Recognition of biomedical entities from literature is a challenging research focus, which is the foundation for extracting a large amount of biomedical knowledge existing in unstructured texts into structured formats. Using the sequence labeling framework to implement biomedical named entity recognition (BioNER) is currently a conventional method. This method, however, often cannot take full advantage of the semantic information in the dataset, and the performance is not always satisfactory. In this work, instead of treating the BioNER task as a sequence labeling problem, we formulate it as a machine reading comprehension (MRC) problem. This formulation can introduce more prior knowledge utilizing well-designed queries, and no longer need decoding processes such as conditional random fields (CRF). We conduct experiments on six BioNER datasets, and the experimental results demonstrate the effectiveness of our method. Our method achieves state-of-the-art (SOTA) performance on the BC4CHEMD, BC5CDR-Chem, BC5CDR-Disease, NCBI-Disease, BC2GM and JNLPBA datasets, achieving F1-scores of 92.92%, 94.19%, 87.83%, 90.04%, 85.48% and 78.93%, respectively.
Open-domain question answering (QA) is the tasl of identifying answers to natural questions from a large corpus of documents. The typical open-domain QA system starts with information retrieval to select a subset of documents from the corpus, which are then processed by a machine reader to select the answer spans. This paper describes Mindstone, an open-domain QA system that consists of a new multi-stage pipeline that employs a traditional BM25-based information retriever, RM3-based neural relevance feedback, neural ranker, and a machine reading comprehension stage. This paper establishes a new baseline for end-to-end performance on question answering for Wikipedia/SQuAD dataset (EM=58.1, F1=65.8), with substantial gains over the previous state of the art (Yang et al., 2019b). We also show how the new pipeline enables the use of low-resolution labels, and can be easily tuned to meet various timing requirements.
We convert the Chinese medical text attributes extraction task into a sequence tagging or machine reading comprehension task. Based on BERT pre-trained models, we have not only tried the widely used LSTM-CRF sequence tagging model, but also other sequence models, such as CNN, UCNN, WaveNet, SelfAttention, etc, which reaches similar performance as LSTM+CRF. This sheds a light on the traditional sequence tagging models. Since the aspect of emphasis for different sequence tagging models varies substantially, ensembling these models adds diversity to the final system. By doing so, our system achieves good performance on the task of Chinese medical text attributes extraction (subtask 2 of CCKS 2019 task 1).
Machine Reading Comprehension (MRC) aims to extract answers to questions given a passage. It has been widely studied recently, especially in open domains. However, few efforts have been made on closed-domain MRC, mainly due to the lack of large-scale training data. In this paper, we introduce a multi-target MRC task for the medical domain, whose goal is to predict answers to medical questions and the corresponding support sentences from medical information sources simultaneously, in order to ensure the high reliability of medical knowledge serving. A high-quality dataset is manually constructed for the purpose, named Multi-task Chinese Medical MRC dataset (CMedMRC), with detailed analysis conducted. We further propose the Chinese medical BERT model for the task (CMedBERT), which fuses medical knowledge into pre-trained language models by the dynamic fusion mechanism of heterogeneous features and the multi-task learning strategy. Experiments show that CMedBERT consistently outperforms strong baselines by fusing context-aware and knowledge-aware token representations.
Machine reading comprehension (MRC) has become a core component in a variety of natural language processing (NLP) applications such as question answering and dialogue systems. It becomes a practical challenge that an MRC model needs to learn in non-stationary environments, in which the underlying data distribution changes over time. A typical scenario is the domain drift, i.e. different domains of data come one after another, where the MRC model is required to adapt to the new domain while maintaining previously learned ability. To tackle such a challenge, in this work, we introduce the \textit{Continual Domain Adaptation} (CDA) task for MRC. So far as we know, this is the first study on the continual learning perspective of MRC. We build two benchmark datasets for the CDA task, by re-organizing existing MRC collections into different domains with respect to context type and question type, respectively. We then analyze and observe the catastrophic forgetting (CF) phenomenon of MRC under the CDA setting. To tackle the CDA task, we propose several BERT-based continual learning MRC models using either regularization-based methodology or dynamic-architecture paradigm. We analyze the performance of different continual learning MRC models under the CDA task and show that the proposed dynamic-architecture based model achieves the best performance.
Machine reading comprehension (MRC) is a challenging task in natural language processing that makes computers understanding natural language texts and answer questions based on those texts. There are many techniques for solving this problems, and word representation is a very important technique that impact most to the accuracy of machine reading comprehension problem in the popular languages like English and Chinese. However, few studies on MRC have been conducted in low-resource languages such as Vietnamese. In this paper, we conduct several experiments on neural network-based model to understand the impact of word representation to the Vietnamese multiple-choice machine reading comprehension. Our experiments include using the Co-match model on six different Vietnamese word embeddings and the BERT model for multiple-choice reading comprehension. On the ViMMRC corpus, the accuracy of BERT model is 61.28% on test set.
Responding to user reviews promptly and satisfactorily improves application ratings, which is key to application popularity and success. The proliferation of such reviews makes it virtually impossible for developers to keep up with responding manually. To address this challenge, recent work has shown the possibility of automatic response generation. However, because the training review-response pairs are aggregated from many different apps, it remains challenging for such models to generate app-specific responses, which, on the other hand, are often desirable as apps have different features and concerns. Solving the challenge by simply building a model per app (i.e., training with review-response pairs of a single app) may be insufficient because individual apps have limited review-response pairs, and such pairs typically lack the relevant information needed to respond to a new review. To enable app-specific response generation, this work proposes AARSynth: an app-aware response synthesis system. The key idea behind AARSynth is to augment the seq2seq model with information specific to a given app. Given a new user review, it first retrieves the top-K most relevant app reviews and the most relevant snippet from the app description. The retrieved information and the new user review are then fed into a fused machine learning model that integrates the seq2seq model with a machine reading comprehension model. The latter helps digest the retrieved reviews and app description. Finally, the fused model generates a response that is customized to the given app. We evaluated AARSynth using a large corpus of reviews and responses from Google Play. The results show that AARSynth outperforms the state-of-the-art system by 22.2% on BLEU-4 score. Furthermore, our human study shows that AARSynth produces a statistically significant improvement in response quality compared to the state-of-the-art system.
Machine reading is a fundamental task for testing the capability of natural language understanding, which is closely related to human cognition in many aspects. With the rising of deep learning techniques, algorithmic models rival human performances on simple QA, and thus increasingly challenging machine reading datasets have been proposed. Though various challenges such as evidence integration and commonsense knowledge have been integrated, one of the fundamental capabilities in human reading, namely logical reasoning, is not fully investigated. We build a comprehensive dataset, named LogiQA, which is sourced from expert-written questions for testing human Logical reasoning. It consists of 8,678 QA instances, covering multiple types of deductive reasoning. Results show that state-of-the-art neural models perform by far worse than human ceiling. Our dataset can also serve as a benchmark for reinvestigating logical AI under the deep learning NLP setting. The dataset is freely available at https://github.com/lgw863/LogiQA-dataset
Machine Reading Comprehension (MRC) is a challenging Natural Language Processing(NLP) research field with wide real-world applications. The great progress of this field in recent years is mainly due to the emergence of large-scale datasets and deep learning. At present, a lot of MRC models have already surpassed human performance on various benchmark datasets despite the obvious giant gap between existing MRC models and genuine human-level reading comprehension. This shows the need for improving existing datasets, evaluation metrics, and models to move current MRC models toward "real" understanding. To address the current lack of comprehensive survey of existing MRC tasks, evaluation metrics, and datasets, herein, (1) we analyze 57 MRC tasks and datasets and propose a more precise classification method of MRC tasks with 4 different attributes; (2) we summarized 9 evaluation metrics of MRC tasks, 7 attributes and 10 characteristics of MRC datasets; (3) We also discuss key open issues in MRC research and highlighted future research directions. In addition, we have collected, organized, and published our data on the companion website(https://mrc-datasets.github.io/) where MRC researchers could directly access each MRC dataset, papers, baseline projects, and the leaderboard.
This paper presents the ReCO, a human-curated ChineseReading Comprehension dataset on Opinion. The questions in ReCO are opinion based queries issued to the commercial search engine. The passages are provided by the crowdworkers who extract the support snippet from the retrieved documents. Finally, an abstractive yes/no/uncertain answer was given by the crowdworkers. The release of ReCO consists of 300k questions that to our knowledge is the largest in Chinese reading comprehension. A prominent characteristic of ReCO is that in addition to the original context paragraph, we also provided the support evidence that could be directly used to answer the question. Quality analysis demonstrates the challenge of ReCO that requires various types of reasoning skills, such as causal inference, logical reasoning, etc. Current QA models that perform very well on many question answering problems, such as BERT, only achieve 77% accuracy on this dataset, a large margin behind humans nearly 92% performance, indicating ReCO presents a good challenge for machine reading comprehension. The codes, datasets are freely available at https://github.com/benywon/ReCO.
Large-scale and high-quality corpora are necessary for evaluating machine reading comprehension models on a low-resource language like Vietnamese. Besides, machine reading comprehension (MRC) for the health domain offers great potential for practical applications; however, there is still very little MRC research in this domain. This paper presents ViNewsQA as a new corpus for the Vietnamese language to evaluate healthcare reading comprehension models. The corpus comprises 22,057 human-generated question-answer pairs. Crowd-workers create the questions and their answers based on a collection of over 4,416 online Vietnamese healthcare news articles, where the answers comprise spans extracted from the corresponding articles. In particular, we develop a process of creating a corpus for the Vietnamese machine reading comprehension. Comprehensive evaluations demonstrate that our corpus requires abilities beyond simple reasoning, such as word matching and demanding difficult reasoning based on single-or-multiple-sentence information. We conduct experiments using different types of machine reading comprehension methods to achieve the first baseline performances, compared with further models' performances. We also measure human performance on the corpus and compared it with several powerful neural network-based and transfer learning-based models. Our experiments show that the best machine model is ALBERT, which achieves an exact match score of 65.26% and an F1-score of 84.89% on our corpus. The significant differences between humans and the best-performance model (14.53% of EM and 10.90% of F1-score) on the test set of our corpus indicate that improvements in ViNewsQA could be explored in the future study. Our corpus is publicly available on our website for the research purpose to encourage the research community to make these improvements.
In this paper, we investigate the Dual-source Transformer architecture on the WikiReading information extraction and machine reading comprehension dataset. The proposed model outperforms the current state-of-the-art by a large margin. Next, we introduce WikiReading Recycled - a newly developed public dataset, supporting the task of multiple property extraction. It keeps the spirit of the original WikiReading but does not inherit the identified disadvantages of its predecessor.
Pre-trained models have brought significant improvements to many NLP tasks and have been extensively analyzed. But little is known about the effect of fine-tuning on specific tasks. Intuitively, people may agree that a pre-trained model already learns semantic representations of words (e.g. synonyms are closer to each other) and fine-tuning further improves its capabilities which require more complicated reasoning (e.g. coreference resolution, entity boundary detection, etc). However, how to verify these arguments analytically and quantitatively is a challenging task and there are few works focus on this topic. In this paper, inspired by the observation that most probing tasks involve identifying matched pairs of phrases (e.g. coreference requires matching an entity and a pronoun), we propose a pairwise probe to understand BERT fine-tuning on the machine reading comprehension (MRC) task. Specifically, we identify five phenomena in MRC. According to pairwise probing tasks, we compare the performance of each layer's hidden representation of pre-trained and fine-tuned BERT. The proposed pairwise probe alleviates the problem of distraction from inaccurate model training and makes a robust and quantitative comparison. Our experimental analysis leads to highly confident conclusions: (1) Fine-tuning has little effect on the fundamental and low-level information and general semantic tasks. (2) For specific abilities required for downstream tasks, fine-tuned BERT is better than pre-trained BERT and such gaps are obvious after the fifth layer.
Conversational Machine Comprehension (CMC), a research track in conversational AI, expects the machine to understand an open-domain natural language text and thereafter engage in a multi-turn conversation to answer questions related to the text. While most of the research in Machine Reading Comprehension (MRC) revolves around single-turn question answering (QA), multi-turn CMC has recently gained prominence, thanks to the advancement in natural language understanding via neural language models such as BERT and the introduction of large-scale conversational datasets such as CoQA and QuAC. The rise in interest has, however, led to a flurry of concurrent publications, each with a different yet structurally similar modeling approach and an inconsistent view of the surrounding literature. With the volume of model submissions to conversational datasets increasing every year, there exists a need to consolidate the scattered knowledge in this domain to streamline future research. This literature review attempts at providing a holistic overview of CMC with an emphasis on the common trends across recently published models, specifically in their approach to tackling conversational history. The review synthesizes a generic framework for CMC models while highlighting the differences in recent approaches and intends to serve as a compendium of CMC for future researchers.
In this paper, we study machine reading comprehension (MRC) on long texts, where a model takes as inputs a lengthy document and a question and then extracts a text span from the document as an answer. State-of-the-art models tend to use a pretrained transformer model (e.g., BERT) to encode the joint contextual information of document and question. However, these transformer-based models can only take a fixed-length (e.g., 512) text as its input. To deal with even longer text inputs, previous approaches usually chunk them into equally-spaced segments and predict answers based on each segment independently without considering the information from other segments. As a result, they may form segments that fail to cover the correct answer span or retain insufficient contexts around it, which significantly degrades the performance. Moreover, they are less capable of answering questions that need cross-segment information. We propose to let a model learn to chunk in a more flexible way via reinforcement learning: a model can decide the next segment that it wants to process in either direction. We also employ recurrent mechanisms to enable information to flow across segments. Experiments on three MRC datasets -- CoQA, QuAC, and TriviaQA -- demonstrate the effectiveness of our proposed recurrent chunking mechanisms: we can obtain segments that are more likely to contain complete answers and at the same time provide sufficient contexts around the ground truth answers for better predictions.
Machine reading comprehension (MRC) aims to teach machines to read and comprehend human languages, which is a long-standing goal of natural language processing (NLP). With the burst of deep neural networks and the evolution of contextualized language models (CLMs), the research of MRC has experienced two significant breakthroughs. MRC and CLM, as a phenomenon, have a great impact on the NLP community. In this survey, we provide a comprehensive and comparative review on MRC covering overall research topics about 1) the origin and development of MRC and CLM, with a particular focus on the role of CLMs; 2) the impact of MRC and CLM to the NLP community; 3) the definition, datasets, and evaluation of MRC; 4) general MRC architecture and technical methods in the view of two-stage Encoder-Decoder solving architecture from the insights of the cognitive process of humans; 5) previous highlights, emerging topics, and our empirical analysis, among which we especially focus on what works in different periods of MRC researches. We propose a full-view categorization and new taxonomies on these topics. The primary views we have arrived at are that 1) MRC boosts the progress from language processing to understanding; 2) the rapid improvement of MRC systems greatly benefits from the development of CLMs; 3) the theme of MRC is gradually moving from shallow text matching to cognitive reasoning.
We introduce BIOMRC, a large-scale cloze-style biomedical MRC dataset. Care was taken to reduce noise, compared to the previous BIOREAD dataset of Pappas et al. (2018). Experiments show that simple heuristics do not perform well on the new dataset, and that two neural MRC models that had been tested on BIOREAD perform much better on BIOMRC, indicating that the new dataset is indeed less noisy or at least that its task is more feasible. Non-expert human performance is also higher on the new dataset compared to BIOREAD, and biomedical experts perform even better. We also introduce a new BERT-based MRC model, the best version of which substantially outperforms all other methods tested, reaching or surpassing the accuracy of biomedical experts in some experiments. We make the new dataset available in three different sizes, also releasing our code, and providing a leaderboard.
Natural Questions is a new challenging machine reading comprehension benchmark with two-grained answers, which are a long answer (typically a paragraph) and a short answer (one or more entities inside the long answer). Despite the effectiveness of existing methods on this benchmark, they treat these two sub-tasks individually during training while ignoring their dependencies. To address this issue, we present a novel multi-grained machine reading comprehension framework that focuses on modeling documents at their hierarchical nature, which are different levels of granularity: documents, paragraphs, sentences, and tokens. We utilize graph attention networks to obtain different levels of representations so that they can be learned simultaneously. The long and short answers can be extracted from paragraph-level representation and token-level representation, respectively. In this way, we can model the dependencies between the two-grained answers to provide evidence for each other. We jointly train the two sub-tasks, and our experiments show that our approach significantly outperforms previous systems at both long and short answer criteria.
Neural models have achieved great success on machine reading comprehension (MRC), many of which typically consist of two components: an evidence extractor and an answer predictor. The former seeks the most relevant information from a reference text, while the latter is to locate or generate answers from the extracted evidence. Despite the importance of evidence labels for training the evidence extractor, they are not cheaply accessible, particularly in many non-extractive MRC tasks such as YES/NO question answering and multi-choice MRC. To address this problem, we present a Self-Training method (STM), which supervises the evidence extractor with auto-generated evidence labels in an iterative process. At each iteration, a base MRC model is trained with golden answers and noisy evidence labels. The trained model will predict pseudo evidence labels as extra supervision in the next iteration. We evaluate STM on seven datasets over three MRC tasks. Experimental results demonstrate the improvement on existing MRC models, and we also analyze how and why such a self-training method works in MRC. The source code can be obtained from https://github.com/SparkJiao/Self-Training-MRC
Machine reading comprehension has made great progress in recent years owing to large-scale annotated datasets. In the clinical domain, however, creating such datasets is quite difficult due to the domain expertise required for annotation. Recently, Pampari et al. (EMNLP'18) tackled this issue by using expert-annotated question templates and existing i2b2 annotations to create emrQA, the first large-scale dataset for question answering (QA) based on clinical notes. In this paper, we provide an in-depth analysis of this dataset and the clinical reading comprehension (CliniRC) task. From our qualitative analysis, we find that (i) emrQA answers are often incomplete, and (ii) emrQA questions are often answerable without using domain knowledge. From our quantitative experiments, surprising results include that (iii) using a small sampled subset (5%-20%), we can obtain roughly equal performance compared to the model trained on the entire dataset, (iv) this performance is close to human expert's performance, and (v) BERT models do not beat the best performing base model. Following our analysis of the emrQA, we further explore two desired aspects of CliniRC systems: the ability to utilize clinical domain knowledge and to generalize to unseen questions and contexts. We argue that both should be considered when creating future datasets.