DRCR improves multi-party dialogue generation by rewriting context with discourse coherence and response-guided preference data plus dynamic self-evolution learning between rewriter and responder.
Multi- party dialogues frequently contain implicit ad- dressees and pronouns whose antecedents span across utterances from different speakers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Discourse Coherence and Response-Guided Context Rewriting for Multi-Party Dialogue Generation
DRCR improves multi-party dialogue generation by rewriting context with discourse coherence and response-guided preference data plus dynamic self-evolution learning between rewriter and responder.