Integrating User History into Heterogeneous Graph for Dialogue Act Recognition

Proceedings of the 28th International Conference on Computational Linguistics, pages 4211–4221 Barcelona, Spain (Online), December 8-13, 2020 4211 Integrating User History into Heterogeneous Graph for Dialogue Act Recognition Dong Wang1,2∗, Ziran Li1,2∗, Hai-Tao Zheng1,2† , Ying Shen3† 1Department of Computer Science and Technology, Tsinghua University 2Tsinghua ShenZhen International Graduate School, Tsinghua University 3School of Intelligent Systems Engineering, Sun Yat-Sen University {wangd18,lizr18}@mails.tsinghua.edu.cn zheng.haitao@sz.tsinghua.edu.cn,sheny76@mail.sysu.edu.cn Abstract Dialogue Act Recognition (DAR) is a challenging problem in Natural Language Understanding, which aims to attach Dialogue Act (DA) labels to each utterance in a conversation. However, previous studies cannot fully recognize the specific expressions given by users due to the in- formality and diversity of natural language expressions. To solve this problem, we propose a Heterogeneous User History (HUH) graph convolution network, which utilizes the user’s histor- ical answers grouped by DA labels as additional clues to recognize the DA label of utterances. To handle the noise caused by introducing the user’s historical answers, we design sets of denois- ing mechanisms, including a History Selection process, a Similarity Re-weighting process, and an Edge Re-weighting process. We evaluate the proposed method on two benchmark datasets MSDialog and MRDA. The experimental results verify the effectiveness of integrating user’s historical answers, and show that our proposed model outperforms the state-of-the-art methods. 1 Introduction Dialogue Acts Recognition (DAR) is an important but challenging task in Natural Language Under- standing (NLU), which aims to attach Dialogue Act (DA) labels to each utterance in a conversation and recognize the speaker’s intention. Automatic DAR can be applied to many applications such as question answering, speech recognition and dialogue systems (Higashinaka et al., 2014; Khanpour et al., 2016). In this work, different from recognizing a single DA, we focus on the task of recognizing multiple DA in a multi-party conversation (i.e., a forum). The latter is difficult but is more common in the real world. Figure 1 shows an example of multiple DA recognition in a tech forum. Previous studies have proposed deep learning models, which approach DAR as a multi-classification problem (Ji et al., 2016; Lee and Dernoncourt, 2016) or a sequence labeling problem (Kumar et al., 2018; Chen et al., 2018; Raheja and Tetreault, 2019; Li et al., 2019). Most of these approaches assume that utterances are sequentially organized, ignoring the rich interaction between multiple users in a conversa- tion. To alleviate such a problem, some recent studies exploit graph-structured networks (Ghosal et al., 2019; Hu et al., 2019), which leverage speaker interaction of the interlocutors to model conversational context. However, due to the informality and diversity of natural language expressions, the same inten- tion has a very rich form of expression. In forums where many users participate, it is more common for different users to express their intentions using personalized expressions. When encountering the unobvious intention or uncommon expression pattern, existing deep learning methods that generalize the utterance feature into a low dimensional vector may degrade the performance of DA recognition. Intuitively, the user’s historical expressions extracted according to the DA …

Content truncated to 500 words