J-CRe3: A Japanese Conversation Dataset for Real-world Reference Resolution
This dataset addresses the need for grounding verbal references to visual information in human-assisting systems like robots, though it is incremental as it focuses on a specific language and domain.
The authors tackled the problem of real-world reference resolution by creating J-CRe3, a Japanese multimodal dataset with egocentric video and dialogue audio, annotated for direct and indirect reference relations, and they built an experimental model to identify challenges in the task.
Understanding expressions that refer to the physical world is crucial for such human-assisting systems in the real world, as robots that must perform actions that are expected by users. In real-world reference resolution, a system must ground the verbal information that appears in user interactions to the visual information observed in egocentric views. To this end, we propose a multimodal reference resolution task and construct a Japanese Conversation dataset for Real-world Reference Resolution (J-CRe3). Our dataset contains egocentric video and dialogue audio of real-world conversations between two people acting as a master and an assistant robot at home. The dataset is annotated with crossmodal tags between phrases in the utterances and the object bounding boxes in the video frames. These tags include indirect reference relations, such as predicate-argument structures and bridging references as well as direct reference relations. We also constructed an experimental model and clarified the challenges in multimodal reference resolution tasks.