Grounding Description-Driven Dialogue State Trackers with Knowledge-Seeking Turns

Alexandru Coca, Bo-Hsiang Tseng, Jinghong Chen, Weizhe Lin, Weixuan Zhang, Tisha Anders, Bill Byrne


Abstract
Schema-guided dialogue state trackers can generalise to new domains without further training, yet they are sensitive to the writing style of the schemata. Augmenting the training set with human or synthetic schema paraphrases improves the model robustness to these variations but can be either costly or difficult to control. We propose to circumvent these issues by grounding the state tracking model in knowledge-seeking turns collected from the dialogue corpus as well as the schema. Including these turns in prompts during finetuning and inference leads to marked improvements in model robustness, as demonstrated by large average joint goal accuracy and schema sensitivity improvements on SGD and SGD-X.
Anthology ID:
2023.sigdial-1.42
Volume:
Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
September
Year:
2023
Address:
Prague, Czechia
Editors:
Svetlana Stoyanchev, Shafiq Joty, David Schlangen, Ondrej Dusek, Casey Kennington, Malihe Alikhani
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
444–456
Language:
URL:
https://aclanthology.org/2023.sigdial-1.42
DOI:
10.18653/v1/2023.sigdial-1.42
Bibkey:
Cite (ACL):
Alexandru Coca, Bo-Hsiang Tseng, Jinghong Chen, Weizhe Lin, Weixuan Zhang, Tisha Anders, and Bill Byrne. 2023. Grounding Description-Driven Dialogue State Trackers with Knowledge-Seeking Turns. In Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 444–456, Prague, Czechia. Association for Computational Linguistics.
Cite (Informal):
Grounding Description-Driven Dialogue State Trackers with Knowledge-Seeking Turns (Coca et al., SIGDIAL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2023.sigdial-1.42.pdf