Reference Resolution and New Entities in Exploratory Data Visualization: From Controlled to Unconstrained Interactions with a Conversational Assistant
Reference Resolution and New Entities in Exploratory Data Visualization: From Controlled to Unconstrained Interactions with a Conversational Assistant
复制标题
DOI：
10.18653/v1/2023.sigdial-1.33
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Abari Bhattacharya;Abhinav Kumar;Barbara Di Eugenio;Roderick S. Tabalba;Jillian Aurisano;Veronica Grosso;Andrew Johnson;Jason Leigh;Moira L. Zellner
中科院分区：
文献类型：
--
作者：
Abari Bhattacharya;Abhinav Kumar;Barbara Di Eugenio;Roderick S. Tabalba;Jillian Aurisano;Veronica Grosso;Andrew Johnson;Jason Leigh;Moira L. Zellner
在数据可视化的上下文中，与其他接地设置一样，引用是由代理参与的任务创建的，并且是突出的，因为它们属于共享的物理设置。我们的重点是解决大型显示器上的可视化引用;至关重要的是，引用解析直接涉及创建新实体的过程，即新的可视化。首先，我们为会话助理开发了一个参考分辨率模型。我们对助手进行了关于涉及单个用户的数据可视化的受控对话的培训。其次，我们将会话助手（包括其引用解析模型）移植到不同的域，支持两个用户在数据探索任务上进行协作。我们探讨了新的设置如何影响参考检测和分辨率;我们比较了受控与无约束设置中的性能，并讨论了我们从这种适应中吸取的一般经验教训。
In the context of data visualization, as in other grounded settings, referents are created by the task the agents engage in and are salient because they belong to the shared physical setting. Our focus is on resolving references to visualizations on large displays; crucially, reference resolution is directly involved in the process of creating new entities, namely new visualizations. First, we developed a reference resolution model for a conversational assistant. We trained the assistant on controlled dialogues for data visualizations involving a single user. Second, we ported the conversational assistant including its reference resolution model to a different domain, supporting two users collaborating on a data exploration task. We explore how the new setting affects reference detection and resolution; we compare the performance in the controlled vs unconstrained setting, and discuss the general lessons that we draw from this adaptation.