@inproceedings{hoang-vu-2020-nuts,
title = "Not-{NUT}s at {WNUT}-2020 Task 2: A {BERT}-based System in Identifying Informative {COVID}-19 {E}nglish Tweets",
author = "Hoang, Thai and
Vu, Phuong",
editor = "Xu, Wei and
Ritter, Alan and
Baldwin, Tim and
Rahimi, Afshin",
booktitle = "Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wnut-1.69",
doi = "10.18653/v1/2020.wnut-1.69",
pages = "466--470",
abstract = "As of 2020 when the COVID-19 pandemic is full-blown on a global scale, people{'}s need to have access to legitimate information regarding COVID-19 is more urgent than ever, especially via online media where the abundance of irrelevant information overshadows the more informative ones. In response to such, we proposed a model that, given an English tweet, automatically identifies whether that tweet bears informative content regarding COVID-19 or not. By ensembling different BERTweet model configurations, we have achieved competitive results that are only shy of those by top performing teams by roughly 1{\%} in terms of F1 score on the informative class. In the post-competition period, we have also experimented with various other approaches that potentially boost generalization to a new dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hoang-vu-2020-nuts">
<titleInfo>
<title>Not-NUTs at WNUT-2020 Task 2: A BERT-based System in Identifying Informative COVID-19 English Tweets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thai</namePart>
<namePart type="family">Hoang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phuong</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afshin</namePart>
<namePart type="family">Rahimi</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>As of 2020 when the COVID-19 pandemic is full-blown on a global scale, people’s need to have access to legitimate information regarding COVID-19 is more urgent than ever, especially via online media where the abundance of irrelevant information overshadows the more informative ones. In response to such, we proposed a model that, given an English tweet, automatically identifies whether that tweet bears informative content regarding COVID-19 or not. By ensembling different BERTweet model configurations, we have achieved competitive results that are only shy of those by top performing teams by roughly 1% in terms of F1 score on the informative class. In the post-competition period, we have also experimented with various other approaches that potentially boost generalization to a new dataset.</abstract>
<identifier type="citekey">hoang-vu-2020-nuts</identifier>
<identifier type="doi">10.18653/v1/2020.wnut-1.69</identifier>
<location>
<url>https://aclanthology.org/2020.wnut-1.69</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>466</start>
<end>470</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Not-NUTs at WNUT-2020 Task 2: A BERT-based System in Identifying Informative COVID-19 English Tweets
%A Hoang, Thai
%A Vu, Phuong
%Y Xu, Wei
%Y Ritter, Alan
%Y Baldwin, Tim
%Y Rahimi, Afshin
%S Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F hoang-vu-2020-nuts
%X As of 2020 when the COVID-19 pandemic is full-blown on a global scale, people’s need to have access to legitimate information regarding COVID-19 is more urgent than ever, especially via online media where the abundance of irrelevant information overshadows the more informative ones. In response to such, we proposed a model that, given an English tweet, automatically identifies whether that tweet bears informative content regarding COVID-19 or not. By ensembling different BERTweet model configurations, we have achieved competitive results that are only shy of those by top performing teams by roughly 1% in terms of F1 score on the informative class. In the post-competition period, we have also experimented with various other approaches that potentially boost generalization to a new dataset.
%R 10.18653/v1/2020.wnut-1.69
%U https://aclanthology.org/2020.wnut-1.69
%U https://doi.org/10.18653/v1/2020.wnut-1.69
%P 466-470
Markdown (Informal)
[Not-NUTs at WNUT-2020 Task 2: A BERT-based System in Identifying Informative COVID-19 English Tweets](https://aclanthology.org/2020.wnut-1.69) (Hoang & Vu, WNUT 2020)
ACL