@inproceedings{tamayo-etal-2022-nlp,
title = "{NLP}-{CIC}-{WFU} at {S}ocial{D}is{NER}: Disease Mention Extraction in {S}panish Tweets Using Transfer Learning and Search by Propagation",
author = "Tamayo, Antonio and
Gelbukh, Alexander and
Burgos, Diego",
editor = "Gonzalez-Hernandez, Graciela and
Weissenbacher, Davy",
booktitle = "Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop {\&} Shared Task",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.smm4h-1.6",
pages = "19--22",
abstract = "Named entity recognition (e.g., disease mention extraction) is one of the most relevant tasks for data mining in the medical field. Although it is a well-known challenge, the bulk of the efforts to tackle this task have been made using clinical texts commonly written in English. In this work, we present our contribution to the SocialDisNER competition, which consists of a transfer learning approach to extracting disease mentions in a corpus from Twitter written in Spanish. We fine-tuned a model based on mBERT and applied post-processing using regular expressions to propagate the entities identified by the model and enhance disease mention extraction. Our system achieved a competitive strict F1 of 0.851 on the testing data set.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tamayo-etal-2022-nlp">
<titleInfo>
<title>NLP-CIC-WFU at SocialDisNER: Disease Mention Extraction in Spanish Tweets Using Transfer Learning and Search by Propagation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Tamayo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Gelbukh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Burgos</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 Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Graciela</namePart>
<namePart type="family">Gonzalez-Hernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davy</namePart>
<namePart type="family">Weissenbacher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Named entity recognition (e.g., disease mention extraction) is one of the most relevant tasks for data mining in the medical field. Although it is a well-known challenge, the bulk of the efforts to tackle this task have been made using clinical texts commonly written in English. In this work, we present our contribution to the SocialDisNER competition, which consists of a transfer learning approach to extracting disease mentions in a corpus from Twitter written in Spanish. We fine-tuned a model based on mBERT and applied post-processing using regular expressions to propagate the entities identified by the model and enhance disease mention extraction. Our system achieved a competitive strict F1 of 0.851 on the testing data set.</abstract>
<identifier type="citekey">tamayo-etal-2022-nlp</identifier>
<location>
<url>https://aclanthology.org/2022.smm4h-1.6</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>19</start>
<end>22</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NLP-CIC-WFU at SocialDisNER: Disease Mention Extraction in Spanish Tweets Using Transfer Learning and Search by Propagation
%A Tamayo, Antonio
%A Gelbukh, Alexander
%A Burgos, Diego
%Y Gonzalez-Hernandez, Graciela
%Y Weissenbacher, Davy
%S Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task
%D 2022
%8 October
%I Association for Computational Linguistics
%C Gyeongju, Republic of Korea
%F tamayo-etal-2022-nlp
%X Named entity recognition (e.g., disease mention extraction) is one of the most relevant tasks for data mining in the medical field. Although it is a well-known challenge, the bulk of the efforts to tackle this task have been made using clinical texts commonly written in English. In this work, we present our contribution to the SocialDisNER competition, which consists of a transfer learning approach to extracting disease mentions in a corpus from Twitter written in Spanish. We fine-tuned a model based on mBERT and applied post-processing using regular expressions to propagate the entities identified by the model and enhance disease mention extraction. Our system achieved a competitive strict F1 of 0.851 on the testing data set.
%U https://aclanthology.org/2022.smm4h-1.6
%P 19-22
Markdown (Informal)
[NLP-CIC-WFU at SocialDisNER: Disease Mention Extraction in Spanish Tweets Using Transfer Learning and Search by Propagation](https://aclanthology.org/2022.smm4h-1.6) (Tamayo et al., SMM4H 2022)
ACL