Dialogue state tracking with incremental reasoning
Liao, Lizi Long, Le Hong Ma, Yunshan Lei, Wenqiang Chua, Tat-Seng
Long, Le Hong
Citations
Altmetric:
Alternative Title
Abstract
Tracking dialogue states to better interpret user goals and feed downstream policy learning is a bottleneck in dialogue management. Common practice has been to treat it as a problem of classifying dialogue content into a set of pre-defined slot-value pairs, or generating values for different slots given the dialogue history. Both have limitations on considering dependencies that occur on dialogues, and are lacking of reasoning capabilities. This paper proposes to track dialogue states gradually with reasoning over dialogue turns with the help of the back-end data. Empirical results demonstrate that our method outperforms the state-of-the-art methods in terms of joint belief accuracy for MultiWOZ 2.1, a large-scale human–human dialogue dataset across multiple domains. © 2021, MIT Press Journals. All rights reserved.
Keywords
Source Title
Transactions of the Association for Computational Linguistics
Publisher
MIT Press Journals
Series/Report No.
Collections
Rights
Attribution 4.0 International
Date
2021-01-01
DOI
10.1162/tacl_a_00384
Type
Article