@inproceedings{ramesh-etal-2021-bert,
title = "{BERT} based Transformers lead the way in Extraction of Health Information from Social Media",
author = "Ramesh, Sidharth and
Tiwari, Abhiraj and
Choubey, Parthivi and
Kashyap, Saisha and
Khose, Sahil and
Lakara, Kumud and
Singh, Nishesh and
Verma, Ujjwal",
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-1.5",
doi = "10.18653/v1/2021.smm4h-1.5",
pages = "33--38",
abstract = "This paper describes our submissions for the Social Media Mining for Health (SMM4H) 2021 shared tasks. We participated in 2 tasks: (1) Classification, extraction and normalization of adverse drug effect (ADE) mentions in English tweets (Task-1) and (2) Classification of COVID-19 tweets containing symptoms (Task-6). Our approach for the first task uses the language representation model RoBERTa with a binary classification head. For the second task, we use BERTweet, based on RoBERTa. Fine-tuning is performed on the pre-trained models for both tasks. The models are placed on top of a custom domain-specific pre-processing pipeline. Our system ranked first among all the submissions for subtask-1(a) with an F1-score of 61{\%}. For subtask-1(b), our system obtained an F1-score of 50{\%} with improvements up to +8{\%} F1 over the median score across all submissions. The BERTweet model achieved an F1 score of 94{\%} on SMM4H 2021 Task-6.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ramesh-etal-2021-bert">
<titleInfo>
<title>BERT based Transformers lead the way in Extraction of Health Information from Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sidharth</namePart>
<namePart type="family">Ramesh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhiraj</namePart>
<namePart type="family">Tiwari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parthivi</namePart>
<namePart type="family">Choubey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saisha</namePart>
<namePart type="family">Kashyap</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sahil</namePart>
<namePart type="family">Khose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kumud</namePart>
<namePart type="family">Lakara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nishesh</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ujjwal</namePart>
<namePart type="family">Verma</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>This paper describes our submissions for the Social Media Mining for Health (SMM4H) 2021 shared tasks. We participated in 2 tasks: (1) Classification, extraction and normalization of adverse drug effect (ADE) mentions in English tweets (Task-1) and (2) Classification of COVID-19 tweets containing symptoms (Task-6). Our approach for the first task uses the language representation model RoBERTa with a binary classification head. For the second task, we use BERTweet, based on RoBERTa. Fine-tuning is performed on the pre-trained models for both tasks. The models are placed on top of a custom domain-specific pre-processing pipeline. Our system ranked first among all the submissions for subtask-1(a) with an F1-score of 61%. For subtask-1(b), our system obtained an F1-score of 50% with improvements up to +8% F1 over the median score across all submissions. The BERTweet model achieved an F1 score of 94% on SMM4H 2021 Task-6.</abstract>
<identifier type="citekey">ramesh-etal-2021-bert</identifier>
<identifier type="doi">10.18653/v1/2021.smm4h-1.5</identifier>
<location>
<url>https://aclanthology.org/2021.smm4h-1.5</url>
</location>
<part>
<date>2021-jun</date>
<extent unit="page">
<start>33</start>
<end>38</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BERT based Transformers lead the way in Extraction of Health Information from Social Media
%A Ramesh, Sidharth
%A Tiwari, Abhiraj
%A Choubey, Parthivi
%A Kashyap, Saisha
%A Khose, Sahil
%A Lakara, Kumud
%A Singh, Nishesh
%A Verma, Ujjwal
%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 ramesh-etal-2021-bert
%X This paper describes our submissions for the Social Media Mining for Health (SMM4H) 2021 shared tasks. We participated in 2 tasks: (1) Classification, extraction and normalization of adverse drug effect (ADE) mentions in English tweets (Task-1) and (2) Classification of COVID-19 tweets containing symptoms (Task-6). Our approach for the first task uses the language representation model RoBERTa with a binary classification head. For the second task, we use BERTweet, based on RoBERTa. Fine-tuning is performed on the pre-trained models for both tasks. The models are placed on top of a custom domain-specific pre-processing pipeline. Our system ranked first among all the submissions for subtask-1(a) with an F1-score of 61%. For subtask-1(b), our system obtained an F1-score of 50% with improvements up to +8% F1 over the median score across all submissions. The BERTweet model achieved an F1 score of 94% on SMM4H 2021 Task-6.
%R 10.18653/v1/2021.smm4h-1.5
%U https://aclanthology.org/2021.smm4h-1.5
%U https://doi.org/10.18653/v1/2021.smm4h-1.5
%P 33-38
Markdown (Informal)
[BERT based Transformers lead the way in Extraction of Health Information from Social Media](https://aclanthology.org/2021.smm4h-1.5) (Ramesh et al., SMM4H 2021)
ACL
- Sidharth Ramesh, Abhiraj Tiwari, Parthivi Choubey, Saisha Kashyap, Sahil Khose, Kumud Lakara, Nishesh Singh, and Ujjwal Verma. 2021. BERT based Transformers lead the way in Extraction of Health Information from Social Media. In Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task, pages 33–38, Mexico City, Mexico. Association for Computational Linguistics.