CorefDiffs: Co-referential and Differential Knowledge Flow in Document Grounded Conversations
This addresses the challenge of smooth knowledge transitions in dialog systems for applications like chatbots, though it appears incremental as it builds on existing graph-based methods.
The paper tackled the problem of ensuring natural conversational flows in document-grounded dialog systems by modeling inter- and intra-document knowledge relations, resulting in CorefDiffs outperforming state-of-the-art methods by 9.5%, 7.4%, and 8.2% on three benchmarks.
Knowledge-grounded dialog systems need to incorporate smooth transitions among knowledge selected for generating responses, to ensure that dialog flows naturally. For document-grounded dialog systems, the inter- and intra-document knowledge relations can be used to model such conversational flows. We develop a novel Multi-Document Co-Referential Graph (Coref-MDG) to effectively capture the inter-document relationships based on commonsense and similarity and the intra-document co-referential structures of knowledge segments within the grounding documents. We propose CorefDiffs, a Co-referential and Differential flow management method, to linearize the static Coref-MDG into conversational sequence logic. CorefDiffs performs knowledge selection by accounting for contextual graph structures and the knowledge difference sequences. CorefDiffs significantly outperforms the state-of-the-art by 9.5\%, 7.4\%, and 8.2\% on three public benchmarks. This demonstrates that the effective modeling of co-reference and knowledge difference for dialog flows are critical for transitions in document-grounded conversation