@inproceedings{awatramani-kumar-2020-linguist,
title = "Linguist Geeks on {WNUT}-2020 Task 2: {COVID}-19 Informative Tweet Identification using Progressive Trained Language Models and Data Augmentation",
author = "Awatramani, Vasudev and
Kumar, Anupam",
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-1.59",
doi = "10.18653/v1/2020.wnut-1.59",
pages = "414--418",
abstract = "Since the outbreak of COVID-19, there has been a surge of digital content on social media. The content ranges from news articles, academic reports, tweets, videos, and even memes. Among such an overabundance of data, it is crucial to distinguish which information is actually informative or merely sensational, redundant or false. This work focuses on developing such a language system that can differentiate between Informative or Uninformative tweets associated with COVID-19 for WNUT-2020 Shared Task 2. For this purpose, we employ deep transfer learning models such as BERT along other techniques such as Noisy Data Augmentation and Progress Training. The approach achieves a competitive F1-score of 0.8715 on the final testing dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="awatramani-kumar-2020-linguist">
<titleInfo>
<title>Linguist Geeks on WNUT-2020 Task 2: COVID-19 Informative Tweet Identification using Progressive Trained Language Models and Data Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vasudev</namePart>
<namePart type="family">Awatramani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anupam</namePart>
<namePart type="family">Kumar</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>Since the outbreak of COVID-19, there has been a surge of digital content on social media. The content ranges from news articles, academic reports, tweets, videos, and even memes. Among such an overabundance of data, it is crucial to distinguish which information is actually informative or merely sensational, redundant or false. This work focuses on developing such a language system that can differentiate between Informative or Uninformative tweets associated with COVID-19 for WNUT-2020 Shared Task 2. For this purpose, we employ deep transfer learning models such as BERT along other techniques such as Noisy Data Augmentation and Progress Training. The approach achieves a competitive F1-score of 0.8715 on the final testing dataset.</abstract>
<identifier type="citekey">awatramani-kumar-2020-linguist</identifier>
<identifier type="doi">10.18653/v1/2020.wnut-1.59</identifier>
<location>
<url>https://aclanthology.org/2020.wnut-1.59</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>414</start>
<end>418</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Linguist Geeks on WNUT-2020 Task 2: COVID-19 Informative Tweet Identification using Progressive Trained Language Models and Data Augmentation
%A Awatramani, Vasudev
%A Kumar, Anupam
%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 awatramani-kumar-2020-linguist
%X Since the outbreak of COVID-19, there has been a surge of digital content on social media. The content ranges from news articles, academic reports, tweets, videos, and even memes. Among such an overabundance of data, it is crucial to distinguish which information is actually informative or merely sensational, redundant or false. This work focuses on developing such a language system that can differentiate between Informative or Uninformative tweets associated with COVID-19 for WNUT-2020 Shared Task 2. For this purpose, we employ deep transfer learning models such as BERT along other techniques such as Noisy Data Augmentation and Progress Training. The approach achieves a competitive F1-score of 0.8715 on the final testing dataset.
%R 10.18653/v1/2020.wnut-1.59
%U https://aclanthology.org/2020.wnut-1.59
%U https://doi.org/10.18653/v1/2020.wnut-1.59
%P 414-418
Markdown (Informal)
[Linguist Geeks on WNUT-2020 Task 2: COVID-19 Informative Tweet Identification using Progressive Trained Language Models and Data Augmentation](https://aclanthology.org/2020.wnut-1.59) (Awatramani & Kumar, WNUT 2020)
ACL