CMR improves multi-party response generation by contrastively learning speaker styles in a first stage and jointly training response generation with contrastive objectives in a second stage.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Advancing Multi-Party Dialogue Framework with Speaker-ware Contrastive Learning
CMR improves multi-party response generation by contrastively learning speaker styles in a first stage and jointly training response generation with contrastive objectives in a second stage.