Knowledge Aware Emotion Recognition in Textual Conversations via Multi-Task Incremental Transformer

Proceedings of the 28th International Conference on Computational Linguistics, pages 4429–4440 Barcelona, Spain (Online), December 8-13, 2020 4429 Knowledge Aware Emotion Recognition in Textual Conversations via Multi-Task Incremental Transformer Duzhen Zhang1,2, Xiuyi Chen1,2*, Shuang Xu1 and Bo Xu1,2 1Institute of Automation, Chinese Academy of Sciences (CASIA). Beijing, China 2School of Artificial Intelligence, University of Chinese Academy of Sciences {zhangduzhen2019,chenxiuyi2017,shuang.xu,xubo}@ia.ac.cn Abstract Emotion recognition in textual conversations (ERTC) plays an important role in a wide range of applications, such as opinion mining, recommender systems, and so on. ERTC, however, is a challenging task. For one thing, speakers often rely on the context and commonsense knowledge to express emotions; for another, most utterances contain neutral emotion in conversations, as a result, the confusion between a few non-neutral utterances and much more neutral ones restrains the emotion recognition performance. In this paper, we propose a novel Knowledge Aware In- cremental Transformer with Multi-task Learning (KAITML) to address these challenges. Firstly, we devise a dual-level graph attention mechanism to leverage commonsense knowledge, which augments the semantic information of the utterance. Then we apply the Incremental Transformer to encode multi-turn contextual utterances. Moreover, we are the first to introduce multi-task learning to alleviate the aforementioned confusion and thus further improve the emotion recog- nition performance. Extensive experimental results show that our KAITML model outperforms the state-of-the-art models across five benchmark datasets. 1 Introduction Emotion recognition in textual conversations (ERTC), which aims to identify the emotion of each utter- ance from the transcript of a conversation, has become a popular research topic in recent years. ERTC can be widely used in various scenarios, such as opinion mining of comments in social media (Chatterjee et al., 2019), emotion analysis of customers in artificial customer service, and others. In addition, it can also be applied to chat robots to analyze the user’s emotional state in real time and generate emotion-aware responses (Poria et al., 2019b; Zhou et al., 2018a; Huang et al., 2018). Truth Prediction Others Angry Sad Happy Others 4424 101 60 92 Angry 54 237 6 1 Sad 44 11 192 3 Happy 88 0 2 194 Table 1: A confusion matrix of the emotion recognition results on the EmoContext test dataset (Chatterjee et al., 2019) from Knowledge-Enriched Transformer (Zhong et al., 2019b), which is the current state- of-the-art model. We notice that there are barely miss-classifications among the non-neutral categories (Angry, Sad, and Happy). Most of the errors, shown in the bold font, correspond to the confusion between a few non-neutral categories and much more neutral category (Others). However, there are several challenges when analyzing emotion in natural conversations. Firstly, unlike vanilla emotion recognition of sentences (Wang and Manning, 2012; Seyeditabari et al., 2018), ERTC requires comprehensively considering the context in the conversation. Secondly, knowledge plays an *The first two authors contributed equally. This work is licensed under a Creative Commons Attribution 4.0 International Licence. Licence details: http:// creativecommons.org/licenses/by/4.0/ 4430 important role in ERTC as speakers often express emotions relying on the context and commonsense knowledge …

Content truncated to 500 words