Papers by Yoon-Sik Cho
GRIT: Guided Relational Integration for Efficient Multi-Table Understanding (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for encoding table structures are limited to single-table settings . end users are increasingly turning to LLMs with natural language queries . |
| Approach: | They propose a method that converts relational schemas into LLM-friendly textual representations. |
| Outcome: | The proposed method improves table-column retrieval performance across multiple tables while reducing memory and computational overhead. |
Improving Contrastive Learning in Emotion Recognition in Conversation via Data Augmentation and Decoupled Neutral Emotion (2024.eacl-long)
Copied to clipboard
| Challenge: | Existing methods to model context of utterances and speaker are inadequate . despite the improvements, there are still intrinsic challenges in the ERC dataset . |
| Approach: | They propose a supervised contrastive learning method specifically oriented for ERC task . they employ a data augmentation method emulating the emotion dynamics in a conversation and a method addressing the predominance and ambiguity of neutral emotion. |
| Outcome: | The proposed method emulates the emotion dynamics in a conversation and addresses the predominance and the ambiguity of neutral emotion. |