对话情感分析旨在分析识别一段对话中用户在发言终止时的情绪状态。与传统的文本情感分析不同,对话过程中的上下文语境和用户之间的交互会对用户的情绪产生重要影响,且对话文本的语法结构复杂,多存在较远距离的语法成分的依赖关系,因而是一项十分具有挑战性的任务。为解决上述问题,该文将文本的句法依存关系引入模型中,通过图卷积网络提取句法结构信息,并与文本情感分析模型相结合,提出了两种同时建模语义和句法结构的模型H-BiLSTM+HGCL和BERT+HGCL。在构建的中文对话情感分析数据集上的实验表明,与不采用依存关系的基线模型相比,该文所提出的模型取得了更好的实验性能。
Abstract
Conversational sentiment analysis aims to analyze and detect the emotional state of a person in a conversation when it is terminated. Different from traditional textual sentiment analysis, the context of dialogues and interactions between the speakers will have an important impact on their emotions. Meanwhile, the syntactic structure of the dialogue text is generally complex, and there is a long-range dependency of syntactic components in many cases. It is therefore a very challenging task. To address this issue, this paper introduces the syntactic dependence of text into the model. We firstly extract the syntactic structure information through the graph convolution network, and then combine it with the text sentiment analysis model. Finally, two models named H-BiLSTM+HGCL and BERT+HGCL are proposed for modeling semantic and syntactic structure simultaneously. Experiments on the Chinese conversation sentiment analysis dataset we constructed show that the proposed model achieves better performance than the baseline models without dependency relation.
关键词
对话情感分析 /
依存关系 /
图卷积网络
{{custom_keyword}} /
Key words
conversational sentiment analysis /
dependency relation /
graph convolutional network
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Mohammad S M, Turney P D. Crowdsourcing a word-emotion association lexicon[J]. Computational Intelligence, 2013, 29(3): 436-465.
[2] Ojamaa B, Jokinen P K, Muischenk K. Sentiment analysis on conversational texts[C]//Proceedings of the 20th Nordic Conference of Computational Linguistics, 2015 (109): 233-237.
[3] 李明, 胡吉霞, 侯琳娜, 等. 商品评论情感倾向性分析[J]. 计算机应用, 2019, 39(S02): 15-19.
[4] 张琰, 黄霁风. 基于 PMI 的豆瓣电影评论文本情感分析[J]. 现代计算机, 2019 (12): 37-40.
[5] Majumder N, Poria S, Hazarika D, et al. Dialoguernn: An attentive rnn for emotion detection in conversations[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33: 6818-6825.
[6] Huang C, Trabelsi A, Zaane O R. ANA at SemEval-2019 Task 3: Contextual Emotion detection in Conversations through hierarchical LSTMs and BERT[J]. arXiv preprint arXiv: 1904.00132, 2019.
[7] Trinh T H, Dai A M, Luong M T, et al. Learning longer-term dependencies in rnns with auxiliary losses[C]//Proceedings of the International Conference on Machine Learning. PMLR, 2018: 4965-4974.
[8] Gupta U, Chatterjee A, Srikanth R, et al. A sentiment-and-semantics-based approach for emotion detection in textual conversations[J]. arXiv preprint arXiv: 1707.06996, 2017.
[9] Chen S Y, Hsu C C, Kuo C C, et al. Emotionlines: An emotion corpus of multi-party conversations[J]. arXiv preprint arXiv: 1802.08379, 2018.
[10] Chatterjee A, Narahari K N, Joshi M, et al. SemEval-2019 task 3: EmoContext contextual emotion detection in text[C]//Proceedings of the 13th International Workshop on Semantic Evaluation, 2019: 39-48.
[11] Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks[J]. arXiv preprint arXiv: 1609.02907, 2016.
[12] Velicˇkovic＇ P, Cucurull G, Casanova A, et al. Graph attention networks[J]. arXiv preprint arXiv: 1710.10903, 2017.
[13] Zhang C, Li Q, Song D. Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019: 4568-4578.
[14] Huang B, Carley K M. Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019: 5469-5477.
[15] Yao L, Mao C, Luo Y. Graph convolutional networks for text classification[C]//Proceedings of the AAAI Conference on Artificial Intelligence,2019, 33: 7370-7377.
[16] 宗成庆. 统计自然语言处理[M].北京: 清华大学出版社, 2013.
[17] Che W, Li Z, Liu T. Ltp: A chinese language technology platform[C]//Proceedings of the 23rd International Conference on Computational Linguistics: Demonstrations. Association for Computational Linguistics, 2010: 13-16.
[18] Qiu L, Lin H, Leung A K, et al. Putting their best foot forward: Emotional disclosure on Facebook[J]. Cyberpsychology, Behavior, and Social Networking, 2012, 15(10): 569-572.
[19] Qiu Y, Li H, Li S, et al. Revisiting correlations between intrinsic and extrinsic evaluations ofword embeddings[M]. Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data. Springer, Cham, 2018: 209-221.
[20] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Proceedings of the Advances in Neural Information Processing Systems, 2017: 5998-6008.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家重点研发计划(2018YFC0832101);国家自然科学基金(61702080,61632011);中央高校基本科研业务费专项资金(DUT19RC(4)016);中国博士后基金(2018M631788)
{{custom_fund}}
PDF(3712 KB)
