CorefDiffs: Co-referential and Differential Knowledge Flow in Document Grounded Conversations
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. W...
Gespeichert in:
Hauptverfasser: | , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | 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 |
---|---|
DOI: | 10.48550/arxiv.2210.02223 |