Litcius/Paper detail

Initiative-Aware Self-Supervised Learning for Knowledge-Grounded Conversations

Chuan Meng, Pengjie Ren, Zhumin Chen, Zhaochun Ren, Tengxiao Xi, Maarten de Rijke

202134 citationsDOIOpen Access PDF

Abstract

In the knowledge-grounded conversation (KGC) task systems aim to produce more informative responses by leveraging external knowledge. KGC includes a vital part, knowledge selection, where conversational agents select the appropriate knowledge to be incorporated in the next response. Mixed initiative is an intrinsic feature of conversations where the user and the system can both take the initiative in suggesting new conversational directions. Knowledge selection can be driven by the user's initiative or by the system's initiative. For the former, the system usually selects knowledge according to the current user utterance that contains new topics or questions posed by the user; for the latter, the system usually selects knowledge according to the previously selected knowledge. No previous study has considered the mixed-initiative characteristics of knowledge selection to improve its performance.

Topics & Concepts

Computer scienceUtteranceSelection (genetic algorithm)ConversationKnowledge managementTask (project management)Knowledge-based systemsHuman–computer interactionArtificial intelligenceEngineeringPsychologyCommunicationSystems engineeringSpeech and dialogue systemsTopic ModelingMulti-Agent Systems and Negotiation
Initiative-Aware Self-Supervised Learning for Knowledge-Grounded Conversations | Litcius