Debiasing Event Understanding for Visual Commonsense Tasks
Minji Seo, YeonJoon Jung, Seungtaek Choi, Seung-won Hwang, Bei Liu
Abstract
We study event understanding as a critical step towards visual commonsense tasks.Meanwhile, we argue that current object-based event understanding is purely likelihood-based, leading to incorrect event prediction, due to biased correlation between events and objects.We propose to mitigate such biases with do-calculus, proposed in causality research, but overcoming its limited robustness, by an optimized aggregation with association-based prediction.We show the effectiveness of our approach, intrinsically by comparing our generated events with ground-truth event annotation, and extrinsically by downstream commonsense tasks.- Anthology ID:
- 2022.findings-acl.65
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2022
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 782–787
- Language:
- URL:
- https://aclanthology.org/2022.findings-acl.65
- DOI:
- 10.18653/v1/2022.findings-acl.65
- Cite (ACL):
- Minji Seo, YeonJoon Jung, Seungtaek Choi, Seung-won Hwang, and Bei Liu. 2022. Debiasing Event Understanding for Visual Commonsense Tasks. In Findings of the Association for Computational Linguistics: ACL 2022, pages 782–787, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- Debiasing Event Understanding for Visual Commonsense Tasks (Seo et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.findings-acl.65.pdf
- Data
- VCR