@inproceedings{maveli-2020-edinburghnlp,
title = "{E}dinburgh{NLP} at {WNUT}-2020 Task 2: Leveraging Transformers with Generalized Augmentation for Identifying Informativeness in {COVID}-19 Tweets",
author = "Maveli, Nickil",
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-1.67",
doi = "10.18653/v1/2020.wnut-1.67",
pages = "455--461",
abstract = "Twitter has become an important communication channel in times of emergency. The ubiquitousness of smartphones enables people to announce an emergency they{'}re observing in real-time. Because of this, more agencies are interested in programatically monitoring Twitter (disaster relief organizations and news agencies) and therefore recognizing the informativeness of a tweet can help filter noise from large volumes of data. In this paper, we present our submission for WNUT-2020 Task 2: Identification of informative COVID-19 English Tweets. Our most successful model is an ensemble of transformers including RoBERTa, XLNet, and BERTweet trained in a Semi-Supervised Learning (SSL) setting. The proposed system achieves a F1 score of 0.9011 on the test set (ranking 7th on the leaderboard), and shows significant gains in performance compared to a baseline system using fasttext embeddings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maveli-2020-edinburghnlp">
<titleInfo>
<title>EdinburghNLP at WNUT-2020 Task 2: Leveraging Transformers with Generalized Augmentation for Identifying Informativeness in COVID-19 Tweets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nickil</namePart>
<namePart type="family">Maveli</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>Twitter has become an important communication channel in times of emergency. The ubiquitousness of smartphones enables people to announce an emergency they’re observing in real-time. Because of this, more agencies are interested in programatically monitoring Twitter (disaster relief organizations and news agencies) and therefore recognizing the informativeness of a tweet can help filter noise from large volumes of data. In this paper, we present our submission for WNUT-2020 Task 2: Identification of informative COVID-19 English Tweets. Our most successful model is an ensemble of transformers including RoBERTa, XLNet, and BERTweet trained in a Semi-Supervised Learning (SSL) setting. The proposed system achieves a F1 score of 0.9011 on the test set (ranking 7th on the leaderboard), and shows significant gains in performance compared to a baseline system using fasttext embeddings.</abstract>
<identifier type="citekey">maveli-2020-edinburghnlp</identifier>
<identifier type="doi">10.18653/v1/2020.wnut-1.67</identifier>
<location>
<url>https://aclanthology.org/2020.wnut-1.67</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>455</start>
<end>461</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EdinburghNLP at WNUT-2020 Task 2: Leveraging Transformers with Generalized Augmentation for Identifying Informativeness in COVID-19 Tweets
%A Maveli, Nickil
%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 maveli-2020-edinburghnlp
%X Twitter has become an important communication channel in times of emergency. The ubiquitousness of smartphones enables people to announce an emergency they’re observing in real-time. Because of this, more agencies are interested in programatically monitoring Twitter (disaster relief organizations and news agencies) and therefore recognizing the informativeness of a tweet can help filter noise from large volumes of data. In this paper, we present our submission for WNUT-2020 Task 2: Identification of informative COVID-19 English Tweets. Our most successful model is an ensemble of transformers including RoBERTa, XLNet, and BERTweet trained in a Semi-Supervised Learning (SSL) setting. The proposed system achieves a F1 score of 0.9011 on the test set (ranking 7th on the leaderboard), and shows significant gains in performance compared to a baseline system using fasttext embeddings.
%R 10.18653/v1/2020.wnut-1.67
%U https://aclanthology.org/2020.wnut-1.67
%U https://doi.org/10.18653/v1/2020.wnut-1.67
%P 455-461
Markdown (Informal)
[EdinburghNLP at WNUT-2020 Task 2: Leveraging Transformers with Generalized Augmentation for Identifying Informativeness in COVID-19 Tweets](https://aclanthology.org/2020.wnut-1.67) (Maveli, WNUT 2020)
ACL