Enhancing Knowledge Selection via Multi-level Document Semantic Graph

Haoran Zhang, Tan Yongmei


Abstract
Knowledge selection is a crucial sub-task of Document Grounded Dialogue System. Existing methods view knowledge selection as a sentence matching or classification. However, those methods can’t capture the semantic relationships within complex document. We propose a flexible method that can construct multi-level document semantic graph from the grounding document automatically and store semantic relationships within the documents effectively. Besides, we also devise an auxiliary task to leverage the graph more efficiently and can help the optimization of knowledge selection task. We conduct extensive experiments on public datasets: WoW(CITATION) and Holl-E(CITATION). And we achieves state-of-the-art result on WoW. Our code has been released at https://github.com/ddf62/multi-level-semantic-document-graph.
Anthology ID:
2024.lrec-main.531
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
5996–6006
Language:
URL:
https://aclanthology.org/2024.lrec-main.531
DOI:
Bibkey:
Cite (ACL):
Haoran Zhang and Tan Yongmei. 2024. Enhancing Knowledge Selection via Multi-level Document Semantic Graph. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 5996–6006, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Enhancing Knowledge Selection via Multi-level Document Semantic Graph (Zhang & Yongmei, LREC-COLING 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.lrec-main.531.pdf