Situated conversations, which refer to visual information as visual question answering (VQA), often contain ambiguities caused by reliance on directive information. This problem is exacerbated because some languages, such as Japanese, often omit subjective or objective terms. Such ambiguities in questions are often clarified by the contexts in conversational situations, such as joint attention with a user or user gaze information. In this study, we propose the Gaze-grounded VQA dataset (GazeVQA) that clarifies ambiguous questions using gaze information by focusing on a clarification process complemented by gaze information. We also propose a method that utilizes gaze target estimation results to improve the accuracy of GazeVQA tasks. Our experimental results showed that the proposed method improved the performance in some cases of a VQA system on GazeVQA and identified some typical problems of GazeVQA tasks that need to be improved.

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.

In this paper, we propose a novel framework for evaluating style-shifting in social media conversations. Our proposed framework captures changes in an individual’s conversational style based on surprisals predicted by a personalized neural language model for individuals. Our personalized language model integrates not only the linguistic contents of conversations but also non-linguistic factors, such as social meanings, including group membership, personal attributes, and individual beliefs. We incorporate these factors directly or implicitly into our model, leveraging large, pre-trained language models and feature vectors derived from a relationship graph on social media. Compared to existing models, our personalized language model demonstrated superior performance in predicting an individual’s language in a test set. Furthermore, an analysis of style-shifting utilizing our proposed metric based on our personalized neural language model reveals a correlation between our metric and various conversation factors as well as human evaluation of style-shifting.