Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 808–819 Florence, Italy, July 28 - August 2, 2019. c⃝2019 Association for Computational Linguistics 808 Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems Chien-Sheng Wu†∗, Andrea Madotto†, Ehsan Hosseini-Asl‡, Caiming Xiong‡, Richard Socher‡ and Pascale Fung† †The Hong Kong University of Science and Technology ‡Salesforce Research jason.wu@connect.ust.hk Abstract Over-dependence on domain ontology and lack of knowledge sharing across domains are two practical and yet less studied problems of dialogue state tracking. Existing approaches generally fall short in tracking unknown slot values during inference and often have diffi- culties in adapting to new domains. In this paper, we propose a TRAnsferable Dialogue statE generator (TRADE) that generates di- alogue states from utterances using a copy mechanism, facilitating knowledge transfer when predicting (domain, slot, value) triplets not encountered during training. Our model is composed of an utterance encoder, a slot gate, and a state generator, which are shared across domains. Empirical results demonstrate that TRADE achieves state-of-the-art joint goal ac- curacy of 48.62% for the five domains of Mul- tiWOZ, a human-human dialogue dataset. In addition, we show its transferring ability by simulating zero-shot and few-shot dialogue state tracking for unseen domains. TRADE achieves 60.58% joint goal accuracy in one of the zero-shot domains, and is able to adapt to few-shot cases without forgetting already trained domains. 1 Introduction Dialogue state tracking (DST) is a core component in task-oriented dialogue systems, such as restau- rant reservation or ticket booking. The goal of DST is to extract user goals/intentions expressed during conversation and to encode them as a com- pact set of dialogue states, i.e., a set of slots and their corresponding values. For example, as shown in Fig. 1, (slot, value) pairs such as (price, cheap) and (area, centre) are extracted from the conver- sation. Accurate DST performance is crucial for ∗Work partially done while the first author was an intern at Salesforce Research. Usr: I am looking for a cheap restaurant in the centre of the city. Sys: There is a cheap chinese restaurant called Dojo Noodle Bar. Usr: Yes please , for 8 people at 18:30 on Thursday. … Usr: I am also looking for some entertainment close to the restaurant. Sys: Is there any type of attraction you would like me to search? Usr: Why do not you try an architectural attraction. Sys: All Saints Church looks good , would you like to head there? … Usr: I also need to book a taxi between the restaurant and the church. Sys: What time would you like the taxi from Dojo Noodle Bar? Usr: 20:30, please. Restaurant: (price, cheap), (area, centre), (people, 8), (time, 18:30), (day, Thursday), (name, Dojo Noodle Bar) Multi-Domain Dialogue State Tracking Attraction: (type, architecture), (area, centre) Taxi: (leaveAt, 20:30), (destination, All Saints Church), (departure, Dojo Noodle Bar) Hotel: Train: Dialogue History Figure 1: An example of multi-domain dialogue state tracking in a conversation. The solid arrows on the left are the single-turn mapping, …

Content truncated to 500 words