Yeonjoon Jung

Also published as: YeonJoon Jung


pdf bib
Debiasing Event Understanding for Visual Commonsense Tasks
Minji Seo | YeonJoon Jung | Seungtaek Choi | Seung-won Hwang | Bei Liu
Findings of the Association for Computational Linguistics: ACL 2022

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 bib
PLM-based World Models for Text-based Games
Minsoo Kim | Yeonjoon Jung | Dohyeon Lee | Seung-won Hwang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

World models have improved the ability of reinforcement learning agents to operate in a sample efficient manner, by being trained to predict plausible changes in the underlying environment. As the core tasks of world models are future prediction and commonsense understanding, our claim is that pre-trained language models (PLMs) already provide a strong base upon which to build world models. Worldformer is a recently proposed world model for text-based game environments, based only partially on PLM and transformers. Our distinction is to fully leverage PLMs as actionable world models in text-based game environments, by reformulating generation as constrained decoding which decomposes actions into verb templates and objects. We show that our model improves future valid action prediction and graph change prediction. Additionally, we show that our model better reflects commonsense than standard PLM.