On the Structure of Address in Multi-Party Dialogue: From Discrete Labels to Continuous Levels
On the Structure of Address in Multi-Party Dialogue: From Discrete Labels to Continuous Levels
多方对话中寻址结构的探讨：从离散标签到连续层级
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.
摘要： 在对话系统与多名用户进行的多方对话中，识别话语的指向对象是一个关键挑战。以往的研究通常将寻址对象检测视为一个多分类任务，即选择一个代表特定参与者或群体的单一标签。这种表述方式假设寻址本质上是离散的，并主要用于预测轮次转换。
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.
在本文中，我们通过将寻址分析为一种连续现象，重新审视了这一假设。我们利用由多名标注者标注的多方人类对话语料库，构建了两种数据：一种是源自多数投票的二元寻址标签，另一种是利用潜在变量模型从标注者判断中推断出的连续寻址层级。
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.
随后，我们研究了这些表征与轮次转换以及听者行为（包括注视和回馈信号）之间的关系。研究结果表明，除了轮次转换外，注视和回馈信号也都与寻址密切相关。此外，使用连续寻址层级的模型比使用离散标签的模型具有更好的预测拟合度，这表明寻址可能呈现出分级结构。最后，我们基于本研究的发现，探讨了寻址对象检测研究的未来方向。
Paper Details:
- Authors: Taiga Mori, Koji Inoue, Divesh Lala, Tatsuya Kawahara
- arXiv ID: 2607.15648
- Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
论文详情：
- 作者： Taiga Mori, Koji Inoue, Divesh Lala, Tatsuya Kawahara
- arXiv ID: 2607.15648
- 学科分类： 计算与语言 (cs.CL)；人工智能 (cs.AI)；人机交互 (cs.HC)