paper-with-me

홈 › Papers

Debiasing Event Understanding for Visual Commonsense Tasks

2022-05-01 · Findings (ACL) 2022 5 · Minji Seo, YeonJoon Jung, Seungtaek Choi, Seung-won Hwang, Bei Liu

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Bias Mitigation or Cultural Commonsense? Evaluating LLMs with a Japanese Dataset

2025-09-29 · Taisei Yamamoto, Ryoma Kumon, Danushka Bollegala, Hitomi Yanaka arxiv

Large language models (LLMs) exhibit social biases, prompting the development of various debiasing methods. However, debiasing methods may degrade the capabilities of LLMs. Previous research has evaluated the impact of b…

Causal Debiasing for Visual Commonsense Reasoning

2025-10-23 · Jiayi Zou, Gengyun Jia, Bing-Kun Bao arxiv

Visual Commonsense Reasoning (VCR) refers to answering questions and providing explanations based on images. While existing methods achieve high prediction accuracy, they often overlook bias in datasets and lack debiasin…

Visual Commonsense Reasoning

Are Visual-Linguistic Models Commonsense Knowledge Bases?

2022-10-01 · COLING 2022 10 · Hsiu-Yu Yang, Carina Silberer

Despite the recent success of pretrained language models as on-the-fly knowledge sources for various downstream tasks, they are shown to inadequately represent trivial common facts that vision typically captures. This li…

Natural Language UnderstandingQuestion Answering

Expressive Scene Graph Generation Using Commonsense Knowledge Infusion for Visual Understanding and Reasoning

2022-05-31 · European Semantic Web Conference (ESWC) 2022 5 · Khan, M. Jaleed; Breslin, John G.; Curry, Edward

Scene graph generation aims to capture the semantic elements in images by modelling objects and their relationships in a structured manner, which are essential for visual understanding and reasoning tasks including image…

Common Sense ReasoningGraph GenerationImage CaptioningImage Generation+9

COMET-M: Reasoning about Multiple Events in Complex Sentences

2023-05-24 · Sahithya Ravi, Raymond Ng, Vered Shwartz

Understanding the speaker's intended meaning often involves drawing commonsense inferences to reason about what is not stated explicitly. In multi-event sentences, it requires understanding the relationships between even…

coreference-resolutionCoreference ResolutionSentence