ACL 2022findings2 citations

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.

BibTeX
@inproceedings{seo-etal-2022-debiasing,
    title = "Debiasing Event Understanding for Visual Commonsense Tasks",
    author = "Seo, Minji  and
      Jung, YeonJoon  and
      Choi, Seungtaek  and
      Hwang, Seung-won  and
      Liu, Bei",
    editor = "Muresan, Smaranda  and
      Nakov, Preslav  and
      Villavicencio, Aline",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.findings-acl.65/",
    doi = "10.18653/v1/2022.findings-acl.65",
    pages = "782--787"
}