Enhancing Knowledge Selection for Grounded Dialogues via Document Semantic Graphs

Sha Li, Mahdi Namazifar, Di Jin, Mohit Bansal, Heng Ji, Yang Liu, Dilek Hakkani-Tur


Abstract
Providing conversation models with background knowledge has been shown to make open-domain dialogues more informative and engaging. Existing models treat knowledge selection as a sentence ranking or classification problem where each sentence is handled individually, ignoring the internal semantic connection between sentences. In this work, we propose to automatically convert the background knowledge documents into document semantic graphs and then perform knowledge selection over such graphs. Our document semantic graphs preserve sentence-level information through the use of sentence nodes and provide concept connections between sentences. We apply multi-task learning to perform sentence-level knowledge selection and concept-level knowledge selection, showing that it improves sentence-level selection. Our experiments show that our semantic graph-based knowledge selection improves over sentence selection baselines for both the knowledge selection task and the end-to-end response generation task on HollE and improves generalization on unseen topics in WoW.
Anthology ID:
2022.naacl-main.202
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2810–2823
Language:
URL:
https://aclanthology.org/2022.naacl-main.202
DOI:
10.18653/v1/2022.naacl-main.202
Bibkey:
Cite (ACL):
Sha Li, Mahdi Namazifar, Di Jin, Mohit Bansal, Heng Ji, Yang Liu, and Dilek Hakkani-Tur. 2022. Enhancing Knowledge Selection for Grounded Dialogues via Document Semantic Graphs. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2810–2823, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Enhancing Knowledge Selection for Grounded Dialogues via Document Semantic Graphs (Li et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.202.pdf
Data
Holl-EWizard of Wikipedia