@inproceedings{truong-etal-2021-covid,
title = "{COVID}-19 Named Entity Recognition for {V}ietnamese",
author = "Truong, Thinh Hung and
Dao, Mai Hoang and
Nguyen, Dat Quoc",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.173",
doi = "10.18653/v1/2021.naacl-main.173",
pages = "2146--2153",
abstract = "The current COVID-19 pandemic has lead to the creation of many corpora that facilitate NLP research and downstream applications to help fight the pandemic. However, most of these corpora are exclusively for English. As the pandemic is a global problem, it is worth creating COVID-19 related datasets for languages other than English. In this paper, we present the first manually-annotated COVID-19 domain-specific dataset for Vietnamese. Particularly, our dataset is annotated for the named entity recognition (NER) task with newly-defined entity types that can be used in other future epidemics. Our dataset also contains the largest number of entities compared to existing Vietnamese NER datasets. We empirically conduct experiments using strong baselines on our dataset, and find that: automatic Vietnamese word segmentation helps improve the NER results and the highest performances are obtained by fine-tuning pre-trained language models where the monolingual model PhoBERT for Vietnamese (Nguyen and Nguyen, 2020) produces higher results than the multilingual model XLM-R (Conneau et al., 2020). We publicly release our dataset at: \url{https://github.com/VinAIResearch/PhoNER_COVID19}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="truong-etal-2021-covid">
<titleInfo>
<title>COVID-19 Named Entity Recognition for Vietnamese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thinh</namePart>
<namePart type="given">Hung</namePart>
<namePart type="family">Truong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mai</namePart>
<namePart type="given">Hoang</namePart>
<namePart type="family">Dao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dat</namePart>
<namePart type="given">Quoc</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The current COVID-19 pandemic has lead to the creation of many corpora that facilitate NLP research and downstream applications to help fight the pandemic. However, most of these corpora are exclusively for English. As the pandemic is a global problem, it is worth creating COVID-19 related datasets for languages other than English. In this paper, we present the first manually-annotated COVID-19 domain-specific dataset for Vietnamese. Particularly, our dataset is annotated for the named entity recognition (NER) task with newly-defined entity types that can be used in other future epidemics. Our dataset also contains the largest number of entities compared to existing Vietnamese NER datasets. We empirically conduct experiments using strong baselines on our dataset, and find that: automatic Vietnamese word segmentation helps improve the NER results and the highest performances are obtained by fine-tuning pre-trained language models where the monolingual model PhoBERT for Vietnamese (Nguyen and Nguyen, 2020) produces higher results than the multilingual model XLM-R (Conneau et al., 2020). We publicly release our dataset at: https://github.com/VinAIResearch/PhoNER_COVID19</abstract>
<identifier type="citekey">truong-etal-2021-covid</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.173</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.173</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>2146</start>
<end>2153</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T COVID-19 Named Entity Recognition for Vietnamese
%A Truong, Thinh Hung
%A Dao, Mai Hoang
%A Nguyen, Dat Quoc
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F truong-etal-2021-covid
%X The current COVID-19 pandemic has lead to the creation of many corpora that facilitate NLP research and downstream applications to help fight the pandemic. However, most of these corpora are exclusively for English. As the pandemic is a global problem, it is worth creating COVID-19 related datasets for languages other than English. In this paper, we present the first manually-annotated COVID-19 domain-specific dataset for Vietnamese. Particularly, our dataset is annotated for the named entity recognition (NER) task with newly-defined entity types that can be used in other future epidemics. Our dataset also contains the largest number of entities compared to existing Vietnamese NER datasets. We empirically conduct experiments using strong baselines on our dataset, and find that: automatic Vietnamese word segmentation helps improve the NER results and the highest performances are obtained by fine-tuning pre-trained language models where the monolingual model PhoBERT for Vietnamese (Nguyen and Nguyen, 2020) produces higher results than the multilingual model XLM-R (Conneau et al., 2020). We publicly release our dataset at: https://github.com/VinAIResearch/PhoNER_COVID19
%R 10.18653/v1/2021.naacl-main.173
%U https://aclanthology.org/2021.naacl-main.173
%U https://doi.org/10.18653/v1/2021.naacl-main.173
%P 2146-2153
Markdown (Informal)
[COVID-19 Named Entity Recognition for Vietnamese](https://aclanthology.org/2021.naacl-main.173) (Truong et al., NAACL 2021)
ACL
- Thinh Hung Truong, Mai Hoang Dao, and Dat Quoc Nguyen. 2021. COVID-19 Named Entity Recognition for Vietnamese. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2146–2153, Online. Association for Computational Linguistics.