情绪原因对抽取任务是将情绪子句与原因子句同时抽取。针对该任务,现有模型的编码层未考虑强化情感词语义表示,且仅使用单一图注意力网络,因此,该文提出了一个使用情感词典、图网络和多头注意力的情绪原因对抽取方法(Sen-BiGAT-Inter)。该方法首先利用情感词典与子句中的情感词汇匹配,并将匹配的情感词汇与该子句进行合并,再使用预训练模型BERT(Bidirectional Encoder Representation from Transformers)对句子进行表示。其次,建立两个图注意力网络,分别学习情绪子句和原因子句表示,进而获取候选情绪原因对的表示。在此基础上,应用多头注意力交互机制学习候选情绪原因对的全局信息,同时结合相对位置信息得到候选情绪原因对的表示,用于实现情绪原因对的抽取。在中文情绪原因对抽取数据集上的实验结果显示,相比目前最优的结果,该文所提出的模型在 F1 值上提升约1.95。
Abstract
Emotion-cause pair extraction is to extract both emotion clause and cause clause at the same time. For this task, the existing method of a single graph attention network does not consider emphasize the semantic representation of emotion words in the encoding layer. This paper proposes a Sen-BiGAT-Inter method using sentiment lexicon, graph network and multi-attention. The proposed method uses the sentiment lexicon to merge this clause with the emotion words in the clause, and uses the pre-training model BERT (Bidirectional Encoder Representation from Transformers) to obtain the clause representation. Then, we build two graph attention networks to learn the representation of emotion clause and cause clause, respectively, and then obtain the representation of candidate emotion-cause pair. On this basis, we get the emotion-cause pair with causality by using multi-head attention to learn the global information of candidate sentence pairs, and combing the relative position information to get the final representation of pairs. The experimental results on Chinese emotion-cause pair extraction dataset show the proposed model improves the F1 value by about 1.95 compared with the current optimal results.
关键词
情绪原因对抽取 /
情感词典 /
图注意力网络
{{custom_keyword}} /
Key words
emotion-cause pair extraction /
sentiment lexicon /
graph attention network
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[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] Gui L, Wu D, Xu R, et al. Event-driven emotion cause extraction with corpus construction[C]//Proceedings of the Conference on Empirical Methods on Natural Language Processing,2016:1639-1649.
[3] Xia R,Ding Z X. Emotion-cause pair extraction: a new task to emotion analysis in texts[C]// Proceedings of the 57th Conference of the Association for Computational Linguistics,2019:1003-1012.
[4] Xia R, Ding Z X. Emotion-cause pair extraction based on joint two-dimensional representation, interaction and prediction[C]// Proceedings of the 58th Conference of the Association for Computational Linguistics,2020:3161-3170.
[5] 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 Computational Linguistics,2020: 3707-3717.
[6] Chen X H, Li Q, Wang J P. A unified sequence labeling model for emotion cause pair extraction[C]//Proceedings of the 28th International Conference on Computational Linguistics,2020: 208-218.
[7] Jacob D, Chang M W, Lee K, et al. BERT: pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,2019,1: 4171-4186.
[8] Lee S Y M, Chen Y, Huang C R, et al. Detecting emotion causes with a linguistic rule-based approach [J]. Computational Intelligence, 2013, 29(3): 2-28.
[9] Gui L,Yuan L, Xu R, et al. Emotion cause detection with linguistic construction in Chinese Weibo text [M].Natural Language Processing and Chinese Computing, 2014:457-464.
[10] Gui L, Hu J, He Y, et al. A question answering approach to emotion cause extraction[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing,2017:1593-1602.
[11] Chen Y, Hou W J, Cheng X Y, et al. Joint learning for emotion classification and emotion cause detection[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2018:646-651.
[12] Fan C, Yan H, Du J, et al. A knowledge regularized hierarchical approach for emotion cause analysis[C]// Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing,2019:5613--5623.
[13] Li X, Feng S , Wang D , et al. Context-aware emotion cause analysis with multi-attention-based neural network[J].Knowledge-Based Systems, 2019,174(15): 205-218.
[14] 慕永利, 李旸, 王素格. 基于E-CNN的情绪原因识别方法[J].中文信息学报, 2018, 32(2): 120-128.
[15] Xia R, Zhang M G, Ding Z X. RTHN: a RNN-transformer hierarchical network for emotion cause extraction[C]//Proceedings of 28th International Joint Conference on Artificial Intelligence,2019:5285-5291.
[16] Li X, Song K, Feng S, et al. A co-attention neural network model for emotion cause analysis with emotional context awareness[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2018:4752-4757.
[17] Wei P, Zhao J, Mao W. Effective inter-clause modeling for end-to-end emotion-cause pair extraction[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics,2020: 3171-3181.
[18] 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.
[19] Tang H, Ji D, Zhou Q. Joint multi-level attentional model for emotion detection and emotion-cause pair extraction[J].Neurocomputing,2020,409(7): 329-340.
[20] Ding Z, Xia R, Yu J. End-to-end emotion-cause pair extraction based on sliding window multi-label learning[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing,2020:3574-358.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(62106130,62076158 );山西省重点研发计划项目(201803D421024);山西省研究生教育创新项目(2021Y148);山西省基础研究计划(20210302124084);山西省高等学校科技创新项目(2021L284)
{{custom_fund}}
PDF(4899 KB)
