Few Shot Dialogue State Tracking using Meta-learning

Saket Dingliwal, Shuyang Gao, Sanchit Agarwal, Chien-Wei Lin, Tagyoung Chung, Dilek Hakkani-Tur


Abstract
Dialogue State Tracking (DST) forms a core component of automated chatbot based systems designed for specific goals like hotel, taxi reservation, tourist information etc. With the increasing need to deploy such systems in new domains, solving the problem of zero/few-shot DST has become necessary. There has been a rising trend for learning to transfer knowledge from resource-rich domains to unknown domains with minimal need for additional data. In this work, we explore the merits of meta-learning algorithms for this transfer and hence, propose a meta-learner D-REPTILE specific to the DST problem. With extensive experimentation, we provide clear evidence of benefits over conventional approaches across different domains, methods, base models and datasets with significant (5-25%) improvement over the baseline in a low-data setting. Our proposed meta-learner is agnostic of the underlying model and hence any existing state-of-the-art DST system can improve its performance on unknown domains using our training strategy.
Anthology ID:
2021.eacl-main.148
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Editors:
Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1730–1739
Language:
URL:
https://aclanthology.org/2021.eacl-main.148
DOI:
10.18653/v1/2021.eacl-main.148
Bibkey:
Cite (ACL):
Saket Dingliwal, Shuyang Gao, Sanchit Agarwal, Chien-Wei Lin, Tagyoung Chung, and Dilek Hakkani-Tur. 2021. Few Shot Dialogue State Tracking using Meta-learning. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1730–1739, Online. Association for Computational Linguistics.
Cite (Informal):
Few Shot Dialogue State Tracking using Meta-learning (Dingliwal et al., EACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-main.148.pdf
Video:
 https://aclanthology.org/2021.eacl-main.148.mp4
Code
 saketdingliwal/Few-Shot-DST
Data
MultiWOZ