Fact-based Dialogue Generation with Convergent and Divergent Decoding
This addresses the limitation of previous fact-based dialogue systems that passively converse and struggle with diversity, offering a solution for applications requiring more engaging and informative human-like interactions.
The paper tackles the problem of generating diverse and proactive responses in fact-based dialogue systems by introducing convergent and divergent decoding, which allows the model to either stay on the current topic or introduce new ones. Results on the DSTC7 dataset show significant outperformance over state-of-the-art baselines in generating appropriate, informative, and diverse responses.
Fact-based dialogue generation is a task of generating a human-like response based on both dialogue context and factual texts. Various methods were proposed to focus on generating informative words that contain facts effectively. However, previous works implicitly assume a topic to be kept on a dialogue and usually converse passively, therefore the systems have a difficulty to generate diverse responses that provide meaningful information proactively. This paper proposes an end-to-end fact-based dialogue system augmented with the ability of convergent and divergent thinking over both context and facts, which can converse about the current topic or introduce a new topic. Specifically, our model incorporates a novel convergent and divergent decoding that can generate informative and diverse responses considering not only given inputs (context and facts) but also inputs-related topics. Both automatic and human evaluation results on DSTC7 dataset show that our model significantly outperforms state-of-the-art baselines, indicating that our model can generate more appropriate, informative, and diverse responses.