Nothing Special   »   [go: up one dir, main page]

Knowledge-grounded Dialog State Tracking

Dian Yu, Mingqiu Wang, Yuan Cao, Laurent El Shafey, Izhak Shafran, Hagen Soltau


Abstract
Knowledge (including structured knowledge such as schema and ontology and unstructured knowledge such as web corpus) is a critical part of dialog understanding, especially for unseen tasks and domains. Traditionally, such domain-specific knowledge is encoded implicitly into model parameters for the execution of downstream tasks, which makes training inefficient. In addition , such models are not easily transferable to new tasks with different schemas. In this work, we propose to perform dialog state tracking grounded on knowledge encoded externally. We query relevant knowledge of various forms based on the dialog context where such information can grounds the prediction of dialog states. We demonstrate superior performance of our proposed method over strong baselines, especially in the few-shot learning setting.
Anthology ID:
2022.findings-emnlp.250
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3428–3435
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.250
DOI:
10.18653/v1/2022.findings-emnlp.250
Bibkey:
Cite (ACL):
Dian Yu, Mingqiu Wang, Yuan Cao, Laurent El Shafey, Izhak Shafran, and Hagen Soltau. 2022. Knowledge-grounded Dialog State Tracking. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 3428–3435, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Knowledge-grounded Dialog State Tracking (Yu et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.250.pdf