Ye, F;
Manotumruksa, J;
Zhang, Q;
Li, S;
Yilmaz, E;
(2021)
Slot Self-Attentive Dialogue State Tracking.
In:
WWW '21: Proceedings of the Web Conference 2021.
(pp. pp. 1598-1608).
ACM
Preview |
Text
3442381.3449939.pdf - Published Version Download (1MB) | Preview |
Abstract
An indispensable component in task-oriented dialogue systems is the dialogue state tracker, which keeps track of users’ intentions in the course of conversation. The typical approach towards this goal is to fill in multiple pre-defined slots that are essential to complete the task. Although various dialogue state tracking methods have been proposed in recent years, most of them predict the value of each slot separately and fail to consider the correlations among slots. In this paper, we propose a slot self-attention mechanism that can learn the slot correlations automatically. Specifically, a slot-token attention is first utilized to obtain slot-specific features from the dialogue context. Then a stacked slot self-attention is applied on these features to learn the correlations among slots. We conduct comprehensive experiments on two multi-domain task-oriented dialogue datasets, including MultiWOZ 2.0 and MultiWOZ 2.1. The experimental results demonstrate that our approach achieves state-of-the-art performance on both datasets, verifying the necessity and effectiveness of taking slot correlations into consideration.
| Type: | Proceedings paper |
|---|---|
| Title: | Slot Self-Attentive Dialogue State Tracking |
| Event: | WWW '21: The Web Conference 2021, April 19–23, 2021, Ljubljana, Slovenia |
| ISBN-13: | 9781450383127 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1145/3442381.3449939 |
| Publisher version: | https://doi.org/10.1145/3442381.3449939 |
| Language: | English |
| Additional information: | This paper is published under the Creative Commons Attribution 4.0 International (CC-BY 4.0) license (https://creativecommons.org/licenses/by/4.0/). |
| Keywords: | dialogue state tracking, belief tracking, slot self-attention, taskoriented dialogue system |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10139656 |
Archive Staff Only
 |
View Item |
