Open-Domain Dialogue Generation Grounded with Dynamic Multi-form Knowledge Fusion

Xu, Feifei; Zhou, Shanlin; Ma, Yunpu; Wang, Xinpeng; Zhang, Wenkai und Li, Zhisong (2022): Open-Domain Dialogue Generation Grounded with Dynamic Multi-form Knowledge Fusion. 27th International Conference on Database Systems for Advanced Applications (DASFAA 2022), Hyderabad, India, April 11–14, 2022. Bhattacharya, Arnab (Hrsg.): In: Database Systems for Advanced Applications. 27th International Conference, DASFAA 2022 Virtual Event, April 11–14, 2022 Proceedings, Part III, Lecture Notes in Computer Science Bd. 13247 Cham, Switzerland: Springer. S. 101-116

Abstract

Open-domain multi-turn conversations normally face the challenges of how to enrich and expand the content of the conversation. Recently, many approaches based on external knowledge are proposed to generate rich semantic and information conversation. Two types of knowledge have been studied for knowledge-aware open-domain dialogue generation: structured triples from knowledge graphs and unstructured texts from documents. To take both advantages of abundant unstructured latent knowledge in the documents and the information expansion capabilities of the structured knowledge graph, this paper presents a new dialogue generation model, Dynamic Multi-form Knowledge Fusion based Open-domain Chatting Machine (DMKCM). In particular, DMKCM applies an indexed text (a virtual Knowledge Base) to locate relevant documents as 1st hop and then expands the content of the dialogue and its 1st hop using a commonsense knowledge graph to get apposite triples as 2nd hop. To merge these two forms of knowledge into the dialogue effectively, we design a dynamic virtual knowledge selector and a controller that help to enrich and expand knowledge space. Moreover, DMKCM adopts a novel dynamic knowledge memory module that effectively uses historical reasoning knowledge to generate better responses. Experimental results indicate the effectiveness of our method in terms of dialogue coherence and informativeness.

• Dokumententyp: Konferenzbeitrag (Paper)
• Fakultät: Mathematik, Informatik und Statistik > Informatik
• Themengebiete: 000 Informatik, Informationswissenschaft, allgemeine Werke > 004 Informatik
• ISSN: 0302-9743
• Ort: Cham, Switzerland
• Bemerkung: ISBN 978-3-031-00128-4. ISBN 978-3-031-00129-1 (eBook)
• Sprache: Englisch