Schema Encoding for Transferable Dialogue State Tracking

Hyunmin Jeon, Gary Geunbae Lee


Abstract
Dialogue state tracking (DST) is an essential sub-task for task-oriented dialogue systems. Recent work has focused on deep neural models for DST. However, the neural models require a large dataset for training. Furthermore, applying them to another domain needs a new dataset because the neural models are generally trained to imitate the given dataset. In this paper, we propose Schema Encoding for Transferable Dialogue State Tracking (SET-DST), which is a neural DST method for effective transfer to new domains. Transferable DST could assist developments of dialogue systems even with few dataset on target domains. We use a schema encoder not just to imitate the dataset but to comprehend the schema of the dataset. We aim to transfer the model to new domains by encoding new schemas and using them for DST on multi-domain settings. As a result, SET-DST improved the joint accuracy by 1.46 points on MultiWOZ 2.1.
Anthology ID:
2022.coling-1.28
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
355–366
Language:
URL:
https://aclanthology.org/2022.coling-1.28
DOI:
Bibkey:
Cite (ACL):
Hyunmin Jeon and Gary Geunbae Lee. 2022. Schema Encoding for Transferable Dialogue State Tracking. In Proceedings of the 29th International Conference on Computational Linguistics, pages 355–366, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Schema Encoding for Transferable Dialogue State Tracking (Jeon & Lee, COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.28.pdf
Data
SGD