Using Semantic Uncertainty to Estimate Transition Relevance in Turn-taking

2026-09-09

AI Summary

研究通过语义不确定性来预测对话中的转换相关点，利用大型语言模型评估当前话语对后续内容的约束程度，以改善自然对话中发言时机的选择。

Abstract

Turn-taking is a fundamental mechanism that governs when interlocutors speak and listen. Although Spoken Dialogue Systems (SDS) exploit a range of linguistic, acoustic, and non-verbal cues, they produce ill-timed responses in unscripted interaction. A central challenge is anticipating Transition Relevance Places (TRPs), or opportunities, not obligations, for a listener to take the floor. Human listeners do not wait for turn endings; as an utterance unfolds, they use expectations about its developing meaning to anticipate TRPs and decide whether to take the floor. We examine whether these evolving expectations can be modeled through semantic uncertainty -- an LLM-derived measure of how strongly a turn so far constrains what may plausibly come next. To do so, we sample possible continuations of an ongoing turn and use changes in semantic dispersion to identify TRPs within turns. We evaluate this account on a dataset with TRP labels derived from real-time listener responses, rather than retrospective annotation. Our approach substantially outperforms prompt-based and fine-tuned text-only baselines, providing empirical support for the view that evolving semantic constraints inform perceived turn-taking opportunities in unscripted interaction.

Problem

• Turn-taking
• Transition Relevance Places
• Semantic Uncertainty
• Spoken Dialogue Systems
• Unscripted Interaction

Innovation

• Semantic Uncertainty
• Transition Relevance Places (TRPs)
• Unscripted Interaction
• Large Language Models (LLMs)