@inproceedings{yang-etal-2020-imec,
title = "imec-{ETRO}-{VUB} at {W}-{NUT} 2020 Shared Task-3: A multilabel {BERT}-based system for predicting {COVID}-19 events",
author = "Yang, Xiangyu and
Bekoulis, Giannis and
Deligiannis, Nikos",
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-1.77",
doi = "10.18653/v1/2020.wnut-1.77",
pages = "505--513",
abstract = "In this paper, we present our system designed to address the W-NUT 2020 shared task for COVID-19 Event Extraction from Twitter. To mitigate the noisy nature of the Twitter stream, our system makes use of the COVID-Twitter-BERT (CT-BERT), which is a language model pre-trained on a large corpus of COVID-19 related Twitter messages. Our system is trained on the COVID-19 Twitter Event Corpus and is able to identify relevant text spans that answer pre-defined questions (i.e., slot types) for five COVID-19 related events (i.e., TESTED POSITIVE, TESTED NEGATIVE, CAN-NOT-TEST, DEATH and CURE {\&} PREVENTION). We have experimented with different architectures; our best performing model relies on a multilabel classifier on top of the CT-BERT model that jointly trains all the slot types for a single event. Our experimental results indicate that our Multilabel-CT-BERT system outperforms the baseline methods by 7 percentage points in terms of micro average F1 score. Our model ranked as 4th in the shared task leaderboard.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2020-imec">
<titleInfo>
<title>imec-ETRO-VUB at W-NUT 2020 Shared Task-3: A multilabel BERT-based system for predicting COVID-19 events</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiangyu</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giannis</namePart>
<namePart type="family">Bekoulis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikos</namePart>
<namePart type="family">Deligiannis</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>In this paper, we present our system designed to address the W-NUT 2020 shared task for COVID-19 Event Extraction from Twitter. To mitigate the noisy nature of the Twitter stream, our system makes use of the COVID-Twitter-BERT (CT-BERT), which is a language model pre-trained on a large corpus of COVID-19 related Twitter messages. Our system is trained on the COVID-19 Twitter Event Corpus and is able to identify relevant text spans that answer pre-defined questions (i.e., slot types) for five COVID-19 related events (i.e., TESTED POSITIVE, TESTED NEGATIVE, CAN-NOT-TEST, DEATH and CURE & PREVENTION). We have experimented with different architectures; our best performing model relies on a multilabel classifier on top of the CT-BERT model that jointly trains all the slot types for a single event. Our experimental results indicate that our Multilabel-CT-BERT system outperforms the baseline methods by 7 percentage points in terms of micro average F1 score. Our model ranked as 4th in the shared task leaderboard.</abstract>
<identifier type="citekey">yang-etal-2020-imec</identifier>
<identifier type="doi">10.18653/v1/2020.wnut-1.77</identifier>
<location>
<url>https://aclanthology.org/2020.wnut-1.77</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>505</start>
<end>513</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T imec-ETRO-VUB at W-NUT 2020 Shared Task-3: A multilabel BERT-based system for predicting COVID-19 events
%A Yang, Xiangyu
%A Bekoulis, Giannis
%A Deligiannis, Nikos
%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 yang-etal-2020-imec
%X In this paper, we present our system designed to address the W-NUT 2020 shared task for COVID-19 Event Extraction from Twitter. To mitigate the noisy nature of the Twitter stream, our system makes use of the COVID-Twitter-BERT (CT-BERT), which is a language model pre-trained on a large corpus of COVID-19 related Twitter messages. Our system is trained on the COVID-19 Twitter Event Corpus and is able to identify relevant text spans that answer pre-defined questions (i.e., slot types) for five COVID-19 related events (i.e., TESTED POSITIVE, TESTED NEGATIVE, CAN-NOT-TEST, DEATH and CURE & PREVENTION). We have experimented with different architectures; our best performing model relies on a multilabel classifier on top of the CT-BERT model that jointly trains all the slot types for a single event. Our experimental results indicate that our Multilabel-CT-BERT system outperforms the baseline methods by 7 percentage points in terms of micro average F1 score. Our model ranked as 4th in the shared task leaderboard.
%R 10.18653/v1/2020.wnut-1.77
%U https://aclanthology.org/2020.wnut-1.77
%U https://doi.org/10.18653/v1/2020.wnut-1.77
%P 505-513
Markdown (Informal)
[imec-ETRO-VUB at W-NUT 2020 Shared Task-3: A multilabel BERT-based system for predicting COVID-19 events](https://aclanthology.org/2020.wnut-1.77) (Yang et al., WNUT 2020)
ACL