@inproceedings{landes-etal-2022-new,
title = "A New Public Corpus for Clinical Section Identification: {M}ed{S}ec{I}d",
author = "Landes, Paul and
Patel, Kunal and
Huang, Sean S. and
Webb, Adam and
Di Eugenio, Barbara and
Caragea, Cornelia",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.326",
pages = "3709--3721",
abstract = "The process by which sections in a document are demarcated and labeled is known as section identification. Such sections are helpful to the reader when searching for information and contextualizing specific topics. The goal of this work is to segment the sections of clinical medical domain documentation. The primary contribution of this work is MedSecId, a publicly available set of 2,002 fully annotated medical notes from the MIMIC-III. We include several baselines, source code, a pretrained model and analysis of the data showing a relationship between medical concepts across sections using principal component analysis.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="landes-etal-2022-new">
<titleInfo>
<title>A New Public Corpus for Clinical Section Identification: MedSecId</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Landes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kunal</namePart>
<namePart type="family">Patel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sean</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Webb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Di Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cornelia</namePart>
<namePart type="family">Caragea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The process by which sections in a document are demarcated and labeled is known as section identification. Such sections are helpful to the reader when searching for information and contextualizing specific topics. The goal of this work is to segment the sections of clinical medical domain documentation. The primary contribution of this work is MedSecId, a publicly available set of 2,002 fully annotated medical notes from the MIMIC-III. We include several baselines, source code, a pretrained model and analysis of the data showing a relationship between medical concepts across sections using principal component analysis.</abstract>
<identifier type="citekey">landes-etal-2022-new</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.326</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>3709</start>
<end>3721</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A New Public Corpus for Clinical Section Identification: MedSecId
%A Landes, Paul
%A Patel, Kunal
%A Huang, Sean S.
%A Webb, Adam
%A Di Eugenio, Barbara
%A Caragea, Cornelia
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F landes-etal-2022-new
%X The process by which sections in a document are demarcated and labeled is known as section identification. Such sections are helpful to the reader when searching for information and contextualizing specific topics. The goal of this work is to segment the sections of clinical medical domain documentation. The primary contribution of this work is MedSecId, a publicly available set of 2,002 fully annotated medical notes from the MIMIC-III. We include several baselines, source code, a pretrained model and analysis of the data showing a relationship between medical concepts across sections using principal component analysis.
%U https://aclanthology.org/2022.coling-1.326
%P 3709-3721
Markdown (Informal)
[A New Public Corpus for Clinical Section Identification: MedSecId](https://aclanthology.org/2022.coling-1.326) (Landes et al., COLING 2022)
ACL
- Paul Landes, Kunal Patel, Sean S. Huang, Adam Webb, Barbara Di Eugenio, and Cornelia Caragea. 2022. A New Public Corpus for Clinical Section Identification: MedSecId. In Proceedings of the 29th International Conference on Computational Linguistics, pages 3709–3721, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.