@inproceedings{copara-etal-2020-contextualized,
title = "Contextualized {F}rench Language Models for Biomedical Named Entity Recognition",
author = "Copara, Jenny and
Knafou, Julien and
Naderi, Nona and
Moro, Claudia and
Ruch, Patrick and
Teodoro, Douglas",
editor = "Cardon, R{\'e}mi and
Grabar, Natalia and
Grouin, Cyril and
Hamon, Thierry",
booktitle = "Actes de la 6e conf{\'e}rence conjointe Journ{\'e}es d'{\'E}tudes sur la Parole (JEP, 33e {\'e}dition), Traitement Automatique des Langues Naturelles (TALN, 27e {\'e}dition), Rencontre des {\'E}tudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (R{\'E}CITAL, 22e {\'e}dition). Atelier D{\'E}fi Fouille de Textes",
month = "6",
year = "2020",
address = "Nancy, France",
publisher = "ATALA et AFCP",
url = "https://aclanthology.org/2020.jeptalnrecital-deft.4/",
pages = "36--48",
abstract = "Named entity recognition (NER) is key for biomedical applications as it allows knowledge discovery in free text data. As entities are semantic phrases, their meaning is conditioned to the context to avoid ambiguity. In this work, we explore contextualized language models for NER in French biomedical text as part of the D{\'e}fi Fouille de Textes challenge. Our best approach achieved an F1 -measure of 66{\%} for symptoms and signs, and pathology categories, being top 1 for subtask 1. For anatomy, dose, exam, mode, moment, substance, treatment, and value categories, it achieved an F1 -measure of 75{\%} (subtask 2). If considered all categories, our model achieved the best result in the challenge, with an F1 -measure of 72{\%}. The use of an ensemble of neural language models proved to be very effective, improving a CRF baseline by up to 28{\%} and a single specialised language model by 4{\%}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="copara-etal-2020-contextualized">
<titleInfo>
<title>Contextualized French Language Models for Biomedical Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jenny</namePart>
<namePart type="family">Copara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julien</namePart>
<namePart type="family">Knafou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nona</namePart>
<namePart type="family">Naderi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Moro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Ruch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Douglas</namePart>
<namePart type="family">Teodoro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Actes de la 6e conférence conjointe Journées d’Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Atelier DÉfi Fouille de Textes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rémi</namePart>
<namePart type="family">Cardon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalia</namePart>
<namePart type="family">Grabar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cyril</namePart>
<namePart type="family">Grouin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Hamon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ATALA et AFCP</publisher>
<place>
<placeTerm type="text">Nancy, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Named entity recognition (NER) is key for biomedical applications as it allows knowledge discovery in free text data. As entities are semantic phrases, their meaning is conditioned to the context to avoid ambiguity. In this work, we explore contextualized language models for NER in French biomedical text as part of the Défi Fouille de Textes challenge. Our best approach achieved an F1 -measure of 66% for symptoms and signs, and pathology categories, being top 1 for subtask 1. For anatomy, dose, exam, mode, moment, substance, treatment, and value categories, it achieved an F1 -measure of 75% (subtask 2). If considered all categories, our model achieved the best result in the challenge, with an F1 -measure of 72%. The use of an ensemble of neural language models proved to be very effective, improving a CRF baseline by up to 28% and a single specialised language model by 4%.</abstract>
<identifier type="citekey">copara-etal-2020-contextualized</identifier>
<location>
<url>https://aclanthology.org/2020.jeptalnrecital-deft.4/</url>
</location>
<part>
<date>2020-6</date>
<extent unit="page">
<start>36</start>
<end>48</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Contextualized French Language Models for Biomedical Named Entity Recognition
%A Copara, Jenny
%A Knafou, Julien
%A Naderi, Nona
%A Moro, Claudia
%A Ruch, Patrick
%A Teodoro, Douglas
%Y Cardon, Rémi
%Y Grabar, Natalia
%Y Grouin, Cyril
%Y Hamon, Thierry
%S Actes de la 6e conférence conjointe Journées d’Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Atelier DÉfi Fouille de Textes
%D 2020
%8 June
%I ATALA et AFCP
%C Nancy, France
%F copara-etal-2020-contextualized
%X Named entity recognition (NER) is key for biomedical applications as it allows knowledge discovery in free text data. As entities are semantic phrases, their meaning is conditioned to the context to avoid ambiguity. In this work, we explore contextualized language models for NER in French biomedical text as part of the Défi Fouille de Textes challenge. Our best approach achieved an F1 -measure of 66% for symptoms and signs, and pathology categories, being top 1 for subtask 1. For anatomy, dose, exam, mode, moment, substance, treatment, and value categories, it achieved an F1 -measure of 75% (subtask 2). If considered all categories, our model achieved the best result in the challenge, with an F1 -measure of 72%. The use of an ensemble of neural language models proved to be very effective, improving a CRF baseline by up to 28% and a single specialised language model by 4%.
%U https://aclanthology.org/2020.jeptalnrecital-deft.4/
%P 36-48
Markdown (Informal)
[Contextualized French Language Models for Biomedical Named Entity Recognition](https://aclanthology.org/2020.jeptalnrecital-deft.4/) (Copara et al., JEP/TALN/RECITAL 2020)
ACL
- Jenny Copara, Julien Knafou, Nona Naderi, Claudia Moro, Patrick Ruch, and Douglas Teodoro. 2020. Contextualized French Language Models for Biomedical Named Entity Recognition. In Actes de la 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Atelier DÉfi Fouille de Textes, pages 36–48, Nancy, France. ATALA et AFCP.