Title | KSAM: Infusing Multi-Source Knowledge into Dialogue Generation via Knowledge Source Aware Multi-Head Decoding |
Authors | Wu, Sixing Li, Ying Zhang, Dawei Wu, Zhonghai |
Affiliation | Peking Univ, Sch Comp Sci, Beijing, Peoples R China Peking Univ, Natl Res Ctr Software Engn, Beijing, Peoples R China Peking Univ, Key Lab High Confidence Software Technol MOE, Beijing, Peoples R China |
Issue Date | 2022 |
Publisher | FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022) |
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. |
URI | http://hdl.handle.net/20.500.11897/654036 |
ISBN | 978-1-955917-25-4 |
Indexed | CPCI-SSH(ISSHP) CPCI-S(ISTP) |
Appears in Collections: | 信息科学技术学院 高可信软件技术教育部重点实验室 |