Papers by Beomseok Lee
Speech Foundation Models and Crowdsourcing for Efficient, High-Quality Data Collection (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods for crowdsourcing data collection require a human workforce, which is hard to sustain. |
| Approach: | They propose to use Speech Foundation Models to automate validation processes . they find that SFMs can reduce reliance on human validation . |
| Outcome: | The proposed model reduces the reliance on human validation without degrading the quality of the final data. |
Language Model Augmented Monotonic Attention for Simultaneous Translation (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing adaptive policies for simultaneous neural machine translation use monotonic attention to perform read/write decisions based on the partial source and target sequences. |
| Approach: | They propose a framework to aid monotonic attention with an external language model to improve its decisions. |
| Outcome: | The proposed approach improves on English-German and English-French translation tasks by using a language model. |
XDetox: Text Detoxification with Token-Level Toxicity Explanations (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for mitigating toxic content are black-box approaches, which results in limitations in modifying toxic tokens. |
| Approach: | They propose a method that integrates token-level toxicity explanations with the masking and infilling detoxification processes. |
| Outcome: | The proposed method outperforms baseline methods in fluency and toxicity reduction. |
Unifying Uniform and Binary-coding Quantization for Accurate Compression of Large Language Models (2025.acl-long)
Copied to clipboard
Seungcheol Park, Jeongin Bae, Beomseok Kwon, Minjun Kim, Byeongwook Kim, Se Jung Kwon, U Kang, Dongsoo Lee
| Challenge: | Quantization is essential for deploying large language models (LLMs) efficiently since they require expensive computational and memory costs. |
| Approach: | They propose a quantization method that unifies flexible mapping techniques to optimize parameters precisely. |
| Outcome: | The proposed method outperforms existing methods and achieves higher accuracy on GSM8K benchmark. |
SARCAT: Generative Span-Act Guided Response Generation using Copy-enhanced Target Augmentation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches for document-grounded dialogue systems are based on retrieve-and-generate frameworks. |
| Approach: | They propose a novel extension to improve document grounded response generation by incorporating a copy mechanism into a augmentation. |
| Outcome: | The proposed extension improves the document-grounded response generation performance even with the base reader. |