UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Dynamic Schema Graph Fusion Network for Multi-Domain Dialogue State Tracking

Feng, Yue; Lipani, Aldo; Ye, Fanghua; Zhang, Qiang; Yilmaz, Emine; (2022) Dynamic Schema Graph Fusion Network for Multi-Domain Dialogue State Tracking. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). (pp. pp. 115-126). ACL Anthology: Dublin, Ireland. Green open access

[thumbnail of Lipani_2022.acl-long.10.pdf]
Preview
Text
Lipani_2022.acl-long.10.pdf

Download (583kB) | Preview

Abstract

Dialogue State Tracking (DST) aims to keep track of users’ intentions during the course of a conversation. In DST, modelling the relations among domains and slots is still an under-studied problem. Existing approaches that have considered such relations generally fall short in: (1) fusing prior slot-domain membership relations and dialogue-aware dynamic slot relations explicitly, and (2) generalizing to unseen domains. To address these issues, we propose a novel Dynamic Schema Graph Fusion Network (DSGFNet), which generates a dynamic schema graph to explicitly fuse the prior slot-domain membership relations and dialogue-aware dynamic slot relations. It also uses the schemata to facilitate knowledge transfer to new domains. DSGFNet consists of a dialogue utterance encoder, a schema graph encoder, a dialogue-aware schema graph evolving network, and a schema graph enhanced dialogue state decoder. Empirical results on benchmark datasets (i.e., SGD, MultiWOZ2.1, and MultiWOZ2.2), show that DSGFNet outperforms existing methods.

Type: Proceedings paper
Title: Dynamic Schema Graph Fusion Network for Multi-Domain Dialogue State Tracking
Event: ACL 2022: 60th Annual Meeting of the Association for Computational Linguistics
Open access status: An open access version is available from UCL Discovery
DOI: 10.18653/v1/2022.acl-long.10
Publisher version: http://dx.doi.org/10.18653/v1/2022.acl-long.10
Language: English
Additional information: ACL materials are Copyright © 1963–2022 ACL; other materials are copyrighted by their respective copyright holders. Materials prior to 2016 here are licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 International License. Permission is granted to make copies for the purposes of teaching and research. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License.
UCL classification: 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 Civil, Environ and Geomatic Eng
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL
URI: https://discovery.ucl.ac.uk/id/eprint/10146908
Downloads since deposit
Loading...
24Downloads
Download activity - last month
Loading...
Download activity - last 12 months
Loading...
Downloads by country - last 12 months
1.United States
2
2.Germany
2
3.Russian Federation
1
4.Japan
1
5.Poland
1

Archive Staff Only

View Item View Item