@inproceedings{baez-etal-2020-chilean,
title = "The {C}hilean Waiting List Corpus: a new resource for clinical Named Entity Recognition in {S}panish",
author = "B{\'a}ez, Pablo and
Villena, Fabi{\'a}n and
Rojas, Mat{\'\i}as and
Dur{\'a}n, Manuel and
Dunstan, Jocelyn",
booktitle = "Proceedings of the 3rd Clinical Natural Language Processing Workshop",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.clinicalnlp-1.32",
doi = "10.18653/v1/2020.clinicalnlp-1.32",
pages = "291--300",
abstract = "In this work we describe the Waiting List Corpus consisting of de-identified referrals for several specialty consultations from the waiting list in Chilean public hospitals. A subset of 900 referrals was manually annotated with 9,029 entities, 385 attributes, and 284 pairs of relations with clinical relevance. A trained medical doctor annotated these referrals, and then together with other three researchers, consolidated each of the annotations. The annotated corpus has nested entities, with 32.2{\%} of entities embedded in other entities. We use this annotated corpus to obtain preliminary results for Named Entity Recognition (NER). The best results were achieved by using a biLSTM-CRF architecture using word embeddings trained over Spanish Wikipedia together with clinical embeddings computed by the group. NER models applied to this corpus can leverage statistics of diseases and pending procedures within this waiting list. This work constitutes the first annotated corpus using clinical narratives from Chile, and one of the few for the Spanish language. The annotated corpus, the clinical word embeddings, and the annotation guidelines are freely released to the research community.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="baez-etal-2020-chilean">
<titleInfo>
<title>The Chilean Waiting List Corpus: a new resource for clinical Named Entity Recognition in Spanish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pablo</namePart>
<namePart type="family">Báez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabián</namePart>
<namePart type="family">Villena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matías</namePart>
<namePart type="family">Rojas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manuel</namePart>
<namePart type="family">Durán</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jocelyn</namePart>
<namePart type="family">Dunstan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Clinical Natural Language Processing Workshop</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work we describe the Waiting List Corpus consisting of de-identified referrals for several specialty consultations from the waiting list in Chilean public hospitals. A subset of 900 referrals was manually annotated with 9,029 entities, 385 attributes, and 284 pairs of relations with clinical relevance. A trained medical doctor annotated these referrals, and then together with other three researchers, consolidated each of the annotations. The annotated corpus has nested entities, with 32.2% of entities embedded in other entities. We use this annotated corpus to obtain preliminary results for Named Entity Recognition (NER). The best results were achieved by using a biLSTM-CRF architecture using word embeddings trained over Spanish Wikipedia together with clinical embeddings computed by the group. NER models applied to this corpus can leverage statistics of diseases and pending procedures within this waiting list. This work constitutes the first annotated corpus using clinical narratives from Chile, and one of the few for the Spanish language. The annotated corpus, the clinical word embeddings, and the annotation guidelines are freely released to the research community.</abstract>
<identifier type="citekey">baez-etal-2020-chilean</identifier>
<identifier type="doi">10.18653/v1/2020.clinicalnlp-1.32</identifier>
<location>
<url>https://aclanthology.org/2020.clinicalnlp-1.32</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>291</start>
<end>300</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Chilean Waiting List Corpus: a new resource for clinical Named Entity Recognition in Spanish
%A Báez, Pablo
%A Villena, Fabián
%A Rojas, Matías
%A Durán, Manuel
%A Dunstan, Jocelyn
%S Proceedings of the 3rd Clinical Natural Language Processing Workshop
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F baez-etal-2020-chilean
%X In this work we describe the Waiting List Corpus consisting of de-identified referrals for several specialty consultations from the waiting list in Chilean public hospitals. A subset of 900 referrals was manually annotated with 9,029 entities, 385 attributes, and 284 pairs of relations with clinical relevance. A trained medical doctor annotated these referrals, and then together with other three researchers, consolidated each of the annotations. The annotated corpus has nested entities, with 32.2% of entities embedded in other entities. We use this annotated corpus to obtain preliminary results for Named Entity Recognition (NER). The best results were achieved by using a biLSTM-CRF architecture using word embeddings trained over Spanish Wikipedia together with clinical embeddings computed by the group. NER models applied to this corpus can leverage statistics of diseases and pending procedures within this waiting list. This work constitutes the first annotated corpus using clinical narratives from Chile, and one of the few for the Spanish language. The annotated corpus, the clinical word embeddings, and the annotation guidelines are freely released to the research community.
%R 10.18653/v1/2020.clinicalnlp-1.32
%U https://aclanthology.org/2020.clinicalnlp-1.32
%U https://doi.org/10.18653/v1/2020.clinicalnlp-1.32
%P 291-300
Markdown (Informal)
[The Chilean Waiting List Corpus: a new resource for clinical Named Entity Recognition in Spanish](https://aclanthology.org/2020.clinicalnlp-1.32) (Báez et al., ClinicalNLP 2020)
ACL