基于多粒度融合的图卷积网络会话情感分析

PDF(5316 KB)

中文信息学报 ›› 2024, Vol. 38 ›› Issue (5) : 136-145.

情感分析与社会计算

基于多粒度融合的图卷积网络会话情感分析

王佳,朱小飞,唐顾,黄贤英

作者信息 +

Multi-granular Information Fusion Approach to Graph Convolutional Network Based Conversational Emotion Recognition

WANG Jia, ZHU Xiaofei, TANG Gu, HUANG Xianying

Author information +

History +

摘要

会话情感分析指对一段会话中的每句话进行情感分类,目前大部分会话情感分析模型不仅忽略了对话中内部信息的相互影响,而且没有考虑到日常对话中存在的隐性背景情感。为了有效解决这些问题,该文提出了一个基于多粒度融合的图卷积神经网络,其主要包括两个模块,即特征提取模块和星图增强的图学习模块。首先,特征提取模块使用预训练语言模型RoBERTa获取会话中语句之间粗粒度的上下文信息,同时结合句法依赖树获取词之间细粒度的句法信息,从而将多粒度特征信息引入到会话情感建模。然后,在星图增强的图学习模块中建模会话的背景情感信息和会话中不同说话者之间的交互信息,从而增强会话情感分析的准确性。实验结果表明,该文提出的模型与其他基线模型相比,其准确性以及度量指标F₁值在所有数据集上均有显著提升。

Abstract

Conversation sentiment analysis refers to the classification of emotions for each sentence in a conversation. To capture the hidden background emotions and the interaction of internal information in the conversation, this paper proposes a multi-granular information fusion approach to graph convolutional neural network based conversational emotion recognition. First, a feature extraction module uses the pre-trained language model RoBERTa to obtain coarse-grained contextual information between statements in conversation, and applies the syntactic dependence tree to obtain fine-grained syntactic information between words. Then, a star graph learning module enhances the accuracy of conversation sentiment analysis by modeling the contextual sentiment information of the conversation and the interaction information between different speakers in the conversation. Experimental results show that the accuracy of the proposed model and the value of the metric F₁ are significantly improved in all data sets compared with other baselines.

导出引用

王佳,朱小飞,唐顾,黄贤英. 基于多粒度融合的图卷积网络会话情感分析. 中文信息学报. 2024, 38(5): 136-145

WANG Jia, ZHU Xiaofei, TANG Gu, HUANG Xianying. Multi-granular Information Fusion Approach to Graph Convolutional Network Based Conversational Emotion Recognition. Journal of Chinese Information Processing. 2024, 38(5): 136-145

参考文献

[1] WAWRE S V, DESHMUKH S N. Sentiment classification using machine learning techniques[J]. International Journal of Science and Research, 2016, 5(4): 819-821.
[2] DONG L, WEI F, TAN C, et al. Adaptive recursive neural network for target-dependent twitter sentiment classification[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, 2014: 49-54.
[3] 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.
[4] MAJUMDER N, HONG P, PENG S, et al. MIME: Mimicking emotions for empathetic response generation[J]. arXiv preprint arXiv: 2010.01454, 2020.
[5] PORIA S, MAJUMDER N, MIHALCEA R, et al. Emotion recognition in conversation: Research, challenges, datasets, and recent advances[J]. IEEE Access, 2019, 7: 100943-100953.
[6] ZHANG D, WU L, SUN C, et al. Modeling both context-and speaker-sensitive dependence for emotion detection in multi-speaker conversations[C]//Proceedings of the IJCAI, 2019: 5415-5421.
[7] SCHULLER B, VALSTER M, EYBEN F, et al. Avec: The continuous audio/visual emotion challenge[C]//Proceedings of the 14th ACM International Conference on Multimodal Interaction, 2012: 449-456.
[8] HAZARIKA D, PORIA S, MIHALCEA R, et al. Icon: Interactive conversational memory network for multimodal emotion detection[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2018: 2594-2604.
[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] GHOSAL D, MAJUMDER N, PORIA S, et al. Dialoguegcn: A graph convolutional neural network for emotion recognition in conversation[J]. arXiv preprint arXiv: 1908.11540, 2019.
[11] ISHIWATARI T, YASUDA Y, MIYAZAKI T, et al. Relation-aware graph attention networks with relational position encodings for emotion recognition in conversations[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2020: 7360-7370.
[12] ZHONG P, WANG D, MIAO C. Knowledge-enriched transformer for emotion detection in textual conversations[J]. arXiv preprint arXiv: 1909.10681, 2019.
[13] TAI K S, SOCHER R, MANNING C D. Improved semantic representations from tree-structured long short-term memory networks[J]. arXiv preprint arXiv: 1503.00075, 2015.
[14] SHUAI B, ZUO Z, WANG B, et al. Dag-recurrent neural networks for scene labeling[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 3620-3629.
[15] THOST V, CHEN J. Directed acyclic graph neural networks[J]. arXiv preprint arXiv: 2101.07965, 2021.
[16] SHEN W, WU S, YANG Y, et al. Directed acyclic graph network for conversational emotion recognition[J]. arXiv preprint arXiv: 2105.12907, 2021.
[17] 徐秀,刘德喜. 基于上下文和位置交互协同注意力的文本情绪原因识别[J]. 中文信息学报,2022, 36(2): 142-151.
[18] JIAO W, YANG H, KING I, et al. Higru: Hierarchical gated recurrent units for utterance-level emotion recognition[J]. arXiv preprint arXiv: 1904.04446, 2019.
[19] 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(01): 6818-6825.
[20] GHOSAL D, MAJUMDER N, GELBUKH A, et al. COSMIC: Commonsense knowledge for emotion identification in conversations[J]. arXiv preprint arXiv: 2010.02795, 2020.
[21] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[22] 雷鹏斌, 秦斌, 王志立, 等.PRBDN: 基于预训练的微博评论情感分类模型[J]. 中文信息学报, 2022, 36(8): 101-108.
[23] 宋明, 刘彦隆. Bert 在微博短文本情感分类中的应用与优化[J]. 小型微型计算机系统, 2021, 42(04): 714-718.
[24] SCHLICHTKRULL M, KIPF T N, BLOEM P, et al. Modeling relational data with graph convolutional networks[C]//Proceedings of the European Semantic Web Conference. Springer, Cham, 2018: 593-607.
[25] WANG G, YING R, HUANG J, et al. Multi-hop attention graph neural network[J]. arXiv preprint arXiv: 2009.14332, 2020.
[26] 赵志影, 邵新慧, 林幸. 用于方面情感分析的结合图卷积神经网络的注意力模型[J]. 中文信息学报, 2022, 36(7): 154-163.
[27] BUSSO C, BULUT M, LEE C C, et al. IEMOCAP: Interactive emotional dyadic motion capture database[J]. Language Resources and Evaluation, 2008, 42(4): 335-359.
[28] LI Y, SU H, SHEN X, et al. Dailydialog: A manually labelled multi-turn dialogue dataset[J]. arXiv preprint arXiv: 1710.03957, 2017.
[29] PORIA S, HAZARIKA D, MAJUMDER N, et al. Meld: A multimodal multi-party dataset for emotion recognition in conversations[J]. arXiv preprint arXiv: 1810.02508, 2018.
[30] ZAHIRI S M, CHOI J D. Emotion detection on TV show transcripts with sequence-based convolutional neural networks[C]//Proceedings of the Workshops at the 32nd AAAI Conference on Artificial Intelligence, 2018.
[31] SHEN W, CHEN J, QUAN X, et al. Dialogxl: All-in-one xlnet for multi-party conversation emotion recognition[J]. arXiv preprint arXiv: 2012.08695, 2020.
[32] TURNEY P. Semantic orientation applied to unsupervised classification of reviews[C]//Proceedings of ACL, 40th Annual Meeting of the Association for Computational Linguistics, 2002.
[33] VO D T, ZHANG Y. Target-dependent twitter sentiment classification with rich automatic features[C]//Proceedings of the 24th International Joint Conference on Artificial Intelligence, 2015.
[34] HAZARIKA D, PORIA S, ZADEH A, et al. Conversational memory network for emotion recognition in dyadic dialogue videos[C]//Proceedings of the Conference,Association for Computational Linguistics, NIH Public Access, 2018: 2122.
[35] 曾义夫, 蓝天, 吴祖峰, 等. 基于双记忆注意力的方面级别情感分类模型[J]. 计算机学报, 2019, 8: 1845-1857.

基金

国家自然科学基金(62141201);重庆市自然科学基金(CSTB2022NSCQ-MSX1672);重庆市教育委员会科学技术研究计划重大项目(KJZD-M202201102)

PDF(5316 KB)

447

Accesses

Citation

Detail

段落导航

摘要
Abstract
关键词
Key words
引用本文
参考文献
基金

选择文件类型/文献管理软件名称

选择包含的内容

摘要

Abstract

关键词

Key words

引用本文

{{custom_sec.title}}

{{custom_sec.title}}

参考文献

{{custom_fnGroup.title_cn}}

脚注

基金

Published
2024-06-24
Issue Date
2024-06-26