Papers by Myoung-Wan Koo

5 papers
Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue System (2023.findings-acl)

Copied to clipboard

Challenge: Recent work on end-to-end dialogue models with pre-trained dialogue corpora shows promising performance in the conversational system.
Approach: They propose an end-to-end TOD system with task-optimized adapters which learn independently per task adding only small number of parameters after fixed layers of pre-trained network.
Outcome: The proposed system achieves state-of-the-art performance on the MultiWOZ benchmark compared to existing models.
Omni-Embed-Audio: Leveraging Multimodal LLMs for Robust Audio-Text Retrieval (2026.acl-long)

Copied to clipboard

Challenge: Experiments with AudioCaps, Clotho, and MECAT show that OEA achieves comparable text-to-text retrieval performance to state-of-the-art M2D-CLAP.
Approach: They propose a retrieval-oriented encoder leveraging multimodal LLMs with native audio understanding that allows users to express their queries in five different ways.
Outcome: Experiments on AudioCaps, Clotho, and MECAT show that OEA achieves comparable text-to-audio retrieval performance to state-of-the-art M2D-CLAP while demonstrating clear advantages in two critical areas.
SELF-EXPERTISE: Knowledge-based Instruction Dataset Augmentation for a Legal Expert Language Model (2024.findings-naacl)

Copied to clipboard

Challenge: generating instructions and outputs from LLMs can produce unintentionally inaccurate or misleading information.
Approach: They propose to generate an instruction dataset in the legal domain from a seed dataset by extracting knowledge from the outputs of the seed dataset.
Outcome: The proposed method reduces hallucinations in automatic instruction dataset augmentation.
Towards Context-Based Violence Detection: A Korean Crime Dialogue Dataset (2024.findings-eacl)

Copied to clipboard

Challenge: Currently, there are three main branches of violence detection, including surveillance of potential threats in offline situation and automatic prevention of harmful media.
Approach: They propose to use the Korean Crime Dialogue Dataset to classify violence that occurs in offline scenarios.
Outcome: The proposed dataset shows that understanding varying relationships among interlocutors improves the performance of crime dialogue classification.
Diagnosis of Dysarthria Severity and Explanation Generation Using XAI-Enhanced CLINIC-GENIE on Diadochokinetic Tasks (2026.findings-eacl)

Copied to clipboard

Challenge: Recent deep learning approaches for dysarthria impairment severity lack interpretability essential for clinical applications.
Approach: They propose a deep neural network classifier that integrates acoustic and speech embeddings with Clinically Explainable Acoustic Features (CEAFs) and a module that transforms CEAFs and their Shapley values into intuitive natural language explanations.
Outcome: The proposed model achieves a balanced accuracy of 0.952 (17.3% improvement over using CEAFs alone) and certified speech-language pathologists rated explanations with an average fidelity score of 4.94, confirming enhanced clinical utility.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations