KSAM: Infusing Multi-Source Knowledge into Dialogue Generation via Knowledge Source Aware Multi-Head Decoding

Sixing Wu, Ying Li, Dawei Zhang, Zhonghai Wu

Abstract
Knowledge-enhanced methods have bridged the gap between human beings and machines in generating dialogue responses. However, most previous works solely seek knowledge from a single source, and thus they often fail to obtain available knowledge because of the insufficient coverage of a single knowledge source. To this end, infusing knowledge from multiple sources becomes a trend. This paper proposes a novel approach Knowledge Source Aware Multi-Head Decoding, KSAM, to infuse multi-source knowledge into dialogue generation more efficiently. Rather than following the traditional single decoder paradigm, KSAM uses multiple independent source-aware decoder heads to alleviate three challenging problems in infusing multi-source knowledge, namely, the diversity among different knowledge sources, the indefinite knowledge alignment issue, and the insufficient flexibility/scalability in knowledge usage. Experiments on a Chinese multi-source knowledge-aligned dataset demonstrate the superior performance of KSAM against various competitive approaches.
Anthology ID:
2022.findings-acl.30
Volume:
Findings of the Association for Computational Linguistics: ACL 2022
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
353–363
Language:
URL:
https://aclanthology.org/2022.findings-acl.30
DOI:
10.18653/v1/2022.findings-acl.30
Bibkey:
Cite (ACL):
Sixing Wu, Ying Li, Dawei Zhang, and Zhonghai Wu. 2022. KSAM: Infusing Multi-Source Knowledge into Dialogue Generation via Knowledge Source Aware Multi-Head Decoding. In Findings of the Association for Computational Linguistics: ACL 2022, pages 353–363, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
KSAM: Infusing Multi-Source Knowledge into Dialogue Generation via Knowledge Source Aware Multi-Head Decoding (Wu et al., Findings 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2022.findings-acl.30.pdf
PDF Search