@inproceedings{kalyan-sangeetha-2020-want,
title = "Want to Identify, Extract and Normalize Adverse Drug Reactions in Tweets? Use {R}o{BERT}a",
author = "Kalyan, Katikapalli Subramanyam and
Sangeetha, Sivanesan",
editor = "Gonzalez-Hernandez, Graciela and
Klein, Ari Z. and
Flores, Ivan and
Weissenbacher, Davy and
Magge, Arjun and
O'Connor, Karen and
Sarker, Abeed and
Minard, Anne-Lyse and
Tutubalina, Elena and
Miftahutdinov, Zulfat and
Alimova, Ilseyar",
booktitle = "Proceedings of the Fifth Social Media Mining for Health Applications Workshop {\&} Shared Task",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.smm4h-1.20/",
pages = "121--124",
abstract = "This paper presents our approach for task 2 and task 3 of Social Media Mining for Health (SMM4H) 2020 shared tasks. In task 2, we have to differentiate adverse drug reaction (ADR) tweets from nonADR tweets and is treated as binary classification. Task 3 involves extracting ADR mentions and then mapping them to MedDRA codes. Extracting ADR mentions is treated as sequence labeling and normalizing ADR mentions is treated as multi-class classification. Our system is based on pre-trained language model RoBERTa and it achieves a) F1-score of 58{\%} in task 2 which is 12{\%} more than the average score b) relaxed F1-score of 70.1{\%} in ADR extraction of task 3 which is 13.7{\%} more than the average score and relaxed F1-score of 35{\%} in ADR extraction + normalization of task 3 which is 5.8{\%} more than the average score. Overall, our models achieve promising results in both the tasks with significant improvements over average scores."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kalyan-sangeetha-2020-want">
<titleInfo>
<title>Want to Identify, Extract and Normalize Adverse Drug Reactions in Tweets? Use RoBERTa</title>
</titleInfo>
<name type="personal">
<namePart type="given">Katikapalli</namePart>
<namePart type="given">Subramanyam</namePart>
<namePart type="family">Kalyan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sivanesan</namePart>
<namePart type="family">Sangeetha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Social Media Mining for Health Applications Workshop & Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Graciela</namePart>
<namePart type="family">Gonzalez-Hernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ari</namePart>
<namePart type="given">Z</namePart>
<namePart type="family">Klein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Flores</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davy</namePart>
<namePart type="family">Weissenbacher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arjun</namePart>
<namePart type="family">Magge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karen</namePart>
<namePart type="family">O’Connor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abeed</namePart>
<namePart type="family">Sarker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne-Lyse</namePart>
<namePart type="family">Minard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Tutubalina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zulfat</namePart>
<namePart type="family">Miftahutdinov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilseyar</namePart>
<namePart type="family">Alimova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents our approach for task 2 and task 3 of Social Media Mining for Health (SMM4H) 2020 shared tasks. In task 2, we have to differentiate adverse drug reaction (ADR) tweets from nonADR tweets and is treated as binary classification. Task 3 involves extracting ADR mentions and then mapping them to MedDRA codes. Extracting ADR mentions is treated as sequence labeling and normalizing ADR mentions is treated as multi-class classification. Our system is based on pre-trained language model RoBERTa and it achieves a) F1-score of 58% in task 2 which is 12% more than the average score b) relaxed F1-score of 70.1% in ADR extraction of task 3 which is 13.7% more than the average score and relaxed F1-score of 35% in ADR extraction + normalization of task 3 which is 5.8% more than the average score. Overall, our models achieve promising results in both the tasks with significant improvements over average scores.</abstract>
<identifier type="citekey">kalyan-sangeetha-2020-want</identifier>
<location>
<url>https://aclanthology.org/2020.smm4h-1.20/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>121</start>
<end>124</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Want to Identify, Extract and Normalize Adverse Drug Reactions in Tweets? Use RoBERTa
%A Kalyan, Katikapalli Subramanyam
%A Sangeetha, Sivanesan
%Y Gonzalez-Hernandez, Graciela
%Y Klein, Ari Z.
%Y Flores, Ivan
%Y Weissenbacher, Davy
%Y Magge, Arjun
%Y O’Connor, Karen
%Y Sarker, Abeed
%Y Minard, Anne-Lyse
%Y Tutubalina, Elena
%Y Miftahutdinov, Zulfat
%Y Alimova, Ilseyar
%S Proceedings of the Fifth Social Media Mining for Health Applications Workshop & Shared Task
%D 2020
%8 December
%I Association for Computational Linguistics
%C Barcelona, Spain (Online)
%F kalyan-sangeetha-2020-want
%X This paper presents our approach for task 2 and task 3 of Social Media Mining for Health (SMM4H) 2020 shared tasks. In task 2, we have to differentiate adverse drug reaction (ADR) tweets from nonADR tweets and is treated as binary classification. Task 3 involves extracting ADR mentions and then mapping them to MedDRA codes. Extracting ADR mentions is treated as sequence labeling and normalizing ADR mentions is treated as multi-class classification. Our system is based on pre-trained language model RoBERTa and it achieves a) F1-score of 58% in task 2 which is 12% more than the average score b) relaxed F1-score of 70.1% in ADR extraction of task 3 which is 13.7% more than the average score and relaxed F1-score of 35% in ADR extraction + normalization of task 3 which is 5.8% more than the average score. Overall, our models achieve promising results in both the tasks with significant improvements over average scores.
%U https://aclanthology.org/2020.smm4h-1.20/
%P 121-124
Markdown (Informal)
[Want to Identify, Extract and Normalize Adverse Drug Reactions in Tweets? Use RoBERTa](https://aclanthology.org/2020.smm4h-1.20/) (Kalyan & Sangeetha, SMM4H 2020)
ACL