计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (11A): 231000086-9.doi: 10.11896/jsjkx.231000086

• 智能计算 • 上一篇    下一篇

基于位置交互感知网络的多任务情绪原因对抽取方法

付明睿, 李卫疆   

  1. 昆明理工大学信息工程与自动化学院 昆明 650500
    昆明理工大学云南省人工智能重点实验室 昆明 650500
  • 出版日期:2024-11-16 发布日期:2024-11-13
  • 通讯作者: 李卫疆(hrbrichard＠126.com)
  • 作者简介:(a2813176983@126.com)
  • 基金资助:
    国家自然科学基金(62066022)

Multi-task Emotion-Cause Pair Extraction Method Based on Position-aware Interaction Network

FU Mingrui, LI Weijiang   

  1. Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500,China
    Yunnan Key Laboratory of Artificial Intelligence,Kunming University of Science and Technology,Kunming 650500,China
  • Online:2024-11-16 Published:2024-11-13
  • About author:FU Mingrui,born in 1997,MS candidate.His main research interests include sentiment analysis and machine learning.
    LI Weijiang,born in 1969,Ph.D,professor.His main research interests include information retrieval and natural language processing.
  • Supported by:
    National Natural Science Foundation of China(62066022).

PDF (PC)

180

摘要： 情绪原因对抽取任务旨在同时抽取情感子句和原因子句。已有的方法把情绪原因对抽取看作情绪抽取、原因抽取和情绪原因对抽取3个独立的任务,不能有效捕捉到任务之间的联系。此外,现有的两阶段模型存在误差传播问题,并且情绪子句和原因子句间相对位置分布不平衡。文中提出了一个新的基于BERT、情感词典和位置感知交互模块的情绪原因对抽取模型MK-BERT。该模型首先用情感词典增强的BERT进行文本编码;其次,为了解决标签位置不平衡问题,根据情感子句和原因子句间的相对距离设计位置感知交互模块,以捕捉位置信息并构建情绪原因对的特征;最后,通过情绪预测模块和原因预测模块间交互编码,充分挖掘多个任务间的共享信息。在中文情绪原因对抽取数据集上进行实验,结果表明,所提模型可以有效地抽取情绪原因对,并且在位置不平衡样本上取得良好性能。

关键词: 情感分析, 情绪原因对抽取, 多任务学习, 情感词典, 位置感知

Abstract: The task of emotion-cause pair extraction is to extract emotion clauses and reason clauses simultaneously.Previous methods regard emotion-cause pair extraction as three independent tasks of emotion extraction,cause extraction,and emotion-cause pair extraction,which cannot effectively capture the connection between tasks.In addition,the existing two-stage models suffer from error propagation problems,and the relative position distribution between emotion clauses and reason clauses is unbalanced.This paper proposes a new emotional reason pair extraction model MK-BERT based on BERT,sentiment lexicon and position-aware interaction module.The model first uses the BERT enhanced by the sentiment lexicon for document encoding.In order to solve the problem of label position imbalance,a position-aware interaction module is designed according to the relative distance between the emotion clause and the reason clause to capture the position information and construct the characteristics of the emotion-cause pair.Then,through interactive encoding between the emotion prediction module and the reason prediction mo-dule,the shared information among multiple tasks is fully mined.Experimental results on the Chinese emotion-reason pair extraction dataset show that the proposed modelcan effectively extract emotion-reason pairs and achieve good performance on positio-nally imbalanced samples.

Key words: Sentiment analysis, Emotion-Cause pair extraction, Multi-task learning, Sentiment lexicon, Position aware

中图分类号: 

  • TP391
[1]LEE S Y M,CHEN Y,HUANG C R.A text-driven rule-based system for emotion cause detection[C]//Proceedings of Computational Approaches to Analysis and Generation of Emotion in Text.2010:45-53.
[2]XIA R,DING Z.Emotion-cause pair extraction:A new task to emotion analysis in texts[C]//Proceedings of the Association for Computational Linguistics.2019:1003-1012.
[3]VASWANI A,SHAZEER N,PARMARN,et al.Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.2017:6000-6010.
[4]GUI L,HU J,HE Y,et al.A question answering approach foremotion cause extraction [C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing.2017:1593-1602.
[5]LI X,SONG K,FENG S,et al.A co-attention neural networkmodel for emotion cause analysis with emotional context awareness [C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing.2018:4752-4757.
[6]YU X Y,WENG E.Multiple Level Hierarchical Network-Based Clause Selection for Emotion Cause Extraction[J].IEEE Access,2019:9071-9079.
[7]DING Z,HE H,ZHANG M,et al.From Independent Prediction to Re-ordered Prediction:Integrating Relative Position and Global Label Information to Emotion Cause Identification[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019,33:6343-6350.
[8]XIA R,ZHANG M,DING Z.RTHN:A RNN-Transformer Hierarchical Network for Emotion Cause Extraction[C]//IJCAI.2019:5285-5291.
[9]HU G,LU G,ZHAO Y.FSS-GCN:A graph convolutional net-works with fusion of semantic and structure for emotion cause analysis[J].Knowledge-Based Systems,2020,212(1):106584.
[10]WEI P,ZHAO J,MAO W.Effective inter-clause modeling forend-to-end emotion-cause pair extraction[C]//Proceedings of the Association for Computational Linguistics.2020:3171-3181.
[11]DING Z,XIA R,YU J.ECPE-2D:Emotion-cause pair extraction based on joint two-dimensional representation,interaction and prediction [C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.2020:3161-3170.
[12]DING Z,XIA R,YU J.End-to-end emotion-cause pair extraction based on sliding window multi-label learning[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing.2020:3574-3583.
[13]YUAN C,FAN C,BAO J,et al.Emotion-cause pair extraction as sequence labeling based on a novel tagging scheme[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing.2020:3568-3573.
[14]TANG H,JI D,ZHOU Q.Joint multi-level attentional model for emotion detection and emotion-cause pair extraction[J].Neurocomputing,2020,409:329-340.
[15]WU S,CHEN F,WU F,et al.A multi-task learning neural network for emotion-cause pair extraction[C]//Proceedings of the 24th European Conference on Artificial Intelligence.2020:1-8.
[16]SONG H,SONG D.An end-to-end multi-task learning to link framework for emotion-cause pair extraction[C]//Proceedings of the International Conference on Image,Video Processing and Artificial Intelligence.2021:13-21.
[17]YU J,LIU W,HE Y,et al.A Mutually Auxiliary MultitaskModel with Self-Distillation for Emotion-Cause Pair Extraction[J].IEEE Access,2021,99:1-1.
[18]CHEN F,SHI Z,YANG Z,et al.Recurrent synchronization network for emotion-cause pair extraction[J].Knowledge-based Systems,2022:238.
[19]CHEN Y,HOU W,LI S,et al.End-to-End Emotion-Cause Pair Extraction with Graph Convolutional Network[C]//International Conference on Computational Linguistics.2020.
[20]WU Z,DAI X,XIA R.Pairwise tagging framework for end-to-end emotion-cause pair extraction[J].Frontiers of Computer Science,2023,17(2):1-10.
[21]HUANG W C,YANG Y X,PENG Z　Y,et al.Deep Neural Net-works Based on Span Association Prediction for Emotion-Cause Pair Extraction[J].Sensors,2022,22(10).
[22]DEVLIN J,CHANG M　W,LEE　K,et al.BERT:Pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.2019:4171-4186.
[23]FAN　C,YUAN　C,DU　J,et al.Transition-based directed graph construction for emotion-cause pair extraction[C]//Proceedings of the 58th Annual Meeting of the Association for Compu-tational Linguistics.2020:3707-3717.
[24]CHENG Z,JIANG Z,YIN Y,et al.A Unified Target-Oriented Sequence-to-Sequence Model for Emotion-Cause Pair Extraction[J].IEEE/ACM Transactions on Audio,Speech,and Language Processing,2021:1-1.
[25]FAN C,YUAN C,GUI　L,et al.Multi-task Sequence Tagging for Emotion-Cause Pair Extraction via Tag Distribution Refinement[J].IEEE/ACM Transactions on Audio,Speech,and Language Processing,2021:1-1.
[26]BAO Y,MA Q,WEI　L,et al.Multi-Granularity Semantic AwareGraph Model for Reducing Position Bias in Emotion-Cause Pair Extraction[J].2022.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发