Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory
This addresses the issue of uninformative dialogue responses for users in conversational AI, though it is incremental as it builds on existing retrieval-based methods.
The paper tackles the problem of generic and dull responses in dialogue generation by proposing a skeleton-then-response framework that uses retrieval memory to guide generation, resulting in significantly improved diversity and informativeness of responses.
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.