Bridging Anaphora Resolution as Question Answering
IBM Research Europe（IBM欧洲研究院）
Yufang Hou
备注：
accepted at ACL2020. This version is slightly different than the ACL2020 camera-ready version. Thanks for Massimo Poesio's comments, I've made two small changes to describe GNOME and the work in Poesio et al. (2004) more accurately
Most previous studies on bridging anaphora resolution (Poesio et al., 2004; Hou et al., 2013b; Hou, 2018a) use the pairwise model to tackle the problem and assume that the gold mention information is given. In this paper, we cast bridging anaphora resolution as question answering based on context. This allows us to find the antecedent for a given anaphor without knowing any gold mention information (except the anaphor itself). We present a question answering framework (BARQA) for this task, which leverages the power of transfer learning. Furthermore, we propose a novel method to generate a large amount of "quasi-bridging" training data. We show that our model pre-trained on this dataset and fine-tuned on a small amount of in-domain dataset achieves new state-of-the-art results for bridging anaphora resolution on two bridging corpora (ISNotes (Markert et al., 2012) and BASHI (Roesiger, 2018)).
IBM Research Ireland（IBM爱尔兰研究公司（IBM Research Ireland））
Most current models of word representations(e.g.,GloVe) have successfully captured fine-grained semantics. However, semantic similarity exhibited in these word embeddings is not suitable for resolving bridging anaphora, which requires the knowledge of associative similarity (i.e., relatedness) instead of semantic similarity information between synonyms or hypernyms. We create word embeddings (embeddings_PP) to capture such relatedness by exploring the syntactic structure of noun phrases. We demonstrate that using embeddings_PP alone achieves around 30% of accuracy for bridging anaphora resolut…
Previous work on bridging anaphora resolution (Poesio et al., 2004; Hou et al., 2013b) use syntactic preposition patterns to calculate word relatedness. However, such patterns only consider NPs' head nouns and hence do not fully capture the semantics of NPs. Recently, Hou (2018) created word embeddings (embeddings_PP) to capture associative similarity (ie, relatedness) between nouns by exploring the syntactic structure of noun phrases. But embeddings_PP only contains word representations for nouns. In this paper, we create new word vectors by combining embeddings_PP with GloVe. This new word e…
Lister Hill National Center for Biomedical Communications（利斯特·希尔国家生物医学交流中心）；U.S. National Library of Medicine（美国国家医学图书馆）
In this paper we present OSCAR (Ontology-based Semantic Composition Augmented Regularization), a method for injecting task-agnostic knowledge from an Ontology or knowledge graph into a neural network during pretraining. We evaluated the impact of including OSCAR when pretraining BERT with Wikipedia articles by measuring the performance when fine-tuning on two question answering tasks involving world knowledge and causal reasoning and one requiring domain (healthcare) knowledge and obtained 33:3%, 18:6%, and 4% improved accuracy compared to pretraining BERT without OSCAR and obtaining new state…
Sluice resolution is a problem where a system needs to output the corresponding antecedents of wh-ellipses. The antecedents are elided contents behind the wh-words but are implicitly referred to using contexts. Previous work frames sluice resolution as question answering where this setting outperforms all its preceding works by large margins. Ellipsis and questions are referentially dependent expressions (anaphoras) and retrieving the corresponding antecedents are like answering questions to output pieces of clarifying information. However, the task is not fully solved. Therefore, we want to f…
In this work, we analyze how human gaze during reading comprehension is conditioned on the given reading comprehension question, and whether this signal can be beneficial for machine reading comprehension. To this end, we collect a new eye-tracking dataset with a large number of participants engaging in a multiple choice reading comprehension task. Our analysis of this data reveals increased fixation times over parts of the text that are most relevant for answering the question. Motivated by this finding, we propose making automated reading comprehension more human-like by mimicking human info…
One of the main challenges in conversational question answering (CQA) is to resolve the conversational dependency, such as anaphora and ellipsis. However, existing approaches do not explicitly train QA models on how to resolve the dependency, and thus these models are limited in understanding human dialogues. In this paper, we propose a novel framework, ExCorD (Explicit guidance on how to resolve Conversational Dependency) to enhance the abilities of QA models in comprehending conversational context. ExCorD first generates self-contained questions that can be understood without the conversatio…
ChartReasoner: Code-Driven Modality Bridging for Long-Chain Reasoning in Chart Question Answering
MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所MAIS研究所）；Shenyang Institute of Computing Technology, Chinese Academy of Sciences（中国科学院沈阳计算技术研究所）；Beijing Wenge Technology Co., Ltd.（北京文耕科技有限公司）；University of Chinese Academy of Sciences（中国科学院大学）
University of Cambridge（剑桥大学）；Mila（米拉研究所）；Université de Montréal（蒙特利尔大学）
Embodied Question Answering (EQA) is a recently proposed task, where an agent is placed in a rich 3D environment and must act based solely on its egocentric input to answer a given question. The desired outcome is that the agent learns to combine capabilities such as scene understanding, navigation and language understanding in order to perform complex reasoning in the visual world. However, initial advancements combining standard vision and language methods with imitation and reinforcement learning algorithms have shown EQA might be too complex and challenging for these techniques. In order t…
Most previous studies on information status (IS) classification and bridging anaphora recognition assume that the gold mention or syntactic tree information is given (Hou et al., 2013; Roesiger et al., 2018; Hou, 2020; Yu and Poesio, 2020). In this paper, we propose an end-to-end neural approach for information status classification. Our approach consists of a mention extraction component and an information status assignment component. During the inference time, our system takes a raw text as the input and generates mentions together with their information status. On the ISNotes corpus (Marker…
Previous work on bridging anaphora recognition (Hou et al., 2013a) casts the problem as a subtask of learning fine-grained information status (IS). However, these systems heavily depend on many hand-crafted linguistic features. In this paper, we propose a simple discourse context-aware BERT model for fine-grained IS classification. On the ISNotes corpus (Markert et al., 2012), our model achieves new state-of-the-art performance on fine-grained IS classification, obtaining a 4.8 absolute overall accuracy improvement compared to Hou et al. (2013a). More importantly, we also show an improvement o…
Neural retrievers based on pre-trained language models (PLMs), such as dual-encoders, have achieved promising performance on the task of open-domain question answering (QA). Their effectiveness can further reach new state-of-the-arts by incorporating cross-architecture knowledge distillation. However, most of the existing studies just directly apply conventional distillation methods. They fail to consider the particular situation where the teacher and student have different structures. In this paper, we propose a novel distillation method that significantly advances cross-architecture distilla…
We describe three models submitted for the CODI-CRAC 2022 shared task. To perform identity anaphora resolution, we test several combinations of the incremental clustering approach based on the Workspace Coreference System (WCS) with other coreference models. The best result is achieved by adding the ''cluster merging'' version of the coref-hoi model, which brings up to 10.33% improvement 1 over vanilla WCS clustering. Discourse deixis resolution is implemented as multi-task learning: we combine the learning objective of corefhoi with anaphor type classification. We adapt the higher-order resol…
Institute for Infocomm Research (I2R), A*STAR（新加坡科技研究局资讯通信研究院）
There is growing interest in the automated extraction of relevant information from clinical dialogues. However, it is difficult to collect and construct large annotated resources for clinical dialogue tasks. Recent developments in natural language processing suggest that large-scale pre-trained language backbones could be leveraged for such machine comprehension and information extraction tasks. Yet, due to the gap between pre-training and downstream clinical domains, it remains challenging to exploit the generic backbones for domain-specific applications. Therefore, in this work, we propose a…
Queen Mary University of London（伦敦玛丽女王大学）；UKP Lab, Technische Universität Darmstadt（德国达姆施塔特工业大学UKP实验室）
Now that the performance of coreference resolvers on the simpler forms of anaphoric reference has greatly improved, more attention is devoted to more complex aspects of anaphora. One limitation of virtually all coreference resolution models is the focus on single-antecedent anaphors. Plural anaphors with multiple antecedents-so-called split-antecedent anaphors (as in John met Mary. They went to the movies) have not been widely studied, because they are not annotated in ONTONOTES and are relatively infrequent in other corpora. In this paper, we introduce the first model for unrestricted resolut…
Previous work on bridging anaphora recognition (Hou et al., 2013a) casts the problem as a subtask of learning fine-grained information status (IS). However, these systems heavily depend on many hand-crafted linguistic features. In this paper, we propose a discourse context-aware self-attention neural network model for fine-grained IS classification. On the ISNotes corpus (Markert et al., 2012), our model with the contextually-encoded word representations (BERT) (Devlin et al., 2018) achieves new state-of-the-art performances on fine-grained IS classification, obtaining a 4.1% absolute overall …
Beyond Isolated Capabilities: Bridging Long CoT Reasoning and Long-Context Understanding
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（多模态人工智能系统国家重点实验室，自动化研究所，中国科学院）；School of Artificial Intelligence, University of Chinese Academy of Sciences（人工智能学院，中国科学院大学）
AMATA: Adaptive Multi-Agent Trajectory Alignment for Knowledge-Intensive Question Answering
School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机科学与信息工程学院）；Shanghai University of Electric Power（上海电力大学）；East China Normal University（华东师范大学）；Guangdong University of Finance and Economics（广东财经大学）；Alibaba Group（阿里巴巴集团）
LongSumEval: Question-Answering Based Evaluation and Feedback-Driven Refinement for Long Document Summarization
dept. of Information Science University of North Texas Denton, Texas, USA（信息科学系 俄克拉荷马州立大学 德顿, 德克萨斯州, 美国）；dept. of Data Science University of North Texas Denton, Texas, USA（数据科学系 俄克拉荷马州立大学 德顿, 德克萨斯州, 美国）
Peking University（北京大学）；Peng Cheng Laboratory（鹏城实验室）；Hong Kong University of Science and Technology（香港科技大学）
Knowledge-aware question answering (KAQA) requires the model to answer questions over a knowledge base, which is essential for both open-domain QA and domain-specific QA, especially when language models alone cannot provide all the knowledge needed. Despite the promising result of recent KAQA systems which tend to integrate linguistic knowledge from pre-trained language models (PLM) and factual knowledge from knowledge graphs (KG) to answer complex questions, a bottleneck exists in effectively fusing the representations from PLMs and KGs because of (i) the semantic and distributional gaps betw…
University of California, Santa Barbara（加州大学圣巴巴拉分校）；Korea University（高丽大学）；Meta AI；Google Research（谷歌研究院）；Apple（苹果公司）
Building dense retrievers requires a series of standard procedures, including training and validating neural models and creating indexes for efficient search. However, these procedures are often misaligned in that training objectives do not exactly reflect the retrieval scenario at inference time. In this paper, we explore how the gap between training and inference in dense retrieval can be reduced, focusing on dense phrase retrieval (Lee et al., 2021) where billions of representations are indexed at inference. Since validating every dense retriever with a large-scale index is practically infe…
LingShu: A Large-Scale Symptom-Centric Contextualized Knowledge Graph Bridging Traditional Chinese Medicine and Modern Biomedicine
Beijing Jiaotong University（北京交通大学）；Hubei Provincial Hospital of Traditional Chinese Medicine（湖北省中医院）；Hubei University of Chinese Medicine（湖北中医药大学）；Hubei Province Academy of Traditional Chinese Medicine（湖北省中医药研究院）；China Academy of Chinese Medical Sciences（中国中医科学院）；Xiyuan Hospital（西苑医院）；National Clinical Research Center for Chinese Medicine Cardiology（国家中医心血管病临床医学研究中心）；Hubei Provincial Clinical Research Center for Acupuncture and Moxibustion in Obesity Treatment（湖北省肥胖病针灸临床研究中心）；Hubei Shizhen Laboratory（湖北时珍实验室）；Tianjin Ta（天津（此处原文未完整，按原文提取））
