@inproceedings{chauhan-2020-neu,
title = "{NEU} at {WNUT}-2020 Task 2: Data Augmentation To Tell {BERT} That Death Is Not Necessarily Informative",
author = "Chauhan, Kumud",
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-1.64",
doi = "10.18653/v1/2020.wnut-1.64",
pages = "440--443",
abstract = "Millions of people around the world are sharing COVID-19 related information on social media platforms. Since not all the information shared on the social media is useful, a machine learning system to identify informative posts can help users in finding relevant information. In this paper, we present a BERT classifier system for W-NUT2020 Shared Task 2: Identification of Informative COVID-19 English Tweets. Further, we show that BERT exploits some easy signals to identify informative tweets, and adding simple patterns to uninformative tweets drastically degrades BERT performance. In particular, simply adding {``}10 deaths{''} to tweets in dev set, reduces BERT F1- score from 92.63 to 7.28. We also propose a simple data augmentation technique that helps in improving the robustness and generalization ability of the BERT classifier.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chauhan-2020-neu">
<titleInfo>
<title>NEU at WNUT-2020 Task 2: Data Augmentation To Tell BERT That Death Is Not Necessarily Informative</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kumud</namePart>
<namePart type="family">Chauhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-nov</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Millions of people around the world are sharing COVID-19 related information on social media platforms. Since not all the information shared on the social media is useful, a machine learning system to identify informative posts can help users in finding relevant information. In this paper, we present a BERT classifier system for W-NUT2020 Shared Task 2: Identification of Informative COVID-19 English Tweets. Further, we show that BERT exploits some easy signals to identify informative tweets, and adding simple patterns to uninformative tweets drastically degrades BERT performance. In particular, simply adding “10 deaths” to tweets in dev set, reduces BERT F1- score from 92.63 to 7.28. We also propose a simple data augmentation technique that helps in improving the robustness and generalization ability of the BERT classifier.</abstract>
<identifier type="citekey">chauhan-2020-neu</identifier>
<identifier type="doi">10.18653/v1/2020.wnut-1.64</identifier>
<location>
<url>https://aclanthology.org/2020.wnut-1.64</url>
</location>
<part>
<date>2020-nov</date>
<extent unit="page">
<start>440</start>
<end>443</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NEU at WNUT-2020 Task 2: Data Augmentation To Tell BERT That Death Is Not Necessarily Informative
%A Chauhan, Kumud
%S Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)
%D 2020
%8 nov
%I Association for Computational Linguistics
%C Online
%F chauhan-2020-neu
%X Millions of people around the world are sharing COVID-19 related information on social media platforms. Since not all the information shared on the social media is useful, a machine learning system to identify informative posts can help users in finding relevant information. In this paper, we present a BERT classifier system for W-NUT2020 Shared Task 2: Identification of Informative COVID-19 English Tweets. Further, we show that BERT exploits some easy signals to identify informative tweets, and adding simple patterns to uninformative tweets drastically degrades BERT performance. In particular, simply adding “10 deaths” to tweets in dev set, reduces BERT F1- score from 92.63 to 7.28. We also propose a simple data augmentation technique that helps in improving the robustness and generalization ability of the BERT classifier.
%R 10.18653/v1/2020.wnut-1.64
%U https://aclanthology.org/2020.wnut-1.64
%U https://doi.org/10.18653/v1/2020.wnut-1.64
%P 440-443
Markdown (Informal)
[NEU at WNUT-2020 Task 2: Data Augmentation To Tell BERT That Death Is Not Necessarily Informative](https://aclanthology.org/2020.wnut-1.64) (Chauhan, WNUT 2020)
ACL