Minbyul Jeong

Minbyul Jeong

Auto-generated profile, based on publicly available information

Minbyul Jeong

Korea University AIGEN Sciences

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 June 2024 in Bioinformatics
Verified
Journal Article
Open access
PDF file
MJMinbyul Jeong
Minbyul Jeong
JSJiwoong Sohn
Jiwoong Sohn
MSMujeen Sung
Mujeen Sung
JKJaewoo Kang
Jaewoo Kang
Recent proprietary large language models (LLMs), such as GPT-4, have achieved a milestone in tackling diverse challenges in the biomedical domain, ranging from multiple-choice questions to long-form generations. To address challenges that still cannot be handled with the encoded knowledge of LLMs, various retrieval-augmented generation (RAG) methods have been developed by searching documents from the knowledge corpus and appending them unconditionally or selectively to the input of LLMs for generation. However, when applying existing methods to different domain-specific problems, poor generalization becomes apparent, leading to fetching incorrect documents or making inaccurate judgments. In this paper, we introduce Self-BioRAG, a framework reliable for biomedical text that specializes in generating explanations, retrieving domain-specific documents, and self-reflecting generated responses. We utilize 84k filtered biomedical instruction sets to train Self-BioRAG that can assess its generated explanations with customized reflective tokens. Our work proves that domain-specific components, such as a retriever, domain-related document corpus, and instruction sets are necessary for adhering to domain-related instructions. Using three major medical question-answering benchmark datasets, experimental results of Self-BioRAG demonstrate significant performance gains by achieving a 7.2% absolute improvement on average over the state-of-the-art open-foundation model with a parameter size of 7B or less. Similarly, Self-BioRAG outperforms RAG by 8% Rouge-1 score in generating more proficient answers on two long-form question-answering benchmarks on average. Overall, we analyze that Self-BioRAG finds the clues in the question, retrieves relevant documents if needed, and understands how to answer with information from retrieved documents and encoded knowledge as a medical expert does. We release our data and code for training our framework components and model weights (7B and 13B) to enhance capabilities in biomedical and clinical domains. Self-BioRAG is available at https://github.com/dmis-lab/self-biorag.

2 September 2022 in Bioinformatics
Verified
Journal Article
Open access
PDF file
MSMujeen Sung
Mujeen Sung
MJMinbyul Jeong
Minbyul Jeong
YCYonghwa Choi
Yonghwa Choi
DKDonghyeon Kim
Donghyeon Kim
JLJinhyuk Lee
Jinhyuk Lee
JKJaewoo Kang
Jaewoo Kang
In biomedical natural language processing, named entity recognition (NER) and named entity normalization (NEN) are key tasks that enable the automatic extraction of biomedical entities (e.g. diseases and drugs) from the ever-growing biomedical literature. In this article, we present BERN2 (Advanced Biomedical Entity Recognition and Normalization), a tool that improves the previous neural network-based NER tool by employing a multi-task NER model and neural network-based NEN models to achieve much faster and more accurate inference. We hope that our tool can help annotate large-scale biomedical texts for various tasks such as biomedical knowledge graph construction. Web service of BERN2 is publicly available at http://bern2.korea.ac.kr. We also provide local installation of BERN2 at https://github.com/dmis-lab/BERN2. Supplementary data are available at Bioinformatics online.

4 June 2022 in Neural Networks
Verified
Journal Article
Open access
SYSeongjun Yun
Seongjun Yun
MJMinbyul Jeong
Minbyul Jeong
SYSungdong Yoo
Sungdong Yoo
SLSeunghun Lee
Seunghun Lee
SYSean S. Yi
Sean S. Yi
HKHyunwoo J. Kim
Hyunwoo J. Kim
Graph Neural Networks (GNNs) have been widely applied to various fields due to their powerful representations of graph-structured data. Despite the success of GNNs, most existing GNNs are designed to learn node representations on the fixed and homogeneous graphs. The limitations especially become problematic when learning representations on a misspecified graph or a heterogeneous graph that consists of various types of nodes and edges. To address these limitations, we propose Graph Transformer Networks (GTNs) that are capable of generating new graph structures, which preclude noisy connections and include useful connections (e.g., meta-paths) for tasks, while learning effective node representations on the new graphs in an end-to-end fashion. We further propose enhanced version of GTNs, Fast Graph Transformer Networks (FastGTNs), that improve scalability of graph transformations. Compared to GTNs, FastGTNs are up to 230× and 150× faster in inference and training, and use up to 100× and 148× less memory while allowing the identical graph transformations as GTNs. In addition, we extend graph transformations to the semantic proximity of nodes allowing non-local operations beyond meta-paths. Extensive experiments on both homogeneous graphs and heterogeneous graphs show that GTNs and FastGTNs with non-local operations achieve the state-of-the-art performance for node classification tasks. The code is available: https://github.com/seongjunyun/Graph_Transformer_Networks.

1 January 2024
Verified
Conference Paper
Open access
PDF file
CYChanwoong Yoon
Chanwoong Yoon
TLTaewhoo Lee
Taewhoo Lee
HHHyeon Hwang
Hyeon Hwang
MJMinbyul Jeong
Minbyul Jeong
JKJaewoo Kang
Jaewoo Kang
Chanwoong Yoon, Taewhoo Lee, Hyeon Hwang, Minbyul Jeong, Jaewoo Kang. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

28 March 2020
Verified
Book Chapter
Closed access
PDF file
WYWonjin Yoon
Wonjin Yoon
JLJinhyuk Lee
Jinhyuk Lee
DKDonghyeon Kim
Donghyeon Kim
MJMinbyul Jeong
Minbyul Jeong
JKJaewoo Kang
Jaewoo Kang

5 February 2020 in arXiv
Verified
Preprint
Open access
PDF file
SYSeongjun Yun
Seongjun Yun
MJMinbyul Jeong
Minbyul Jeong
RKRaehyun Kim
Raehyun Kim
JKJaewoo Kang
Jaewoo Kang
HKHyunwoo J. Kim
Hyunwoo J. Kim
Graph neural networks (GNNs) have been widely used in representation learning on graphs and achieved state-of-the-art performance in tasks such as node classification and link prediction. However, most existing GNNs are designed to learn node representations on the fixed and homogeneous graphs. The limitations especially become problematic when learning representations on a misspecified graph or a heterogeneous graph that consists of various types of nodes and edges. In this paper, we propose Graph Transformer Networks (GTNs) that are capable of generating new graph structures, which involve identifying useful connections between unconnected nodes on the original graph, while learning effective node representation on the new graphs in an end-to-end fashion. Graph Transformer layer, a core layer of GTNs, learns a soft selection of edge types and composite relations for generating useful multi-hop connections so-called meta-paths. Our experiments show that GTNs learn new graph structures, based on data and tasks without domain knowledge, and yield powerful node representation via convolution on the new graphs. Without domain-specific graph preprocessing, GTNs achieved the best performance in all three benchmark node classification tasks against the state-of-the-art methods that require pre-defined meta-paths from domain knowledge.