstractive methods.

In this paper, we focus on the problem of question generation (QG). Recent neural network-based approaches employ the sequence-to-sequence model which takes an answer and its context as input and generates a relevant question as output. However, we observe two major issues with these approaches: (1) The generated interrogative words (or question words) do not match the answer type. (2) The model copies the context words that are far from and irrelevant to the answer, instead of the words that are close and relevant to the answer. To address these two issues, we propose an answer-focused and position-aware neural question generation model. (1) By answer-focused, we mean that we explicitly model question word generation by incorporating the answer embedding, which can help generate an interrogative word matching the answer type. (2) By position-aware, we mean that we model the relative distance between the context words and the answer. Hence the model can be aware of the position of the context words when copying them to generate a question. We conduct extensive experiments to examine the effectiveness of our model. The experimental results show that our model significantly improves the baseline and outperforms the state-of-the-art system.

Recent neural sequence-to-sequence models have shown significant progress on short text summarization. However, for document summarization, they fail to capture the long-term structure of both documents and multi-sentence summaries, resulting in information loss and repetitions. In this paper, we propose to leverage the structural information of both documents and multi-sentence summaries to improve the document summarization performance. Specifically, we import both structural-compression and structural-coverage regularization into the summarization process in order to capture the information compression and information coverage properties, which are the two most important structural properties of document summarization. Experimental results demonstrate that the structural regularization improves the document summarization performance significantly, which enables our model to generate more informative and concise summaries, and thus significantly outperforms state-of-the-art neural abstractive methods.