| Title | More is Better: Enhancing Open-Domain Dialogue Generation via Multi-Source Heterogeneous Knowledge |
| Authors | Wu, Sixing Li, Ying Wang, Minghui Zhang, Dawei Zhou, Yang Wu, Zhonghai |
| Affiliation | Peking Univ, Sch Elect Engn & Comp Sci, Beijing, Peoples R China Peking Univ, Sch Software & Microelect, Beijing, Peoples R China Aubum Univ, Auburn, AL USA 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 | 2021 |
| Publisher | 2021 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2021) |
| Abstract | Despite achieving remarkable performance, previous knowledge-enhanced works usually only use a single-source homogeneous knowledge base of limited knowledge coverage. Thus, they often degenerate into traditional methods because not all dialogues can be linked with knowledge entries. This paper proposes a novel dialogue generation model, MSKE-Dialog, to solve this issue with three unique advantages: (1) Rather than only one, MSKE-Dialog can simultaneously leverage multiple heterogeneous knowledge sources (it includes but is not limited to commonsense knowledge facts, text knowledge, infobox knowledge) to improve the knowledge coverage; (2) To avoid the topic conflict among the context and different knowledge sources, we propose a Multi-Reference Selection to better select context/knowledge; (3) We propose a Multi-Reference Generation to generate informative responses by referring to multiple generation references at the same time. Extensive evaluations on a Chinese dataset show the superior performance of this work against various state-of-the-art approaches. To our best knowledge, this work is the first to use the multi-source heterogeneous knowledge in the open-domain knowledge-enhanced dialogue generation. |
| URI | http://hdl.handle.net/20.500.11897/654800 |
| ISBN | 978-1-955917-09-4 |
| Indexed | CPCI-SSH(ISSHP) CPCI-S(ISTP) |
| Appears in Collections: | 信息科学技术学院 软件与微电子学院 高可信软件技术教育部重点实验室 |
