Incorporating factual knowledge into pre-trained language models (PLM) such as BERT is an emerging trend in recent NLP studies. However, most of the existing methods combine the external knowledge integration module with a modified pre-training loss and re-implement the pre-training process on the large-scale corpus. Re-pretraining these models is usually resource-consuming, and difficult to adapt to another domain with a different knowledge graph (KG). Besides, those works either cannot embed knowledge context dynamically according to textual context or struggle with the knowledge ambiguity issue. In this paper, we propose a novel knowledge-aware language model framework based on fine-tuning process, which equips PLM with a unified knowledge-enhanced text graph that contains both text and multi-relational sub-graphs extracted from KG. We design a hierarchical relational-graph-based message passing mechanism, which can allow the representations of injected KG and text to mutually update each other and can dynamically select ambiguous mentioned entities that share the same text. Our empirical results show that our model can efficiently incorporate world knowledge from KGs into existing language models such as BERT, and achieve significant improvement on the machine reading comprehension (MRC) task compared with other knowledge-enhanced models.
Multi-party dialogue machine reading comprehension (MRC) brings tremendous challenge since it involves multiple speakers at one dialogue, resulting in intricate speaker information flows and noisy dialogue contexts. To alleviate such difficulties, previous models focus on how to incorporate these information using complex graph-based modules and additional manually labeled data, which is usually rare in real scenarios. In this paper, we design two labour-free self- and pseudo-self-supervised prediction tasks on speaker and key-utterance to implicitly model the speaker information flows, and capture salient clues in a long dialogue. Experimental results on two benchmark datasets have justified the effectiveness of our method over competitive baselines and current state-of-the-art models.
Interactive machine reading comprehension (iMRC) is machine comprehension tasks where knowledge sources are partially observable. An agent must interact with an environment sequentially to gather necessary knowledge in order to answer a question. We hypothesize that graph representations are good inductive biases, which can serve as an agent's memory mechanism in iMRC tasks. We explore four different categories of graphs that can capture text information at various levels. We describe methods that dynamically build and update these graphs during information gathering, as well as neural models to encode graph representations in RL agents. Extensive experiments on iSQuAD suggest that graph representations can result in significant performance improvements for RL agents.
Achieving human-level performance on some of the Machine Reading Comprehension (MRC) datasets is no longer challenging with the help of powerful Pre-trained Language Models (PLMs). However, the internal mechanism of these artifacts remains unclear, placing an obstacle for further understanding these models. This paper focuses on conducting a series of analytical experiments to examine the relations between the multi-head self-attention and the final MRC system performance, revealing the potential explainability in PLM-based MRC models. To ensure the robustness of the analyses, we perform our experiments in a multilingual way on top of various PLMs. We discover that passage-to-question and passage understanding attentions are the most important ones in the question answering process, showing strong correlations to the final performance than other parts. Through comprehensive visualizations and case studies, we also observe several general findings on the attention maps, which can be helpful to understand how these models solve the questions.
Reasoning machine reading comprehension (R-MRC) aims to answer complex questions that require discrete reasoning based on text. To support discrete reasoning, evidence, typically the concise textual fragments that describe question-related facts, including topic entities and attribute values, are crucial clues from question to answer. However, previous end-to-end methods that achieve state-of-the-art performance rarely solve the problem by paying enough emphasis on the modeling of evidence, missing the opportunity to further improve the model's reasoning ability for R-MRC. To alleviate the above issue, in this paper, we propose an evidence-emphasized discrete reasoning approach (EviDR), in which sentence and clause level evidence is first detected based on distant supervision, and then used to drive a reasoning module implemented with a relational heterogeneous graph convolutional network to derive answers. Extensive experiments are conducted on DROP (discrete reasoning over paragraphs) dataset, and the results demonstrate the effectiveness of our proposed approach. In addition, qualitative analysis verifies the capability of the proposed evidence-emphasized discrete reasoning for R-MRC.
Task requirements (TRs) writing is an important question type in Key English Test and Preliminary English Test. A TR writing question may include multiple requirements and a high-quality essay must respond to each requirement thoroughly and accurately. However, the limited teacher resources prevent students from getting detailed grading instantly. The majority of existing automatic essay scoring systems focus on giving a holistic score but rarely provide reasons to support it. In this paper, we proposed an end-to-end framework based on machine reading comprehension (MRC) to address this problem to some extent. The framework not only detects whether an essay responds to a requirement question, but clearly marks where the essay answers the question. Our framework consists of three modules: question normalization module, ELECTRA based MRC module and response locating module. We extensively explore state-of-the-art MRC methods. Our approach achieves 0.93 accuracy score and 0.85 F1 score on a real-world educational dataset. To encourage reproducible results, we make our code publicly available at \url{https://github.com/aied2021TRMRC/AIED_2021_TRMRC_code}.
Pretrained Language Models (PLMs) have achieved tremendous success in natural language understanding tasks. While different learning schemes -- fine-tuning, zero-shot, and few-shot learning -- have been widely explored and compared for languages such as English, there is comparatively little work in Chinese to fairly and comprehensively evaluate and compare these methods and thus hinders cumulative progress. In this paper, we introduce the Chinese Few-shot Learning Evaluation Benchmark (FewCLUE), the first comprehensive few-shot evaluation benchmark in Chinese. It includes nine tasks, ranging from single-sentence and sentence-pair classification tasks to machine reading comprehension tasks. We systematically evaluate five state-of-the-art (SOTA) few-shot learning methods (including PET, ADAPET, LM-BFF, P-tuning and EFL), and compare their performance with fine-tuning and zero-shot learning schemes on the newly constructed FewCLUE benchmark. Experimental results reveal that: 1) The effect of different few-shot learning methods is sensitive to the pre-trained model to which the methods are applied; 2) PET and P-tuning achieve the best overall performance with RoBERTa and ERNIE respectively. Our benchmark is used in the few-shot learning contest of NLPCC 2021. In addition, we provide a user-friendly toolkit, as well as an online leaderboard to help facilitate further progress on Chinese few-shot learning. We provide a baseline performance on different learning methods, a reference for future research.
Recent pretraining models in Chinese neglect two important aspects specific to the Chinese language: glyph and pinyin, which carry significant syntax and semantic information for language understanding. In this work, we propose ChineseBERT, which incorporates both the {\it glyph} and {\it pinyin} information of Chinese characters into language model pretraining. The glyph embedding is obtained based on different fonts of a Chinese character, being able to capture character semantics from the visual features, and the pinyin embedding characterizes the pronunciation of Chinese characters, which handles the highly prevalent heteronym phenomenon in Chinese (the same character has different pronunciations with different meanings). Pretrained on large-scale unlabeled Chinese corpus, the proposed ChineseBERT model yields significant performance boost over baseline models with fewer training steps. The porpsoed model achieves new SOTA performances on a wide range of Chinese NLP tasks, including machine reading comprehension, natural language inference, text classification, sentence pair matching, and competitive performances in named entity recognition. Code and pretrained models are publicly available at https://github.com/ShannonAI/ChineseBert.
We propose a simple and effective strategy for data augmentation for low-resource machine reading comprehension (MRC). Our approach first pretrains the answer extraction components of a MRC system on the augmented data that contains approximate context of the correct answers, before training it on the exact answer spans. The approximate context helps the QA method components in narrowing the location of the answers. We demonstrate that our simple strategy substantially improves both document retrieval and answer extraction performance by providing larger context of the answers and additional training data. In particular, our method significantly improves the performance of BERT based retriever (15.12\%), and answer extractor (4.33\% F1) on TechQA, a complex, low-resource MRC task. Further, our data augmentation strategy yields significant improvements of up to 3.9\% exact match (EM) and 2.7\% F1 for answer extraction on PolicyQA, another practical but moderate sized QA dataset that also contains long answer spans.
Recent studies report that many machine reading comprehension (MRC) models can perform closely to or even better than humans on benchmark datasets. However, existing works indicate that many MRC models may learn shortcuts to outwit these benchmarks, but the performance is unsatisfactory in real-world applications. In this work, we attempt to explore, instead of the expected comprehension skills, why these models learn the shortcuts. Based on the observation that a large portion of questions in current datasets have shortcut solutions, we argue that larger proportion of shortcut questions in training data make models rely on shortcut tricks excessively. To investigate this hypothesis, we carefully design two synthetic datasets with annotations that indicate whether a question can be answered using shortcut solutions. We further propose two new methods to quantitatively analyze the learning difficulty regarding shortcut and challenging questions, and revealing the inherent learning mechanism behind the different performance between the two kinds of questions. A thorough empirical analysis shows that MRC models tend to learn shortcut questions earlier than challenging questions, and the high proportions of shortcut questions in training sets hinder models from exploring the sophisticated reasoning skills in the later stage of training.
This paper introduces the SemEval-2021 shared task 4: Reading Comprehension of Abstract Meaning (ReCAM). This shared task is designed to help evaluate the ability of machines in representing and understanding abstract concepts. Given a passage and the corresponding question, a participating system is expected to choose the correct answer from five candidates of abstract concepts in a cloze-style machine reading comprehension setup. Based on two typical definitions of abstractness, i.e., the imperceptibility and nonspecificity, our task provides three subtasks to evaluate the participating models. Specifically, Subtask 1 aims to evaluate how well a system can model concepts that cannot be directly perceived in the physical world. Subtask 2 focuses on models' ability in comprehending nonspecific concepts located high in a hypernym hierarchy given the context of a passage. Subtask 3 aims to provide some insights into models' generalizability over the two types of abstractness. During the SemEval-2021 official evaluation period, we received 23 submissions to Subtask 1 and 28 to Subtask 2. The participating teams additionally made 29 submissions to Subtask 3. The leaderboard and competition website can be found at https://competitions.codalab.org/competitions/26153. The data and baseline code are available at https://github.com/boyuanzheng010/SemEval2021-Reading-Comprehension-of-Abstract-Meaning.
Recent years have witnessed an increasing interest in training machines with reasoning ability, which deeply relies on accurately and clearly presented clue forms. The clues are usually modeled as entity-aware knowledge in existing studies. However, those entity-aware clues are primarily focused on commonsense, making them insufficient for tasks that require knowledge of temporary facts or events, particularly in logical reasoning for reading comprehension. To address this challenge, we are motivated to cover both commonsense and temporary knowledge clues hierarchically. Specifically, we propose a general formalism of knowledge units by extracting backbone constituents of the sentence, such as the subject-verb-object formed ``facts''. We then construct a supergraph on top of the fact units, allowing for the benefit of sentence-level (relations among fact groups) and entity-level interactions (concepts or actions inside a fact). Experimental results on logical reasoning benchmarks and dialogue modeling datasets show that our approach improves the baselines substantially, and it is general across backbone models. Code is available at \url{https://github.com/ozyyshr/FocalReasoner}.
We introduce Korean Language Understanding Evaluation (KLUE) benchmark. KLUE is a collection of 8 Korean natural language understanding (NLU) tasks, including Topic Classification, SemanticTextual Similarity, Natural Language Inference, Named Entity Recognition, Relation Extraction, Dependency Parsing, Machine Reading Comprehension, and Dialogue State Tracking. We build all of the tasks from scratch from diverse source corpora while respecting copyrights, to ensure accessibility for anyone without any restrictions. With ethical considerations in mind, we carefully design annotation protocols. Along with the benchmark tasks and data, we provide suitable evaluation metrics and fine-tuning recipes for pretrained language models for each task. We furthermore release the pretrained language models (PLM), KLUE-BERT and KLUE-RoBERTa, to help reproducing baseline models on KLUE and thereby facilitate future research. We make a few interesting observations from the preliminary experiments using the proposed KLUE benchmark suite, already demonstrating the usefulness of this new benchmark suite. First, we find KLUE-RoBERTa-large outperforms other baselines, including multilingual PLMs and existing open-source Korean PLMs. Second, we see minimal degradation in performance even when we replace personally identifiable information from the pretraining corpus, suggesting that privacy and NLU capability are not at odds with each other. Lastly, we find that using BPE tokenization in combination with morpheme-level pre-tokenization is effective in tasks involving morpheme-level tagging, detection and generation. In addition to accelerating Korean NLP research, our comprehensive documentation on creating KLUE will facilitate creating similar resources for other languages in the future. KLUE is available at https://klue-benchmark.com.
Higher-order methods for dependency parsing can partially but not fully address the issue that edges in dependency trees should be constructed at the text span/subtree level rather than word level. In this paper, we propose a new method for dependency parsing to address this issue. The proposed method constructs dependency trees by directly modeling span-span (in other words, subtree-subtree) relations. It consists of two modules: the {\it text span proposal module} which proposes candidate text spans, each of which represents a subtree in the dependency tree denoted by (root, start, end); and the {\it span linking module}, which constructs links between proposed spans. We use the machine reading comprehension (MRC) framework as the backbone to formalize the span linking module, where one span is used as a query to extract the text span/subtree it should be linked to. The proposed method has the following merits: (1) it addresses the fundamental problem that edges in a dependency tree should be constructed between subtrees; (2) the MRC framework allows the method to retrieve missing spans in the span proposal stage, which leads to higher recall for eligible spans. Extensive experiments on the PTB, CTB and Universal Dependencies (UD) benchmarks demonstrate the effectiveness of the proposed method. The code is available at \url{https://github.com/ShannonAI/mrc-for-dependency-parsing}
Pre-trained Language Models (PLMs) have achieved great success on Machine Reading Comprehension (MRC) over the past few years. Although the general language representation learned from large-scale corpora does benefit MRC, the poor support in evidence extraction which requires reasoning across multiple sentences hinders PLMs from further advancing MRC. To bridge the gap between general PLMs and MRC, we present REPT, a REtrieval-based Pre-Training approach. In particular, we introduce two self-supervised tasks to strengthen evidence extraction during pre-training, which is further inherited by downstream MRC tasks through the consistent retrieval operation and model architecture. To evaluate our proposed method, we conduct extensive experiments on five MRC datasets that require collecting evidence from and reasoning across multiple sentences. Experimental results demonstrate the effectiveness of our pre-training approach. Moreover, further analysis shows that our approach is able to enhance the capacity of evidence extraction without explicit supervision.
Achieving human-level performance on some of Machine Reading Comprehension (MRC) datasets is no longer challenging with the help of powerful Pre-trained Language Models (PLMs). However, it is necessary to provide both answer prediction and its explanation to further improve the MRC system's reliability, especially for real-life applications. In this paper, we propose a new benchmark called ExpMRC for evaluating the explainability of the MRC systems. ExpMRC contains four subsets, including SQuAD, CMRC 2018, RACE$^+$, and C$^3$ with additional annotations of the answer's evidence. The MRC systems are required to give not only the correct answer but also its explanation. We use state-of-the-art pre-trained language models to build baseline systems and adopt various unsupervised approaches to extract evidence without a human-annotated training set. The experimental results show that these models are still far from human performance, suggesting that the ExpMRC is challenging. Resources will be available through https://github.com/ymcui/expmrc
Machine reading comprehension (MRC) is a sub-field in natural language processing that aims to assist computers understand unstructured texts and then answer questions related to them. In practice, the conversation is an essential way to communicate and transfer information. To help machines understand conversation texts, we present UIT-ViCoQA, a new corpus for conversational machine reading comprehension in the Vietnamese language. This corpus consists of 10,000 questions with answers over 2,000 conversations about health news articles. Then, we evaluate several baseline approaches for conversational machine comprehension on the UIT-ViCoQA corpus. The best model obtains an F1 score of 45.27%, which is 30.91 points behind human performance (76.18%), indicating that there is ample room for improvement. Our dataset is available at our website: http://nlp.uit.edu.vn/datasets/ for research purposes.
When making an online purchase, it becomes important for the customer to read the product reviews carefully and make a decision based on that. However, reviews can be lengthy, may contain repeated, or sometimes irrelevant information that does not help in decision making. In this paper, we introduce MRCBert, a novel unsupervised method to generate summaries from product reviews. We leverage Machine Reading Comprehension, i.e. MRC, approach to extract relevant opinions and generate both rating-wise and aspect-wise summaries from reviews. Through MRCBert we show that we can obtain reasonable performance using existing models and transfer learning, which can be useful for learning under limited or low resource scenarios. We demonstrated our results on reviews of a product from the Electronics category in the Amazon Reviews dataset. Our approach is unsupervised as it does not require any domain-specific dataset, such as the product review dataset, for training or fine-tuning. Instead, we have used SQuAD v1.1 dataset only to fine-tune BERT for the MRC task. Since MRCBert does not require a task-specific dataset, it can be easily adapted and used in other domains.
Understanding how events are semantically related to each other is the essence of reading comprehension. Recent event-centric reading comprehension datasets focus mostly on event arguments or temporal relations. While these tasks partially evaluate machines' ability of narrative understanding, human-like reading comprehension requires the capability to process event-based information beyond arguments and temporal reasoning. For example, to understand causality between events, we need to infer motivation or purpose; to establish event hierarchy, we need to understand the composition of events. To facilitate these tasks, we introduce ESTER, a comprehensive machine reading comprehension (MRC) dataset for Event Semantic Relation Reasoning. The dataset leverages natural language queries to reason about the five most common event semantic relations, provides more than 6K questions and captures 10.1K event relation pairs. Experimental results show that the current SOTA systems achieve 22.1%, 63.3%, and 83.5% for token-based exact-match, F1, and event-based HIT@1 scores, which are all significantly below human performances (36.0%, 79.6%, 100% respectively), highlighting our dataset as a challenging benchmark.
A method for creating a vision-and-language (V&L) model is to extend a language model through structural modifications and V&L pre-training. Such an extension aims to make a V&L model inherit the capability of natural language understanding (NLU) from the original language model. To see how well this is achieved, we propose to evaluate V&L models using an NLU benchmark (GLUE). We compare five V&L models, including single-stream and dual-stream models, trained with the same pre-training. Dual-stream models, with their higher modality independence achieved by approximately doubling the number of parameters, are expected to preserve the NLU capability better. Our main finding is that the dual-stream scores are not much different than the single-stream scores, contrary to expectation. Further analysis shows that pre-training causes the performance drop in NLU tasks with few exceptions. These results suggest that adopting a single-stream structure and devising the pre-training could be an effective method for improving the maintenance of language knowledge in V&L extensions.