@inproceedings{lopez-ubeda-etal-2020-transfer,
title = "Transfer learning applied to text classification in {S}panish radiological reports",
author = "L{\'o}pez {\'U}beda, Pilar and
D{\'\i}az-Galiano, Manuel Carlos and
Urena Lopez, L. Alfonso and
Martin, Maite and
Mart{\'\i}n-Noguerol, Teodoro and
Luna, Antonio",
editor = "Melero, Maite",
booktitle = "Proceedings of the LREC 2020 Workshop on Multilingual Biomedical Text Processing (MultilingualBIO 2020)",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.multilingualbio-1.5",
pages = "29--32",
abstract = "Pre-trained text encoders have rapidly advanced the state-of-the-art on many Natural Language Processing tasks. This paper presents the use of transfer learning methods applied to the automatic detection of codes in radiological reports in Spanish. Assigning codes to a clinical document is a popular task in NLP and in the biomedical domain. These codes can be of two types: standard classifications (e.g. ICD-10) or specific to each clinic or hospital. In this study we show a system using specific radiology clinic codes. The dataset is composed of 208,167 radiology reports labeled with 89 different codes. The corpus has been evaluated with three methods using the BERT model applied to Spanish: Multilingual BERT, BETO and XLM. The results are interesting obtaining 70{\%} of F1-score with a pre-trained multilingual model.",
language = "English",
ISBN = "979-10-95546-65-8",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lopez-ubeda-etal-2020-transfer">
<titleInfo>
<title>Transfer learning applied to text classification in Spanish radiological reports</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pilar</namePart>
<namePart type="family">López Úbeda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manuel</namePart>
<namePart type="given">Carlos</namePart>
<namePart type="family">Díaz-Galiano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">L</namePart>
<namePart type="given">Alfonso</namePart>
<namePart type="family">Urena Lopez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Martin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Teodoro</namePart>
<namePart type="family">Martín-Noguerol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Luna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the LREC 2020 Workshop on Multilingual Biomedical Text Processing (MultilingualBIO 2020)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Melero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-65-8</identifier>
</relatedItem>
<abstract>Pre-trained text encoders have rapidly advanced the state-of-the-art on many Natural Language Processing tasks. This paper presents the use of transfer learning methods applied to the automatic detection of codes in radiological reports in Spanish. Assigning codes to a clinical document is a popular task in NLP and in the biomedical domain. These codes can be of two types: standard classifications (e.g. ICD-10) or specific to each clinic or hospital. In this study we show a system using specific radiology clinic codes. The dataset is composed of 208,167 radiology reports labeled with 89 different codes. The corpus has been evaluated with three methods using the BERT model applied to Spanish: Multilingual BERT, BETO and XLM. The results are interesting obtaining 70% of F1-score with a pre-trained multilingual model.</abstract>
<identifier type="citekey">lopez-ubeda-etal-2020-transfer</identifier>
<location>
<url>https://aclanthology.org/2020.multilingualbio-1.5</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>29</start>
<end>32</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Transfer learning applied to text classification in Spanish radiological reports
%A López Úbeda, Pilar
%A Díaz-Galiano, Manuel Carlos
%A Urena Lopez, L. Alfonso
%A Martin, Maite
%A Martín-Noguerol, Teodoro
%A Luna, Antonio
%Y Melero, Maite
%S Proceedings of the LREC 2020 Workshop on Multilingual Biomedical Text Processing (MultilingualBIO 2020)
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-65-8
%G English
%F lopez-ubeda-etal-2020-transfer
%X Pre-trained text encoders have rapidly advanced the state-of-the-art on many Natural Language Processing tasks. This paper presents the use of transfer learning methods applied to the automatic detection of codes in radiological reports in Spanish. Assigning codes to a clinical document is a popular task in NLP and in the biomedical domain. These codes can be of two types: standard classifications (e.g. ICD-10) or specific to each clinic or hospital. In this study we show a system using specific radiology clinic codes. The dataset is composed of 208,167 radiology reports labeled with 89 different codes. The corpus has been evaluated with three methods using the BERT model applied to Spanish: Multilingual BERT, BETO and XLM. The results are interesting obtaining 70% of F1-score with a pre-trained multilingual model.
%U https://aclanthology.org/2020.multilingualbio-1.5
%P 29-32
Markdown (Informal)
[Transfer learning applied to text classification in Spanish radiological reports](https://aclanthology.org/2020.multilingualbio-1.5) (López Úbeda et al., MultilingualBIO 2020)
ACL