Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory
For dialogue response generation, traditional generative models generate responses solely from input queries. Such models rely on insufficient information for generating a specific response since a certain query could be answered in multiple ways. Consequentially, those models tend to output generic and dull responses, impeding the generation of informative utterances. Recently, researchers have attempted to fill the information gap by exploiting information retrieval techniques. When generating a response for a current query, similar dialogues retrieved from the entire training data are considered as an additional knowledge source. While this may harvest massive information, the generative models could be overwhelmed, leading to undesirable performance. In this paper, we propose a new framework which exploits retrieval results via a skeleton-then-response paradigm. At first, a skeleton is generated by revising the retrieved responses. Then, a novel generative model uses both the generated skeleton and the original query for response generation. Experimental results show that our approaches significantly improve the diversity and informativeness of the generated responses.
Code (1)
Tasks
Dialogue GenerationDiversityInformation RetrievalInformativenessResponse GenerationRetrievalSimilar Papers 제목 키워드 기반
Retrieval-guided Dialogue Response Generation via a Matching-to-Generation Framework
End-to-end sequence generation is a popular technique for developing open domain dialogue systems, though they suffer from the \textit{safe response problem}. Researchers have attempted to tackle this problem by incorpor…
Response GenerationRetrievalHexa: Self-Improving for Knowledge-Grounded Dialogue System
A common practice in knowledge-grounded dialogue generation is to explicitly utilize intermediate steps (e.g., web-search, memory retrieval) with modular approaches. However, data for such steps are often inaccessible co…
Dialogue GenerationDiversityRetrievalTarget-Guided Dialogue Response Generation Using Commonsense and Data Augmentation
Target-guided response generation enables dialogue systems to smoothly transition a conversation from a dialogue context toward a target sentence. Such control is useful for designing dialogue systems that direct a conve…
Data AugmentationResponse GenerationSentenceTarget-Guided Dialogue Response Generation Using Commonsense and Data Augmentation
Targeted-guided response generation enables dialogue systems to smoothly guide a conversation from a dialogue context toward a target sentence. Such control is useful for designing dialogue systems that direct a conversa…
Data AugmentationResponse GenerationSentenceConsistentChat: Building Skeleton-Guided Consistent Dialogues for Large Language Models from Scratch
Current instruction data synthesis methods primarily focus on single-turn instructions and often neglect cross-turn coherence, resulting in context drift and reduced task completion rates in extended conversations. To ad…
Dialogue Generation