Search Results for author: Minji Seo

Found 3 papers, 1 papers with code

Debiasing Event Understanding for Visual Commonsense Tasks

no code implementations Findings (ACL) 2022 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.

XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanations

no code implementations CVPR 2021 Eunji Kim, Siwon Kim, Minji Seo, Sungroh Yoon

Automated diagnosis using deep neural networks in chest radiography can help radiologists detect life-threatening diseases.

Categorical Metadata Representation for Customized Text Classification

2 code implementations TACL 2019 Jihyeok Kim, Reinald Kim Amplayo, Kyungjae Lee, Sua Sung, Minji Seo, Seung-won Hwang

The performance of text classification has improved tremendously using intelligently engineered neural-based models, especially those injecting categorical metadata as additional information, e. g., using user/product information for sentiment classification.

Ranked #4 on Sentiment Analysis on User and product information (Yelp 2013 (Acc) metric)

Classification General Classification +4

Cannot find the paper you are looking for? You can Submit a new open access paper.