Abstract
The correct interpretation of quantifier statements in the context of a visual scene requires non-trivial inference mechanisms. For the example of “most”, we discuss two strategies which rely on fundamentally different cognitive concepts. Our aim is to identify what strategy deep learning models for visual question answering learn when trained on such questions. To this end, we carefully design data to replicate experiments from psycholinguistics where the same question was investigated for humans. Focusing on the FiLM visual question answering model, our experiments indicate that a form of approximate number system emerges whose performance declines with more difficult scenes as predicted by Weber’s law. Moreover, we identify confounding factors, like spatial arrangement of the scene, which impede the effectiveness of this system.- Anthology ID:
- W19-4806
- Volume:
- Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
- Month:
- August
- Year:
- 2019
- Address:
- Florence, Italy
- Editors:
- Tal Linzen, Grzegorz Chrupała, Yonatan Belinkov, Dieuwke Hupkes
- Venue:
- BlackboxNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 46–55
- Language:
- URL:
- https://aclanthology.org/W19-4806
- DOI:
- 10.18653/v1/W19-4806
- Cite (ACL):
- Alexander Kuhnle and Ann Copestake. 2019. The Meaning of “Most” for Visual Question Answering Models. In Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 46–55, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- The Meaning of “Most” for Visual Question Answering Models (Kuhnle & Copestake, BlackboxNLP 2019)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/W19-4806.pdf
- Data
- CLEVR, ShapeWorld, Visual Question Answering