@inproceedings{pimpalkhute-etal-2021-iiitn,
title = "{IIITN} {NLP} at {SMM}4{H} 2021 Tasks: Transformer Models for Classification on Health-Related Imbalanced {T}witter Datasets",
author = "Pimpalkhute, Varad and
Nakhate, Prajwal and
Diwan, Tausif",
booktitle = "Proceedings of the Sixth Social Media Mining for Health ({\#}SMM4H) Workshop and Shared Task",
month = jun,
year = "2021",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.smm4h-1.24",
doi = "10.18653/v1/2021.smm4h-1.24",
pages = "118--122",
abstract = "With increasing users sharing health-related information on social media, there has been a rise in using social media for health monitoring and surveillance. In this paper, we present a system that addresses classic health-related binary classification problems presented in Tasks 1a, 4, and 8 of the 6th edition of Social Media Mining for Health Applications (SMM4H) shared tasks. We developed a system based on RoBERTa (for Task 1a {\&} 4) and BioBERT (for Task 8). Furthermore, we address the challenge of the imbalanced dataset and propose techniques such as undersampling, oversampling, and data augmentation to overcome the imbalanced nature of a given health-related dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pimpalkhute-etal-2021-iiitn">
<titleInfo>
<title>IIITN NLP at SMM4H 2021 Tasks: Transformer Models for Classification on Health-Related Imbalanced Twitter Datasets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Varad</namePart>
<namePart type="family">Pimpalkhute</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prajwal</namePart>
<namePart type="family">Nakhate</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tausif</namePart>
<namePart type="family">Diwan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With increasing users sharing health-related information on social media, there has been a rise in using social media for health monitoring and surveillance. In this paper, we present a system that addresses classic health-related binary classification problems presented in Tasks 1a, 4, and 8 of the 6th edition of Social Media Mining for Health Applications (SMM4H) shared tasks. We developed a system based on RoBERTa (for Task 1a & 4) and BioBERT (for Task 8). Furthermore, we address the challenge of the imbalanced dataset and propose techniques such as undersampling, oversampling, and data augmentation to overcome the imbalanced nature of a given health-related dataset.</abstract>
<identifier type="citekey">pimpalkhute-etal-2021-iiitn</identifier>
<identifier type="doi">10.18653/v1/2021.smm4h-1.24</identifier>
<location>
<url>https://aclanthology.org/2021.smm4h-1.24</url>
</location>
<part>
<date>2021-jun</date>
<extent unit="page">
<start>118</start>
<end>122</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IIITN NLP at SMM4H 2021 Tasks: Transformer Models for Classification on Health-Related Imbalanced Twitter Datasets
%A Pimpalkhute, Varad
%A Nakhate, Prajwal
%A Diwan, Tausif
%S Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task
%D 2021
%8 jun
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F pimpalkhute-etal-2021-iiitn
%X With increasing users sharing health-related information on social media, there has been a rise in using social media for health monitoring and surveillance. In this paper, we present a system that addresses classic health-related binary classification problems presented in Tasks 1a, 4, and 8 of the 6th edition of Social Media Mining for Health Applications (SMM4H) shared tasks. We developed a system based on RoBERTa (for Task 1a & 4) and BioBERT (for Task 8). Furthermore, we address the challenge of the imbalanced dataset and propose techniques such as undersampling, oversampling, and data augmentation to overcome the imbalanced nature of a given health-related dataset.
%R 10.18653/v1/2021.smm4h-1.24
%U https://aclanthology.org/2021.smm4h-1.24
%U https://doi.org/10.18653/v1/2021.smm4h-1.24
%P 118-122
Markdown (Informal)
[IIITN NLP at SMM4H 2021 Tasks: Transformer Models for Classification on Health-Related Imbalanced Twitter Datasets](https://aclanthology.org/2021.smm4h-1.24) (Pimpalkhute et al., SMM4H 2021)
ACL