Dialogue Summaries as Dialogue States (DS2), Template-Guided Summarization for Few-shot Dialogue State Tracking

Jamin Shin, Hangyeol Yu, Hyeongdon Moon, Andrea Madotto, Juneyoung Park


Abstract
Annotating task-oriented dialogues is notorious for the expensive and difficult data collection process. Few-shot dialogue state tracking (DST) is a realistic solution to this problem. In this paper, we hypothesize that dialogue summaries are essentially unstructured dialogue states; hence, we propose to reformulate dialogue state tracking as a dialogue summarization problem. To elaborate, we train a text-to-text language model with synthetic template-based dialogue summaries, generated by a set of rules from the dialogue states. Then, the dialogue states can be recovered by inversely applying the summary generation rules. We empirically show that our method DS2 outperforms previous works on few-shot DST in MultiWoZ 2.0 and 2.1, in both cross-domain and multi-domain settings. Our method also exhibits vast speedup during both training and inference as it can generate all states at once.Finally, based on our analysis, we discover that the naturalness of the summary templates plays a key role for successful training.
Anthology ID:
2022.findings-acl.302
Volume:
Findings of the Association for Computational Linguistics: ACL 2022
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3824–3846
Language:
URL:
https://aclanthology.org/2022.findings-acl.302
DOI:
10.18653/v1/2022.findings-acl.302
Bibkey:
Cite (ACL):
Jamin Shin, Hangyeol Yu, Hyeongdon Moon, Andrea Madotto, and Juneyoung Park. 2022. Dialogue Summaries as Dialogue States (DS2), Template-Guided Summarization for Few-shot Dialogue State Tracking. In Findings of the Association for Computational Linguistics: ACL 2022, pages 3824–3846, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Dialogue Summaries as Dialogue States (DS2), Template-Guided Summarization for Few-shot Dialogue State Tracking (Shin et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-acl.302.pdf
Software:
 2022.findings-acl.302.software.zip
Video:
 https://aclanthology.org/2022.findings-acl.302.mp4
Code
 jshin49/ds2
Data
MultiWOZSAMSum Corpus