Papers by Younghun Lee
KOLD: Korean Offensive Language Dataset (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent directions for offensive language detection focus on English and do not transfer well to other languages because of cultural and linguistic differences. |
| Approach: | They present a Korean offensive language dataset annotated with offensive language comments . they use the comments as training data for Korean BERT and RoBERTa models . |
| Outcome: | The proposed model improves offensiveness detection, target classification, and span detection while having room for improvement for target group classification and span prediction. |
A Multilingual Dataset and Empirical Validation for the Mutual Reinforcement Effect in Information Extraction (2026.findings-acl)
Copied to clipboard
Chengguang Gan, Sunbowen Lee, Qingyu Yin, Yunhao Liang, Xinyang He, Hanjun Wei, Younghun Lim, Shijian Wang, Hexiang Huang, QingHao Zhang, Shiwen Ni, Tatsunori Mori
| Challenge: | Existing work on the Mutual Reinforcement Effect in information extraction has not been empirically validated . 76 percent of the 21 sub-datasets exhibit the Mutual Reforcement effect across languages . |
| Approach: | They propose a multilingual MRE mix dataset that integrates 21 sub-datasets covering English, Japanese, and Chinese. |
| Outcome: | The proposed framework reduces manual annotation effort while preserving structural requirements of MRE tasks. |
SOLAR: Towards Characterizing Subjectivity of Individuals through Modeling Value Conflicts and Trade-offs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies suggest that Large Language Models can account for individual-level subjectivity, yet exploring whether LLMs can generate perspectives and reasoning that align well with a specific persona or demographic information has not been adequately studied. |
| Approach: | They propose a framework that observes value conflicts and trade-offs in user-generated texts to better represent subjective ground of individuals. |
| Outcome: | The proposed framework improves inference performance for users with limited data and in controversial situations. |
Towards Explaining Subjective Ground of Individuals on Social Media (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Large-scale language models have been reducing the gap between machines and humans in understanding how the real world works, yet understanding an individual’s perspective and behavior from text is far from being resolved. |
| Approach: | They propose a neural model that learns subjective grounds of individuals and accounts for their judgments on situations posted on social media. |
| Outcome: | The proposed model provides human-readable explanations of an individual’s subjective preference in judging social situations and also learns an individual's orientation towards abstract moral concepts. |
Weighted Contrastive Learning With False Negative Control to Help Long-tailed Product Classification (2023.acl-industry)
Copied to clipboard
| Challenge: | Item categorization (IC) aims to classify a product into leaf nodes in a categorical taxonomy due to scarce supervision. |
| Approach: | They propose to use K-positive contrastive loss (KCL) to address IC task’s long-tail issue by re-weighting positive pairs in the KCL loss with a regularization that the sum of weights should be constrained to K+1 as close as possible. |
| Outcome: | The proposed method improves on the long-tail issue in the image classification task and when using text-based contrastive learning, it can be applied on the IC task. |
Towards Understanding Counseling Conversations: Domain Knowledge and Large Language Models (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing language models such as Transformer-based models fail to predict the conversation outcome. |
| Approach: | They propose to integrate human-annotated domain knowledge and LLM-generated features to provide richer context to counseling conversations. |
| Outcome: | The proposed model improves by 15% when combined with human-annotated domain knowledge and LLM-generated features. |