A Gaze-grounded Visual Question Answering Dataset for Clarifying Ambiguous Japanese Questions

Shun Inadumi, Seiya Kawano, Akishige Yuguchi, Yasutomo Kawanishi, Koichiro Yoshino

Abstract
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.
Anthology ID:
2024.lrec-main.48
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
558–571
Language:
URL:
https://aclanthology.org/2024.lrec-main.48
DOI:
Bibkey:
Cite (ACL):
Shun Inadumi, Seiya Kawano, Akishige Yuguchi, Yasutomo Kawanishi, and Koichiro Yoshino. 2024. A Gaze-grounded Visual Question Answering Dataset for Clarifying Ambiguous Japanese Questions. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 558–571, Torino, Italia. ELRA and ICCL.
Cite (Informal):
A Gaze-grounded Visual Question Answering Dataset for Clarifying Ambiguous Japanese Questions (Inadumi et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2024.lrec-main.48.pdf
PDF Search