Skip to content
conftrace_
2026 EMNLP EMNLP 2026

Leveraging Turn-taking Dynamics for Intent Recognition in Multi-party Conversations

AbstractWe propose a multi-task learning approach for multi-party dialogue intent recognition that leverages an auxiliary task that models turn-taking dynamics. Specifically, we introduce turn-transition entropy, a self-supervised target computed from the sequence of speaker transitions, which quantifies the predictability of interaction patterns. Experiments on multiple pre-trained models demonstrate that incorporating this auxiliary task improves intent recognition performance, outperforming existing approaches which ignore multi-party interaction dynamics. We find that our proposed continuous target can be learned as a single-task objective, suggesting that it is an actual signal carrying useful information.

More from EMNLP 2026

All EMNLP 2026 papers →