@inproceedings{hu-verberne-2020-named,
title = "Named Entity Recognition for {C}hinese biomedical patents",
author = "Hu, Yuting and
Verberne, Suzan",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.54",
doi = "10.18653/v1/2020.coling-main.54",
pages = "627--637",
abstract = "There is a large body of work on Biomedical Entity Recognition (Bio-NER) for English but there have only been a few attempts addressing NER for Chinese biomedical texts. Because of the growing amount of Chinese biomedical discoveries being patented, and lack of NER models for patent data, we train and evaluate NER models for the analysis of Chinese biomedical patent data, based on BERT. By doing so, we show the value and potential of this domain-specific NER task. For the evaluation of our methods we built our own Chinese biomedical patents NER dataset, and our optimized model achieved an F1 score of 0.54{\mbox{$\pm$}}0.15. Further biomedical analysis indicates that our solution can help detecting meaningful biomedical entities and novel gene-gene interactions, with limited labeled data, training time and computing power.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hu-verberne-2020-named">
<titleInfo>
<title>Named Entity Recognition for Chinese biomedical patents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuting</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suzan</namePart>
<namePart type="family">Verberne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>There is a large body of work on Biomedical Entity Recognition (Bio-NER) for English but there have only been a few attempts addressing NER for Chinese biomedical texts. Because of the growing amount of Chinese biomedical discoveries being patented, and lack of NER models for patent data, we train and evaluate NER models for the analysis of Chinese biomedical patent data, based on BERT. By doing so, we show the value and potential of this domain-specific NER task. For the evaluation of our methods we built our own Chinese biomedical patents NER dataset, and our optimized model achieved an F1 score of 0.54\pm0.15. Further biomedical analysis indicates that our solution can help detecting meaningful biomedical entities and novel gene-gene interactions, with limited labeled data, training time and computing power.</abstract>
<identifier type="citekey">hu-verberne-2020-named</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.54</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.54</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>627</start>
<end>637</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Named Entity Recognition for Chinese biomedical patents
%A Hu, Yuting
%A Verberne, Suzan
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F hu-verberne-2020-named
%X There is a large body of work on Biomedical Entity Recognition (Bio-NER) for English but there have only been a few attempts addressing NER for Chinese biomedical texts. Because of the growing amount of Chinese biomedical discoveries being patented, and lack of NER models for patent data, we train and evaluate NER models for the analysis of Chinese biomedical patent data, based on BERT. By doing so, we show the value and potential of this domain-specific NER task. For the evaluation of our methods we built our own Chinese biomedical patents NER dataset, and our optimized model achieved an F1 score of 0.54\pm0.15. Further biomedical analysis indicates that our solution can help detecting meaningful biomedical entities and novel gene-gene interactions, with limited labeled data, training time and computing power.
%R 10.18653/v1/2020.coling-main.54
%U https://aclanthology.org/2020.coling-main.54
%U https://doi.org/10.18653/v1/2020.coling-main.54
%P 627-637
Markdown (Informal)
[Named Entity Recognition for Chinese biomedical patents](https://aclanthology.org/2020.coling-main.54) (Hu & Verberne, COLING 2020)
ACL