Cluster-based Beam Search for Pointer-Generator Chatbot Grounded by Knowledge

•Proposed an end-to-end model to incorporate conversation history and facts with copy mechanism.•Proposed a new beam search strategy to improve response diversity driven by K-means clustering.•Proposed a language modeling approach to filter out safe responses.•Evaluated on DSTC7 and achieved the first place.•Post-evaluated system with word-piece tokenization.