On the Structure of Address in Multi-Party Dialogue: From Discrete Labels to Continuous Levels

2026-07-17

AI Summary

This work addresses the limitation of modeling addressee in multiparty dialogue as discrete categories, which overlooks its inherent continuous structure. For the first time, we formulate addressee as a continuous latent variable and propose a probabilistic model that infers a continuous addressee hierarchy from multiple human annotations. This model jointly integrates turn-taking patterns, gaze behavior, and response dynamics within a unified framework. Empirical results demonstrate that the continuous addressee representation significantly outperforms conventional discrete-label approaches in predictive fit. Moreover, the analysis reveals a graded structure underlying addressee selection and its tight coupling with nonverbal behaviors, providing strong evidence for the fundamentally continuous nature of addressing in multiparty conversation.

Abstract

In multi-party dialogues between a dialogue system and multiple users, identifying to whom an utterance is addressed is a key challenge. Prior work has typically treated addressee detection as a multi-class classification task, selecting a single label representing an individual participant or the group. This formulation assumes that address is inherently discrete and has primarily been used for predicting turn-taking. In this paper, we revisit this assumption by analyzing address as a continuous phenomenon. Using a multi-party human dialogue corpus annotated by multiple annotators, we construct both binary address labels derived from majority-vote addressee labels and continuous address levels inferred from annotator judgments using a latent-variable model. We then examine how these representations relate to turn-taking as well as listener behaviors, including gaze and backchannels. Our results show that, in addition to turn-taking, both gaze and backchannels are associated with address. Furthermore, models using continuous address levels achieve better predictive fit than those using discrete labels, suggesting that address may exhibit graded structure. Finally, we discuss the future directions of addressee detection research based on the findings of this study.

Problem

• addressee detection
• multi-party dialogue
• address structure
• continuous address
• turn-taking

Innovation

• continuous address
• multi-party dialogue
• addressee detection
• latent-variable model
• listener behavior