From machine reading comprehension to dialogue state tracking: Bridging the gap

Shuyang Gao, Sanchit Agarwal, Tagyoung Chung, Di Jin, Dilek Hakkani-Tur

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Dialogue state tracking (DST) is at the heart of task-oriented dialogue systems. However, the scarcity of labeled data is an obstacle to building accurate and robust state tracking systems that work across a variety of domains. Existing approaches generally require some dialogue data with state information and their ability to generalize to unknown domains is limited. In this paper, we propose using machine reading comprehension (RC) in state tracking from two perspectives: model architectures and datasets. We divide the slot types in dialogue state into categorical or extractive to borrow the advantages from both multiple-choice and span-based reading comprehension models. Our method achieves near the current state-of-the-art in joint goal accuracy on MultiWOZ 2.1 given full training data. More importantly, by leveraging machine reading comprehension datasets, our method outperforms the existing approaches by many a large margin in few-shot scenarios when the availability of in-domain data is limited. Lastly, even without any state tracking data, i.e., zero-shot scenario, our proposed approach achieves greater than 90% average slot accuracy in 12 out of 30 slots in MultiWOZ 2.1.

Original languageEnglish (US)
Title of host publicationACL 2020 - NLP for Conversational AI, Proceedings of the 2nd Workshop
PublisherAssociation for Computational Linguistics (ACL)
Pages79-89
Number of pages11
ISBN (Electronic)9781952148088
StatePublished - 2020
Externally publishedYes
Event2nd Workshop on NLP for Conversational AI, NLP4ConvAI 2020 at the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020 - Virtual, Online, United States
Duration: Jul 9 2020 → …

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)0736-587X

Conference

Conference2nd Workshop on NLP for Conversational AI, NLP4ConvAI 2020 at the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020
Country/TerritoryUnited States
CityVirtual, Online
Period7/9/20 → …

ASJC Scopus subject areas

  • Computer Science Applications
  • Linguistics and Language
  • Language and Linguistics

Fingerprint

Dive into the research topics of 'From machine reading comprehension to dialogue state tracking: Bridging the gap'. Together they form a unique fingerprint.

Cite this