EmotionIC:emotional inertia and contagion-driven dependency modeling for emotion recognition in conversation  

作　　者：Yingjian LIU Jiang LI Xiaoping WANG Zhigang ZENG 

机构地区：[1]School of Artificial Intelligence and Automation,Huazhong University of Science and Technology,Wuhan 430074,China [2]Institute of Artificial Intelligence,Huazhong University of Science and Technology,Wuhan 430074,China [3]Hubei Key Laboratory of Brain-inspired Inteigent Systems,Huazhong University of Science and Technology,Wuhan 430074,China [4]Key Laboratory of Image Processing and Intelligent Control(Huazhong University of Science and Technology),Ministry of Education,Wuhan 430074,China

出　　处：《Science China(Information Sciences)》2024年第8期126-142,共17页中国科学（信息科学）（英文版）

基　　金：supported in part by National Natural Science Foundation of China(Grant Nos.62236005,61936004,U1913602)。

摘　　要：Emotion recognition in conversation(ERC)has attracted growing attention in recent years as a result of the advancement and implementation of human-computer interface technologies.In this paper,we propose an emotional inertia and contagion-driven dependency modeling approach(EmotionIC)for ERC tasks.Our EmotionIC consists of three main components,i.e.,identity masked multi-head attention(IM-MHA),dialogue-based gated recurrent unit(DiaGRU),and skip-chain conditional random field(SkipCRF).Compared to previous ERC models,EmotionIC can model a conversation more thoroughly at both the feature-extraction and classification levels.The proposed model attempts to integrate the advantages of attention-and recurrence-based methods at the feature-extraction level.Specifically,IMMHA is applied to capture identity-based global contextual dependencies,while DiaGRU is utilized to extract speaker-and temporal-aware local contextual information.At the classification level,SkipCRF can explicitly mine com-plex emotional flows from higher-order neighboring utterances in the conversation.Experimental results show that our method can significantly outperform the state-of-the-art models on four benchmark datasets.The ablation studies confirm that our modules can effectively model emotional inertia and contagion.

关 键 词：emotion recognition in conversation emotional inertia and contagion multi-head attention gated recurrent unit conditional random field 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TP391.1[自动化与计算机技术—控制科学与工程]