@inproceedings{trust-etal-2022-uccnlp,
title = "{UCCNLP}@{SMM}4{H}{'}22:Label distribution aware long-tailed learning with post-hoc posterior calibration applied to text classification",
author = "Trust, Paul and
Kadusabe, Provia and
Zahran, Ahmed and
Minghim, Rosane and
Omala, Kizito",
editor = "Gonzalez-Hernandez, Graciela and
Weissenbacher, Davy",
booktitle = "Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop {\&} Shared Task",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.smm4h-1.26",
pages = "90--94",
abstract = "The paper describes our submissions for the Social Media Mining for Health (SMM4H) workshop 2022 shared tasks. We participated in 2 tasks: (1) classification of adverse drug events (ADE) mentions in english tweets (Task-1a) and (2) classification of self-reported intimate partner violence (IPV) on twitter (Task 7). We proposed an approach that uses RoBERTa (A Robustly Optimized BERT Pretraining Approach) fine-tuned with a label distribution-aware margin loss function and post-hoc posterior calibration for robust inference against class imbalance. We achieved a 4{\%} and 1 {\%} increase in performance on IPV and ADE respectively when compared with the traditional fine-tuning strategy with unweighted cross-entropy loss.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="trust-etal-2022-uccnlp">
<titleInfo>
<title>UCCNLP@SMM4H’22:Label distribution aware long-tailed learning with post-hoc posterior calibration applied to text classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Trust</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Provia</namePart>
<namePart type="family">Kadusabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Zahran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rosane</namePart>
<namePart type="family">Minghim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kizito</namePart>
<namePart type="family">Omala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Seventh Workshop on 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">Davy</namePart>
<namePart type="family">Weissenbacher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The paper describes our submissions for the Social Media Mining for Health (SMM4H) workshop 2022 shared tasks. We participated in 2 tasks: (1) classification of adverse drug events (ADE) mentions in english tweets (Task-1a) and (2) classification of self-reported intimate partner violence (IPV) on twitter (Task 7). We proposed an approach that uses RoBERTa (A Robustly Optimized BERT Pretraining Approach) fine-tuned with a label distribution-aware margin loss function and post-hoc posterior calibration for robust inference against class imbalance. We achieved a 4% and 1 % increase in performance on IPV and ADE respectively when compared with the traditional fine-tuning strategy with unweighted cross-entropy loss.</abstract>
<identifier type="citekey">trust-etal-2022-uccnlp</identifier>
<location>
<url>https://aclanthology.org/2022.smm4h-1.26</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>90</start>
<end>94</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UCCNLP@SMM4H’22:Label distribution aware long-tailed learning with post-hoc posterior calibration applied to text classification
%A Trust, Paul
%A Kadusabe, Provia
%A Zahran, Ahmed
%A Minghim, Rosane
%A Omala, Kizito
%Y Gonzalez-Hernandez, Graciela
%Y Weissenbacher, Davy
%S Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task
%D 2022
%8 October
%I Association for Computational Linguistics
%C Gyeongju, Republic of Korea
%F trust-etal-2022-uccnlp
%X The paper describes our submissions for the Social Media Mining for Health (SMM4H) workshop 2022 shared tasks. We participated in 2 tasks: (1) classification of adverse drug events (ADE) mentions in english tweets (Task-1a) and (2) classification of self-reported intimate partner violence (IPV) on twitter (Task 7). We proposed an approach that uses RoBERTa (A Robustly Optimized BERT Pretraining Approach) fine-tuned with a label distribution-aware margin loss function and post-hoc posterior calibration for robust inference against class imbalance. We achieved a 4% and 1 % increase in performance on IPV and ADE respectively when compared with the traditional fine-tuning strategy with unweighted cross-entropy loss.
%U https://aclanthology.org/2022.smm4h-1.26
%P 90-94
Markdown (Informal)
[UCCNLP@SMM4H’22:Label distribution aware long-tailed learning with post-hoc posterior calibration applied to text classification](https://aclanthology.org/2022.smm4h-1.26) (Trust et al., SMM4H 2022)
ACL