CorefDiffs: Co-referential and Differential Knowledge Flow in Document Grounded Conversations

Lin Xu, Qixian Zhou, Jinlan Fu, Min-Yen Kan, See-Kiong Ng


Abstract
Knowledge-grounded dialog systems need to incorporate smooth transitions among knowledge selected for generating responses, to ensure that dialog flows naturally. For document-grounded dialog systems, the inter- and intra-document knowledge relations can be used to model such conversational flows. We develop a novel Multi-Document Co-Referential Graph (Coref-MDG) to effectively capture the inter-document relationships based on commonsense and similarity and the intra-document co-referential structures of knowledge segments within the grounding documents. We propose CorefDiffs, a Co-referential and Differential flow management method, to linearize the static Coref-MDG into conversational sequence logic. CorefDiffs performs knowledge selection by accounting for contextual graph structures and the knowledge difference sequences. CorefDiffs significantly outperforms the state-of-the-art by 9.5%, 7.4% and 8.2% on three public benchmarks. This demonstrates that the effective modeling of co-reference and knowledge difference for dialog flows are critical for transitions in document-grounded conversation.
Anthology ID:
2022.coling-1.38
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:
471–484
Language:
URL:
https://aclanthology.org/2022.coling-1.38
DOI:
Bibkey:
Cite (ACL):
Lin Xu, Qixian Zhou, Jinlan Fu, Min-Yen Kan, and See-Kiong Ng. 2022. CorefDiffs: Co-referential and Differential Knowledge Flow in Document Grounded Conversations. In Proceedings of the 29th International Conference on Computational Linguistics, pages 471–484, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
CorefDiffs: Co-referential and Differential Knowledge Flow in Document Grounded Conversations (Xu et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.38.pdf
Data
Holl-EMultiDoc2Dial