@inproceedings{dang-etal-2020-ensemble,
title = "Ensemble {BERT} for Classifying Medication-mentioning Tweets",
author = {Dang, Huong and
Lee, Kahyun and
Henry, Sam and
Uzuner, {\"O}zlem},
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-1.5",
pages = "37--41",
abstract = "Twitter is a valuable source of patient-generated data that has been used in various population health studies. The first step in many of these studies is to identify and capture Twitter messages (tweets) containing medication mentions. In this article, we describe our submission to Task 1 of the Social Media Mining for Health Applications (SMM4H) Shared Task 2020. This task challenged participants to detect tweets that mention medications or dietary supplements in a natural, highly imbalance dataset. Our system combined a handcrafted preprocessing step with an ensemble of 20 BERT-based classifiers generated by dividing the training dataset into subsets using 10-fold cross validation and exploiting two BERT embedding models. Our system ranked first in this task, and improved the average F1 score across all participating teams by 19.07{\%} with a precision, recall, and F1 on the test set of 83.75{\%}, 87.01{\%}, and 85.35{\%} respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dang-etal-2020-ensemble">
<titleInfo>
<title>Ensemble BERT for Classifying Medication-mentioning Tweets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Huong</namePart>
<namePart type="family">Dang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kahyun</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sam</namePart>
<namePart type="family">Henry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Özlem</namePart>
<namePart type="family">Uzuner</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>Twitter is a valuable source of patient-generated data that has been used in various population health studies. The first step in many of these studies is to identify and capture Twitter messages (tweets) containing medication mentions. In this article, we describe our submission to Task 1 of the Social Media Mining for Health Applications (SMM4H) Shared Task 2020. This task challenged participants to detect tweets that mention medications or dietary supplements in a natural, highly imbalance dataset. Our system combined a handcrafted preprocessing step with an ensemble of 20 BERT-based classifiers generated by dividing the training dataset into subsets using 10-fold cross validation and exploiting two BERT embedding models. Our system ranked first in this task, and improved the average F1 score across all participating teams by 19.07% with a precision, recall, and F1 on the test set of 83.75%, 87.01%, and 85.35% respectively.</abstract>
<identifier type="citekey">dang-etal-2020-ensemble</identifier>
<location>
<url>https://aclanthology.org/2020.smm4h-1.5</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>37</start>
<end>41</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Ensemble BERT for Classifying Medication-mentioning Tweets
%A Dang, Huong
%A Lee, Kahyun
%A Henry, Sam
%A Uzuner, Özlem
%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 dang-etal-2020-ensemble
%X Twitter is a valuable source of patient-generated data that has been used in various population health studies. The first step in many of these studies is to identify and capture Twitter messages (tweets) containing medication mentions. In this article, we describe our submission to Task 1 of the Social Media Mining for Health Applications (SMM4H) Shared Task 2020. This task challenged participants to detect tweets that mention medications or dietary supplements in a natural, highly imbalance dataset. Our system combined a handcrafted preprocessing step with an ensemble of 20 BERT-based classifiers generated by dividing the training dataset into subsets using 10-fold cross validation and exploiting two BERT embedding models. Our system ranked first in this task, and improved the average F1 score across all participating teams by 19.07% with a precision, recall, and F1 on the test set of 83.75%, 87.01%, and 85.35% respectively.
%U https://aclanthology.org/2020.smm4h-1.5
%P 37-41
Markdown (Informal)
[Ensemble BERT for Classifying Medication-mentioning Tweets](https://aclanthology.org/2020.smm4h-1.5) (Dang et al., SMM4H 2020)
ACL
- Huong Dang, Kahyun Lee, Sam Henry, and Özlem Uzuner. 2020. Ensemble BERT for Classifying Medication-mentioning Tweets. In Proceedings of the Fifth Social Media Mining for Health Applications Workshop & Shared Task, pages 37–41, Barcelona, Spain (Online). Association for Computational Linguistics.