@inproceedings{colic-etal-2020-annotating,
title = "Annotating the Pandemic: Named Entity Recognition and Normalisation in {COVID}-19 Literature",
author = "Colic, Nico and
Furrer, Lenz and
Rinaldi, Fabio",
editor = "Verspoor, Karin and
Cohen, Kevin Bretonnel and
Conway, Michael and
de Bruijn, Berry and
Dredze, Mark and
Mihalcea, Rada and
Wallace, Byron",
booktitle = "Proceedings of the 1st Workshop on {NLP} for {COVID}-19 (Part 2) at {EMNLP} 2020",
month = dec,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.nlpcovid19-2.27",
doi = "10.18653/v1/2020.nlpcovid19-2.27",
abstract = "The COVID-19 pandemic has been accompanied by such an explosive increase in media coverage and scientific publications that researchers find it difficult to keep up. We are presenting a publicly available pipeline to perform named entity recognition and normalisation in parallel to help find relevant publications and to aid in downstream NLP tasks such as text summarisation. In our approach, we are using a dictionary-based system for its high recall in conjunction with two models based on BioBERT for their accuracy. Their outputs are combined according to different strategies depending on the entity type. In addition, we are using a manually crafted dictionary to increase performance for new concepts related to COVID-19. We have previously evaluated our work on the CRAFT corpus, and make the output of our pipeline available on two visualisation platforms.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="colic-etal-2020-annotating">
<titleInfo>
<title>Annotating the Pandemic: Named Entity Recognition and Normalisation in COVID-19 Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nico</namePart>
<namePart type="family">Colic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lenz</namePart>
<namePart type="family">Furrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Rinaldi</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 1st Workshop on NLP for COVID-19 (Part 2) at EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Karin</namePart>
<namePart type="family">Verspoor</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">Michael</namePart>
<namePart type="family">Conway</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Berry</namePart>
<namePart type="family">de Bruijn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Dredze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rada</namePart>
<namePart type="family">Mihalcea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Byron</namePart>
<namePart type="family">Wallace</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 COVID-19 pandemic has been accompanied by such an explosive increase in media coverage and scientific publications that researchers find it difficult to keep up. We are presenting a publicly available pipeline to perform named entity recognition and normalisation in parallel to help find relevant publications and to aid in downstream NLP tasks such as text summarisation. In our approach, we are using a dictionary-based system for its high recall in conjunction with two models based on BioBERT for their accuracy. Their outputs are combined according to different strategies depending on the entity type. In addition, we are using a manually crafted dictionary to increase performance for new concepts related to COVID-19. We have previously evaluated our work on the CRAFT corpus, and make the output of our pipeline available on two visualisation platforms.</abstract>
<identifier type="citekey">colic-etal-2020-annotating</identifier>
<identifier type="doi">10.18653/v1/2020.nlpcovid19-2.27</identifier>
<location>
<url>https://aclanthology.org/2020.nlpcovid19-2.27</url>
</location>
<part>
<date>2020-12</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Annotating the Pandemic: Named Entity Recognition and Normalisation in COVID-19 Literature
%A Colic, Nico
%A Furrer, Lenz
%A Rinaldi, Fabio
%Y Verspoor, Karin
%Y Cohen, Kevin Bretonnel
%Y Conway, Michael
%Y de Bruijn, Berry
%Y Dredze, Mark
%Y Mihalcea, Rada
%Y Wallace, Byron
%S Proceedings of the 1st Workshop on NLP for COVID-19 (Part 2) at EMNLP 2020
%D 2020
%8 December
%I Association for Computational Linguistics
%C Online
%F colic-etal-2020-annotating
%X The COVID-19 pandemic has been accompanied by such an explosive increase in media coverage and scientific publications that researchers find it difficult to keep up. We are presenting a publicly available pipeline to perform named entity recognition and normalisation in parallel to help find relevant publications and to aid in downstream NLP tasks such as text summarisation. In our approach, we are using a dictionary-based system for its high recall in conjunction with two models based on BioBERT for their accuracy. Their outputs are combined according to different strategies depending on the entity type. In addition, we are using a manually crafted dictionary to increase performance for new concepts related to COVID-19. We have previously evaluated our work on the CRAFT corpus, and make the output of our pipeline available on two visualisation platforms.
%R 10.18653/v1/2020.nlpcovid19-2.27
%U https://aclanthology.org/2020.nlpcovid19-2.27
%U https://doi.org/10.18653/v1/2020.nlpcovid19-2.27
Markdown (Informal)
[Annotating the Pandemic: Named Entity Recognition and Normalisation in COVID-19 Literature](https://aclanthology.org/2020.nlpcovid19-2.27) (Colic et al., NLP-COVID19 2020)
ACL