Papers by Hyunmin Lee
AudioCaps: Generating Captions for Audios in The Wild (N19-1)
Copied to clipboard
| Challenge: | a dataset of 46K audio clips with human-written text pairs is used to generate captions for audio . the task of translating a multimedia input source into natural language has been extensively studied over the past few years . |
| Approach: | They propose a top-down multi-scale encoder and aligned semantic attention for audio captioning. |
| Outcome: | The proposed captions are faithful to audio inputs and better than existing models. |
VEHME: A Vision-Language Model For Evaluating Handwritten Mathematics Expressions (2025.emnlp-main)
Copied to clipboard
| Challenge: | VEHME is a vision language model for assessing handwritten math answers . traditional methods of assessing student work are limited by time constraints, class sizes and cognitive load . |
| Approach: | They propose a Vision-Language Model for Evaluating Handwritten Mathematics Expressions to assess handwritten math responses with high accuracy and interpretable reasoning traces. |
| Outcome: | VEHME achieves state-of-the-art performance among open-source models and approaches accuracy of proprietary systems. |
Schema Encoding for Transferable Dialogue State Tracking (2022.coling-1)
Copied to clipboard
| Challenge: | Recent work has focused on deep neural models for task-oriented dialogue systems . however, the neural models require a large dataset for training and a new dataset to be trained on another domain. |
| Approach: | They propose a schema encoder for transferable dialogue state tracking to new domains . they aim to transfer the model to new datasets by encoding new schemas based on the dataset . |
| Outcome: | The proposed method improves the accuracy of the proposed model on multi-domain settings. |