A Multi-turn Machine Reading Comprehension Framework with Rethink Mechanism for Emotion-Cause Pair Extraction

Emotion-cause pair extraction (ECPE) is an emerging task in emotion cause analysis, which extracts potential emotion-cause pairs from an emotional document. Most recent studies use end-to-end methods to tackle the ECPE task. However, these methods either suffer from a label sparsity problem or fail to model complicated relations between emotions and causes. Furthermore, they all do not consider explicit semantic information of clauses. To this end, we transform the ECPE task into a document-level machine reading comprehension (MRC) task and propose a Multi-turn MRC framework with Rethink mechanism (MM-R). Our framework can model complicated relations between emotions and causes while avoiding generating the pairing matrix (the leading cause of the label sparsity problem). Besides, the multi-turn structure can fuse explicit semantic information flow between emotions and causes. Extensive experiments on the benchmark emotion cause corpus demonstrate the effectiveness of our proposed framework, which outperforms existing state-of-the-art methods.

[1]  Hongfei Lin,et al.  Two-stage supervised ranking for emotion cause extraction , 2021, Knowl. Based Syst..

[2]  Shikun Zhang,et al.  Capturing Event Argument Interaction via A Bi-Directional Entity-Level Recurrent Decoder , 2021, ACL.

[3]  Lin Gui,et al.  Position Bias Mitigation: A Knowledge-Aware Graph Model for Emotion Cause Extraction , 2021, ACL.

[4]  Yubo Chen,et al.  What the Role is vs. What Plays the Role: Semi-Supervised Event Argument Extraction via Dual Question Answering , 2021, AAAI.

[5]  Yongliang Shen,et al.  Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition , 2021, ACL.

[6]  Qixuan Sun,et al.  A Dual-Questioning Attention Network for Emotion-Cause Pair Extraction with Context Awareness , 2021, 2021 International Joint Conference on Neural Networks (IJCNN).

[7]  Yu Wang,et al.  Bidirectional Machine Reading Comprehension for Aspect Sentiment Triplet Extraction , 2021, AAAI.

[8]  Ashutosh Modi,et al.  An End-to-End Network for Emotion-Cause Pair Extraction , 2021, WASSA.

[9]  Yi Shen,et al.  A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysis , 2021, AAAI.

[10]  Jie Liu,et al.  A Novel Interactive Recurrent Attention Network for Emotion-Cause Pair Extraction , 2020, ACAI.

[11]  Shoushan Li,et al.  End-to-End Emotion-Cause Pair Extraction with Graph Convolutional Network , 2020, COLING.

[12]  Jianping Wang,et al.  A Unified Sequence Labeling Model for Emotion Cause Pair Extraction , 2020, COLING.

[13]  Jing Shan,et al.  A New Component of Interactive Multi-task Network Model for Emotion-Cause Pair Extraction , 2020, Journal of Physics: Conference Series.

[14]  Yafeng Yin,et al.  A Symmetric Local Search Network for Emotion-Cause Pair Extraction , 2020, COLING.

[15]  Ruifeng Xu,et al.  Emotion-Cause Pair Extraction as Sequence Labeling Based on a Novel Tagging Scheme , 2020, EMNLP.

[16]  Jian Liu,et al.  Event Extraction as Machine Reading Comprehension , 2020, EMNLP.

[17]  Jianfei Yu,et al.  End-to-End Emotion-Cause Pair Extraction Based on Sliding Window Multi-Label Learning , 2020, EMNLP.

[18]  Zexuan Zhong,et al.  A Frustratingly Easy Approach for Joint Entity and Relation Extraction , 2020, ArXiv.

[19]  Rui Fan,et al.  An End-to-End Multi-task Learning Network with Scope Controller for Emotion-Cause Pair Extraction , 2020, NLPCC.

[20]  Libo Qin,et al.  A Co-Interactive Transformer for Joint Slot Filling and Intent Detection , 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[21]  Donghong Ji,et al.  Joint multi-level attentional model for emotion detection and emotion-cause pair extraction , 2020, Neurocomputing.

[22]  Jiahao Zhao,et al.  Effective Inter-Clause Modeling for End-to-End Emotion-Cause Pair Extraction , 2020, ACL.

[23]  Jianfei Yu,et al.  ECPE-2D: Emotion-Cause Pair Extraction based on Joint Two-Dimensional Representation, Interaction and Prediction , 2020, ACL.

[24]  Ruifeng Xu,et al.  Transition-based Directed Graph Construction for Emotion-Cause Pair Extraction , 2020, ACL.

[25]  Dawei Song,et al.  End-to-end Emotion-Cause Pair Extraction via Learning to Link , 2020, ArXiv.

[26]  Lidong Bing,et al.  A Knowledge Regularized Hierarchical Approach for Emotion Cause Analysis , 2019, EMNLP.

[27]  Jiwei Li,et al.  A Unified MRC Framework for Named Entity Recognition , 2019, ACL.

[28]  Yue Zhang,et al.  Hierarchically-Refined Label Attention Network for Sequence Labeling , 2019, EMNLP.

[29]  Yiqun Liu,et al.  Human Behavior Inspired Machine Reading Comprehension , 2019, SIGIR.

[30]  Rui Xia,et al.  RTHN: A RNN-Transformer Hierarchical Network for Emotion Cause Extraction , 2019, IJCAI.

[31]  Rui Xia,et al.  Emotion-Cause Pair Extraction: A New Task to Emotion Analysis in Texts , 2019, ACL.

[32]  Rui Xia,et al.  From Independent Prediction to Re-ordered Prediction: Integrating Relative Position and Global Label Information to Emotion Cause Identification , 2019, AAAI.

[33]  Mingxin Zhou,et al.  Entity-Relation Extraction as Multi-Turn Question Answering , 2019, ACL.

[34]  Ming-Wei Chang,et al.  BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions , 2019, NAACL.

[35]  Anders Søgaard,et al.  Jointly Learning to Label Sentences and Tokens , 2018, AAAI.

[36]  Richard Socher,et al.  The Natural Language Decathlon: Multitask Learning as Question Answering , 2018, ArXiv.

[37]  Frank Hutter,et al.  Decoupled Weight Decay Regularization , 2017, ICLR.

[38]  Frank Hutter,et al.  Fixing Weight Decay Regularization in Adam , 2017, ArXiv.

[39]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[40]  Qin Lu,et al.  A Question Answering Approach for Emotion Cause Extraction , 2017, EMNLP.

[41]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[42]  Yu Zhou,et al.  Event-Driven Emotion Cause Extraction with Corpus Construction , 2016, EMNLP.

[43]  Hua Xu,et al.  Text-based emotion classification using emotion cause extraction , 2014, Expert Syst. Appl..

[44]  Lin Gui,et al.  Multi-Task Sequence Tagging for Emotion-Cause Pair Extraction Via Tag Distribution Refinement , 2021, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[45]  Wenyuan Liu,et al.  A Mutually Auxiliary Multitask Model With Self-Distillation for Emotion-Cause Pair Extraction , 2021, IEEE Access.

[46]  Yongfeng Huang,et al.  A Multi-Task Learning Neural Network for Emotion-Cause Pair Extraction , 2020, ECAI.

[47]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[48]  Zhang Xiong,et al.  Multiple Level Hierarchical Network-Based Clause Selection for Emotion Cause Extraction , 2019, IEEE Access.

[49]  Liang Yang,et al.  Extracting Emotion Causes Using Learning to Rank Methods From an Information Retrieval Perspective , 2019, IEEE Access.

[50]  Daling Wang,et al.  A Co-Attention Neural Network Model for Emotion Cause Analysis with Emotional Context Awareness , 2018, EMNLP.

[51]  Léon Bottou,et al.  Large-Scale Machine Learning with Stochastic Gradient Descent , 2010, COMPSTAT.