An Iterative Emotion Interaction Network for Emotion Recognition in Conversations

Proceedings of the 28th International Conference on Computational Linguistics, pages 4078–4088 Barcelona, Spain (Online), December 8-13, 2020 4078 An Iterative Emotion Interaction Network for Emotion Recognition in Conversations Xin Lu, Yanyan Zhao, Yang Wu, Yijian Tian, Huipeng Chen, Bing Qin∗ Research Center for Social Computing and Information Retrieval Harbin Institute of Technology, China {xlu, yyzhao, ywu, yjtian, chp, qinb}@ir.hit.edu.cn Abstract Emotion recognition in conversations (ERC) has received much attention recently in the natural language processing community. Considering that the emotions of the utterances in conversa- tions are interactive, previous works usually implicitly model the emotion interaction between utterances by modeling dialogue context, but the misleading emotion information from context often interferes with the emotion interaction. We noticed that the gold emotion labels of the context utterances can provide explicit and accurate emotion interaction, but it is impossible to input gold labels at inference time. To address this problem, we propose an iterative emotion in- teraction network, which uses iteratively predicted emotion labels instead of gold emotion labels to explicitly model the emotion interaction. This approach solves the above problem, and can effectively retain the performance advantages of explicit modeling. We conduct experiments on two datasets, and our approach achieves state-of-the-art performance. 1 Introduction Emotion recognition in conversations (ERC) aims to recognize the emotion of each utterance in conver- sations. Recently it has received much attention due to its applications in various conversation scenes, such as emotional chatbots (Zhou et al., 2018), emotion detection of customers in artificial services (Song et al., 2019), sentiment analysis of comments in social media (Chatterjee et al., 2019), and so on. Different from the common sentence-level emotion recognition task, ERC is special due to some characteristics. The first one is that the utterances are context dependent, and modeling context can provide more information for emotion recognition (Poria et al., 2017; Jiao et al., 2019). The second characteristic of ERC is that the utterances are speaker-sensitive, thus many researchers modeled the state of speakers and the inter-speaker dependency relations (Hazarika et al., 2018b; Majumder et al., 2019; Zhang et al., 2019; Ghosal et al., 2019). In this paper, we observe another characteristic that is the emotions of the utterances are interactive. For example, in Figure 1, the emotion of the utterance from Speaker A can directly influence Speaker B. Thus, modeling the emotion interaction between utterances is helpful for the ERC task. Previous works usually implicitly model the emotion interaction by modeling dialogue context (Po- ria et al., 2017; Jiao et al., 2019). However, because of the arbitrariness of the dialogue, the context utterances often convey misleading emotion information when recognizing the emotion of the target ut- terance, such as in Figure 1(a). To solve this problem, we observe that the gold emotion labels (such as “happy”, “angry”) of the context utterances can provide explicit and accurate emotion interaction be- tween utterances, such as in Figure 1(b). Thus, we can introduce the emotion labels to explicitly model the emotion interaction between utterances. However, a challenging problem …

Content truncated to 500 words