Publication Type

Journal Article

Version

publishedVersion

Publication Date

5-2021

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-theart methods in terms of joint belief accuracy for MultiWOZ 2.1, a large-scale human–human dialogue dataset across multiple domains.

Discipline

Artificial Intelligence and Robotics

Research Areas

Intelligent Systems and Optimization

Publication

Transactions of the Association for Computational Linguistics

Volume

9

First Page

557

Last Page

569

ISSN

2307-387X

Identifier

10.1162/tacl_a_00384

Publisher

Massachusetts Institute of Technology Press

Additional URL

http://doi.org/10.1162/tacl_a_00384

Share

COinS