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
@article{arxiv.2210.02223,
title = {CorefDiffs: Co-referential and Differential Knowledge Flow in Document Grounded Conversations},
author = {Lin Xu and Qixian Zhou and Jinlan Fu and Min-Yen Kan and See-Kiong Ng},
journal= {arXiv preprint arXiv:2210.02223},
year = {2022}
}