@inproceedings{gattepaille-2020-far,
title = "How Far Can We Go with Just Out-of-the-box {BERT} Models?",
author = "Gattepaille, Lucie",
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-1.14",
pages = "95--100",
abstract = "Social media have been seen as a promising data source for pharmacovigilance. Howev-er, methods for automatic extraction of Adverse Drug Reactions from social media plat-forms such as Twitter still need further development before they can be included reliably in routine pharmacovigilance practices. As the Bidirectional Encoder Representations from Transformer (BERT) models have shown great performance in many major NLP tasks recently, we decided to test its performance on the SMM4H Shared Tasks 1 to 3, by submitting results of pretrained and fine-tuned BERT models without more added knowledge than the one carried in the training datasets and additional datasets. Our three submissions all ended up above average over all teams{'} submissions: 0.766 F1 for task 1 (15{\%} above the average of 0.665), 0.47 F1 for task 2 (2{\%} above the average of 0.46) and 0.380 F1 score for task 3 (30{\%} above the average of 0.292). Used in many of the high-ranking submission in the 2019 edition of the SMM4H Shared Task, BERT contin-ues to be state-of-the-art in ADR extraction for Twitter data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gattepaille-2020-far">
<titleInfo>
<title>How Far Can We Go with Just Out-of-the-box BERT Models?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lucie</namePart>
<namePart type="family">Gattepaille</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>Social media have been seen as a promising data source for pharmacovigilance. Howev-er, methods for automatic extraction of Adverse Drug Reactions from social media plat-forms such as Twitter still need further development before they can be included reliably in routine pharmacovigilance practices. As the Bidirectional Encoder Representations from Transformer (BERT) models have shown great performance in many major NLP tasks recently, we decided to test its performance on the SMM4H Shared Tasks 1 to 3, by submitting results of pretrained and fine-tuned BERT models without more added knowledge than the one carried in the training datasets and additional datasets. Our three submissions all ended up above average over all teams’ submissions: 0.766 F1 for task 1 (15% above the average of 0.665), 0.47 F1 for task 2 (2% above the average of 0.46) and 0.380 F1 score for task 3 (30% above the average of 0.292). Used in many of the high-ranking submission in the 2019 edition of the SMM4H Shared Task, BERT contin-ues to be state-of-the-art in ADR extraction for Twitter data.</abstract>
<identifier type="citekey">gattepaille-2020-far</identifier>
<location>
<url>https://aclanthology.org/2020.smm4h-1.14</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>95</start>
<end>100</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How Far Can We Go with Just Out-of-the-box BERT Models?
%A Gattepaille, Lucie
%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 gattepaille-2020-far
%X Social media have been seen as a promising data source for pharmacovigilance. Howev-er, methods for automatic extraction of Adverse Drug Reactions from social media plat-forms such as Twitter still need further development before they can be included reliably in routine pharmacovigilance practices. As the Bidirectional Encoder Representations from Transformer (BERT) models have shown great performance in many major NLP tasks recently, we decided to test its performance on the SMM4H Shared Tasks 1 to 3, by submitting results of pretrained and fine-tuned BERT models without more added knowledge than the one carried in the training datasets and additional datasets. Our three submissions all ended up above average over all teams’ submissions: 0.766 F1 for task 1 (15% above the average of 0.665), 0.47 F1 for task 2 (2% above the average of 0.46) and 0.380 F1 score for task 3 (30% above the average of 0.292). Used in many of the high-ranking submission in the 2019 edition of the SMM4H Shared Task, BERT contin-ues to be state-of-the-art in ADR extraction for Twitter data.
%U https://aclanthology.org/2020.smm4h-1.14
%P 95-100
Markdown (Informal)
[How Far Can We Go with Just Out-of-the-box BERT Models?](https://aclanthology.org/2020.smm4h-1.14) (Gattepaille, SMM4H 2020)
ACL