The PhotoBook Dataset: Building Common Ground through Visually-Grounded Dialogue
This dataset addresses the problem of modeling common ground in dialogue interactions for researchers in computational linguistics and AI, though it is incremental as it builds on existing work in dialogue analysis.
The paper introduces the PhotoBook dataset, a large-scale collection of 2,500 visually-grounded dialogues in English, designed to study shared dialogue history, and shows through a baseline model that accumulated shared information is crucial for resolving later descriptions in reference chains.
This paper introduces the PhotoBook dataset, a large-scale collection of visually-grounded, task-oriented dialogues in English designed to investigate shared dialogue history accumulating during conversation. Taking inspiration from seminal work on dialogue analysis, we propose a data-collection task formulated as a collaborative game prompting two online participants to refer to images utilising both their visual context as well as previously established referring expressions. We provide a detailed description of the task setup and a thorough analysis of the 2,500 dialogues collected. To further illustrate the novel features of the dataset, we propose a baseline model for reference resolution which uses a simple method to take into account shared information accumulated in a reference chain. Our results show that this information is particularly important to resolve later descriptions and underline the need to develop more sophisticated models of common ground in dialogue interaction.