Multi-Domain Dialogue Acts and Response Co-Generation

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7125–7134 July 5 - 10, 2020. c⃝2020 Association for Computational Linguistics 7125 Multi-Domain Dialogue Acts and Response Co-Generation Kai Wang1, Junfeng Tian2, Rui Wang2, Xiaojun Quan1∗, Jianxing Yu1 1School of Data and Computer Science, Sun Yat-sen University, China 2Alibaba Group, China wangk73@mail2.sysu.edu.cn, {quanxj3, yujx26}@mail.sysu.edu.cn {tjf141457, masi.wr}@alibaba-inc.com Abstract Generating fluent and informative responses is of critical importance for task-oriented di- alogue systems. Existing pipeline approaches generally predict multiple dialogue acts first and use them to assist response generation. There are at least two shortcomings with such approaches. First, the inherent structures of multi-domain dialogue acts are neglected. Sec- ond, the semantic associations between acts and responses are not taken into account for response generation. To address these issues, we propose a neural co-generation model that generates dialogue acts and responses concur- rently. Unlike those pipeline approaches, our act generation module preserves the semantic structures of multi-domain dialogue acts and our response generation module dynamically attends to different acts as needed. We train the two modules jointly using an uncertainty loss to adjust their task weights adaptively. Exten- sive experiments are conducted on the large- scale MultiWOZ dataset and the results show that our model achieves very favorable im- provement over several state-of-the-art models in both automatic and human evaluations. 1 Introduction Task-oriented dialogue systems aim to facilitate people with such services as hotel reservation and ticket booking through natural language conversa- tions. Recent years have seen a rapid proliferation of interests in this task from both academia and industry (Bordes et al., 2017; Budzianowski et al., 2018; Wu et al., 2019). A standard architecture of these systems generally decomposes this task into several subtasks, including natural language understanding (Gupta et al., 2018), dialogue state tracking (Zhong et al., 2018) and natural language ∗Xiaojun Quan is the corresponding author of this paper. Most of this work was done when Kai Wang was working as an intern at Alibaba DAMO Academy. I'm looking for an expensive Indian restaurant. That sounds great! Can I get their address and phone number? Belief State: restaurant-{food=Indian, name=Curry Garden} External Database User Dialogue Example System I have 5. How about Curry Garden? It serves Indian food and is in the expensive price range. Sure! Their address is 106 regent street city centre1 and their phone number is 012233023302. Would you like me to book a table3 for you? Dialog Acts: 1restaurant-inform-address 2restaurant-inform-phone 3book-inform-none Predict ID Name Food Address ... 2 Curry Garden Indian 106 ... centre ... Figure 1: An example of dialogue from the MultiWOZ dataset, where the dialogue system needs to generate a natural language response according to current belief state and related database records. generation (Su et al., 2018). They can be modeled separately and combined into a pipeline system. Figure 1 shows a dialogue example, from which we can notice that the natural language generation subtask can be further divided into dialogue act prediction and response generation (Chen et al., 2019; …

Content truncated to 500 words