@inproceedings{phan-nguyen-2022-simple,
title = "Simple Semantic-based Data Augmentation for Named Entity Recognition in Biomedical Texts",
author = "Phan, Uyen and
Nguyen, Nhung",
editor = "Demner-Fushman, Dina and
Cohen, Kevin Bretonnel and
Ananiadou, Sophia and
Tsujii, Junichi",
booktitle = "Proceedings of the 21st Workshop on Biomedical Language Processing",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.bionlp-1.12",
doi = "10.18653/v1/2022.bionlp-1.12",
pages = "123--129",
abstract = "Data augmentation is important in addressing data sparsity and low resources in NLP. Unlike data augmentation for other tasks such as sentence-level and sentence-pair ones, data augmentation for named entity recognition (NER) requires preserving the semantic of entities. To that end, in this paper we propose a simple semantic-based data augmentation method for biomedical NER. Our method leverages semantic information from pre-trained language models for both entity-level and sentence-level. Experimental results on two datasets: i2b2-2010 (English) and VietBioNER (Vietnamese) showed that the proposed method could improve NER performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="phan-nguyen-2022-simple">
<titleInfo>
<title>Simple Semantic-based Data Augmentation for Named Entity Recognition in Biomedical Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Uyen</namePart>
<namePart type="family">Phan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nhung</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 21st Workshop on Biomedical Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="given">Bretonnel</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Data augmentation is important in addressing data sparsity and low resources in NLP. Unlike data augmentation for other tasks such as sentence-level and sentence-pair ones, data augmentation for named entity recognition (NER) requires preserving the semantic of entities. To that end, in this paper we propose a simple semantic-based data augmentation method for biomedical NER. Our method leverages semantic information from pre-trained language models for both entity-level and sentence-level. Experimental results on two datasets: i2b2-2010 (English) and VietBioNER (Vietnamese) showed that the proposed method could improve NER performance.</abstract>
<identifier type="citekey">phan-nguyen-2022-simple</identifier>
<identifier type="doi">10.18653/v1/2022.bionlp-1.12</identifier>
<location>
<url>https://aclanthology.org/2022.bionlp-1.12</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>123</start>
<end>129</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simple Semantic-based Data Augmentation for Named Entity Recognition in Biomedical Texts
%A Phan, Uyen
%A Nguyen, Nhung
%Y Demner-Fushman, Dina
%Y Cohen, Kevin Bretonnel
%Y Ananiadou, Sophia
%Y Tsujii, Junichi
%S Proceedings of the 21st Workshop on Biomedical Language Processing
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F phan-nguyen-2022-simple
%X Data augmentation is important in addressing data sparsity and low resources in NLP. Unlike data augmentation for other tasks such as sentence-level and sentence-pair ones, data augmentation for named entity recognition (NER) requires preserving the semantic of entities. To that end, in this paper we propose a simple semantic-based data augmentation method for biomedical NER. Our method leverages semantic information from pre-trained language models for both entity-level and sentence-level. Experimental results on two datasets: i2b2-2010 (English) and VietBioNER (Vietnamese) showed that the proposed method could improve NER performance.
%R 10.18653/v1/2022.bionlp-1.12
%U https://aclanthology.org/2022.bionlp-1.12
%U https://doi.org/10.18653/v1/2022.bionlp-1.12
%P 123-129
Markdown (Informal)
[Simple Semantic-based Data Augmentation for Named Entity Recognition in Biomedical Texts](https://aclanthology.org/2022.bionlp-1.12) (Phan & Nguyen, BioNLP 2022)
ACL