Learning to Express in Knowledge-Grounded Conversation
This work addresses the challenge of generating more engaging and personalized responses in dialogue systems, though it is incremental by focusing on expression style rather than core knowledge grounding.
The paper tackles the problem of varying expression styles for the same knowledge in knowledge-grounded conversations by introducing a model that learns to control response structure and content style, achieving results that generate responses in desired styles as evaluated on benchmarks.
Grounding dialogue generation by extra knowledge has shown great potentials towards building a system capable of replying with knowledgeable and engaging responses. Existing studies focus on how to synthesize a response with proper knowledge, yet neglect that the same knowledge could be expressed differently by speakers even under the same context. In this work, we mainly consider two aspects of knowledge expression, namely the structure of the response and style of the content in each part. We therefore introduce two sequential latent variables to represent the structure and the content style respectively. We propose a segmentation-based generation model and optimize the model by a variational approach to discover the underlying pattern of knowledge expression in a response. Evaluation results on two benchmarks indicate that our model can learn the structure style defined by a few examples and generate responses in desired content style.