Enhancing Knowledge Selection for Grounded Dialogues via Document Semantic Graphs
Providing conversation models with background knowledge has been shown to make open-domain dialogues more informative and engaging. Existing models treat knowledge selection as a sentence ranking or classification problem where each sentence is handled individually, ignoring the internal semantic connection between sentences. In this work, we propose to automatically convert the background knowledge documents into document semantic graphs and then perform knowledge selection over such graphs. Our document semantic graphs preserve sentence-level information through the use of sentence nodes and provide concept connections between sentences. We apply multi-task learning to perform sentence-level knowledge selection and concept-level knowledge selection, showing that it improves sentence-level selection. Our experiments show that our semantic graph-based knowledge selection improves over sentence selection baselines for both the knowledge selection task and the end-to-end response generation task on HollE and improves generalization on unseen topics in WoW.
Code (0)
등록된 구현이 없습니다.
Tasks
Multi-Task LearningResponse GenerationSentenceSimilar Papers 제목 키워드 기반
Enhanced Knowledge Selection for Grounded Dialogues via Document Semantic Graphs
Providing conversation models with background knowledge has been shown to make open-domain dialogues more informative and engaging. Existing models treat knowledge selection as a sentence ranking or classification proble…
Multi-Task LearningResponse GenerationSentenceA Pre-training Strategy for Zero-Resource Response Selection in Knowledge-Grounded Conversations
Recently, many studies are emerging towards building a retrieval-based dialogue system that is able to effectively leverage background knowledge (e.g., documents) when conversing with humans. However, it is non-trivial t…
Language ModellingRetrievalTask 2GraphDiffs: Graph Modeling with Differential Sequence for Document-Grounded Conversation
Knowledge grounded dialogue systems need to incorporate natural transitions between knowledge for dialogue to flow smoothly. Current systems not only lack good structured representations for knowledge that span multiple …
Task2Dial: A Novel Task and Dataset for Commonsense-enhanced Task-based Dialogue Grounded in Documents
This paper proposes a novel task on commonsense-enhanced task-based dialogue grounded in documents and describes the Task2Dial dataset, a novel dataset of document-grounded task-based dialogues, where an Information Give…
Low-Resource Knowledge-Grounded Dialogue Generation
Responding with knowledge has been recognized as an important capability for an intelligent conversational agent. Yet knowledge-grounded dialogues, as training data for learning such a response generation model, are diff…
DecoderDialogue GenerationResponse Generation