@inproceedings{wadhawan-2020-phonemer,
title = "Phonemer at {WNUT}-2020 Task 2: Sequence Classification Using {COVID} {T}witter {BERT} and Bagging Ensemble Technique based on Plurality Voting",
author = "Wadhawan, Anshul",
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-1.47",
doi = "10.18653/v1/2020.wnut-1.47",
pages = "347--351",
abstract = "This paper presents the approach that we employed to tackle the EMNLP WNUT-2020 Shared Task 2 : Identification of informative COVID-19 English Tweets. The task is to develop a system that automatically identifies whether an English Tweet related to the novel coronavirus (COVID-19) is informative or not. We solve the task in three stages. The first stage involves pre-processing the dataset by filtering only relevant information. This is followed by experimenting with multiple deep learning models like CNNs, RNNs and Transformer based models. In the last stage, we propose an ensemble of the best model trained on different subsets of the provided dataset. Our final approach achieved an F1-score of 0.9037 and we were ranked sixth overall with F1-score as the evaluation criteria.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wadhawan-2020-phonemer">
<titleInfo>
<title>Phonemer at WNUT-2020 Task 2: Sequence Classification Using COVID Twitter BERT and Bagging Ensemble Technique based on Plurality Voting</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anshul</namePart>
<namePart type="family">Wadhawan</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>This paper presents the approach that we employed to tackle the EMNLP WNUT-2020 Shared Task 2 : Identification of informative COVID-19 English Tweets. The task is to develop a system that automatically identifies whether an English Tweet related to the novel coronavirus (COVID-19) is informative or not. We solve the task in three stages. The first stage involves pre-processing the dataset by filtering only relevant information. This is followed by experimenting with multiple deep learning models like CNNs, RNNs and Transformer based models. In the last stage, we propose an ensemble of the best model trained on different subsets of the provided dataset. Our final approach achieved an F1-score of 0.9037 and we were ranked sixth overall with F1-score as the evaluation criteria.</abstract>
<identifier type="citekey">wadhawan-2020-phonemer</identifier>
<identifier type="doi">10.18653/v1/2020.wnut-1.47</identifier>
<location>
<url>https://aclanthology.org/2020.wnut-1.47</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>347</start>
<end>351</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Phonemer at WNUT-2020 Task 2: Sequence Classification Using COVID Twitter BERT and Bagging Ensemble Technique based on Plurality Voting
%A Wadhawan, Anshul
%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 wadhawan-2020-phonemer
%X This paper presents the approach that we employed to tackle the EMNLP WNUT-2020 Shared Task 2 : Identification of informative COVID-19 English Tweets. The task is to develop a system that automatically identifies whether an English Tweet related to the novel coronavirus (COVID-19) is informative or not. We solve the task in three stages. The first stage involves pre-processing the dataset by filtering only relevant information. This is followed by experimenting with multiple deep learning models like CNNs, RNNs and Transformer based models. In the last stage, we propose an ensemble of the best model trained on different subsets of the provided dataset. Our final approach achieved an F1-score of 0.9037 and we were ranked sixth overall with F1-score as the evaluation criteria.
%R 10.18653/v1/2020.wnut-1.47
%U https://aclanthology.org/2020.wnut-1.47
%U https://doi.org/10.18653/v1/2020.wnut-1.47
%P 347-351
Markdown (Informal)
[Phonemer at WNUT-2020 Task 2: Sequence Classification Using COVID Twitter BERT and Bagging Ensemble Technique based on Plurality Voting](https://aclanthology.org/2020.wnut-1.47) (Wadhawan, WNUT 2020)
ACL