@inproceedings{byun-etal-2024-korean,
title = "{K}orean Bio-Medical Corpus ({KBMC}) for Medical Named Entity Recognition",
author = "Byun, Sungjoo and
Hong, Jiseung and
Park, Sumin and
Jang, Dongjun and
Seo, Jean and
Kim, Minseok and
Oh, Chaeyoung and
Shin, Hyopil",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.868/",
pages = "9941--9947",
abstract = "Named Entity Recognition (NER) plays a pivotal role in medical Natural Language Processing (NLP). Yet, there has not been an open-source medical NER dataset specifically for the Korean language. To address this, we utilized ChatGPT to assist in constructing the KBMC (Korean Bio-Medical Corpus), which we are now presenting to the public. With the KBMC dataset, we noticed an impressive 20{\%} increase in medical NER performance compared to models trained on general Korean NER datasets. This research underscores the significant benefits and importance of using specialized tools and datasets, like ChatGPT, to enhance language processing in specialized fields such as healthcare."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="byun-etal-2024-korean">
<titleInfo>
<title>Korean Bio-Medical Corpus (KBMC) for Medical Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sungjoo</namePart>
<namePart type="family">Byun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiseung</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sumin</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongjun</namePart>
<namePart type="family">Jang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jean</namePart>
<namePart type="family">Seo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minseok</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chaeyoung</namePart>
<namePart type="family">Oh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyopil</namePart>
<namePart type="family">Shin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Named Entity Recognition (NER) plays a pivotal role in medical Natural Language Processing (NLP). Yet, there has not been an open-source medical NER dataset specifically for the Korean language. To address this, we utilized ChatGPT to assist in constructing the KBMC (Korean Bio-Medical Corpus), which we are now presenting to the public. With the KBMC dataset, we noticed an impressive 20% increase in medical NER performance compared to models trained on general Korean NER datasets. This research underscores the significant benefits and importance of using specialized tools and datasets, like ChatGPT, to enhance language processing in specialized fields such as healthcare.</abstract>
<identifier type="citekey">byun-etal-2024-korean</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.868/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>9941</start>
<end>9947</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Korean Bio-Medical Corpus (KBMC) for Medical Named Entity Recognition
%A Byun, Sungjoo
%A Hong, Jiseung
%A Park, Sumin
%A Jang, Dongjun
%A Seo, Jean
%A Kim, Minseok
%A Oh, Chaeyoung
%A Shin, Hyopil
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F byun-etal-2024-korean
%X Named Entity Recognition (NER) plays a pivotal role in medical Natural Language Processing (NLP). Yet, there has not been an open-source medical NER dataset specifically for the Korean language. To address this, we utilized ChatGPT to assist in constructing the KBMC (Korean Bio-Medical Corpus), which we are now presenting to the public. With the KBMC dataset, we noticed an impressive 20% increase in medical NER performance compared to models trained on general Korean NER datasets. This research underscores the significant benefits and importance of using specialized tools and datasets, like ChatGPT, to enhance language processing in specialized fields such as healthcare.
%U https://aclanthology.org/2024.lrec-main.868/
%P 9941-9947
Markdown (Informal)
[Korean Bio-Medical Corpus (KBMC) for Medical Named Entity Recognition](https://aclanthology.org/2024.lrec-main.868/) (Byun et al., LREC-COLING 2024)
ACL
- Sungjoo Byun, Jiseung Hong, Sumin Park, Dongjun Jang, Jean Seo, Minseok Kim, Chaeyoung Oh, and Hyopil Shin. 2024. Korean Bio-Medical Corpus (KBMC) for Medical Named Entity Recognition. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 9941–9947, Torino, Italia. ELRA and ICCL.