Papers by Minsu Park
Improving Multi-lingual Alignment Through Soft Contrastive Learning (2024.naacl-srw)
Copied to clipboard
| Challenge: | Existing methods to train multi-lingual sentence embeddings ruins the mono-lingual space. |
| Approach: | They propose a method to align multi-lingual embeddings based on similarity of sentences measured by a pre-trained mono-lingual teacher model. |
| Outcome: | The proposed method outperforms existing multi-lingual embeddings including LaBSE on five languages and on a translation pair for Tatoeba dataset. |
Large Language Models Are Natural Video Popularity Predictors (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) can better capture cultural and social factors such as viewing intensity and geographic spread of video content. |
| Approach: | They propose to use Large Language Models to capture cultural and social factors that influence video popularity and generate interpretable, attribute-based explanations. |
| Outcome: | The proposed model captures both engagement intensity and geographic spread on 13,639 popular videos, while the neural network's predictions reach 82% without fine-tuning. |