@inproceedings{cercas-curry-etal-2023-milanlp,
title = "{M}ila{NLP} at {S}em{E}val-2023 Task 10: Ensembling Domain-Adapted and Regularized Pretrained Language Models for Robust Sexism Detection",
author = "Cercas Curry, Amanda and
Attanasio, Giuseppe and
Nozza, Debora and
Hovy, Dirk",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Da San Martino, Giovanni and
Tayyar Madabushi, Harish and
Kumar, Ritesh and
Sartori, Elisa},
booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.semeval-1.285",
doi = "10.18653/v1/2023.semeval-1.285",
pages = "2067--2074",
abstract = "We present the system proposed by the MilaNLP team for the Explainable Detection of Online Sexism (EDOS) shared task. We propose an ensemble modeling approach to combine different classifiers trained with domain adaptation objectives and standard fine-tuning. Our results show that the ensemble is more robust than individual models and that regularized models generate more {``}conservative{''} predictions, mitigating the effects of lexical overfitting.However, our error analysis also finds that many of the misclassified instances are debatable, raising questions about the objective annotatability of hate speech data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cercas-curry-etal-2023-milanlp">
<titleInfo>
<title>MilaNLP at SemEval-2023 Task 10: Ensembling Domain-Adapted and Regularized Pretrained Language Models for Robust Sexism Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amanda</namePart>
<namePart type="family">Cercas Curry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Attanasio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debora</namePart>
<namePart type="family">Nozza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dirk</namePart>
<namePart type="family">Hovy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Sartori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present the system proposed by the MilaNLP team for the Explainable Detection of Online Sexism (EDOS) shared task. We propose an ensemble modeling approach to combine different classifiers trained with domain adaptation objectives and standard fine-tuning. Our results show that the ensemble is more robust than individual models and that regularized models generate more “conservative” predictions, mitigating the effects of lexical overfitting.However, our error analysis also finds that many of the misclassified instances are debatable, raising questions about the objective annotatability of hate speech data.</abstract>
<identifier type="citekey">cercas-curry-etal-2023-milanlp</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.285</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.285</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>2067</start>
<end>2074</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MilaNLP at SemEval-2023 Task 10: Ensembling Domain-Adapted and Regularized Pretrained Language Models for Robust Sexism Detection
%A Cercas Curry, Amanda
%A Attanasio, Giuseppe
%A Nozza, Debora
%A Hovy, Dirk
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Da San Martino, Giovanni
%Y Tayyar Madabushi, Harish
%Y Kumar, Ritesh
%Y Sartori, Elisa
%S Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F cercas-curry-etal-2023-milanlp
%X We present the system proposed by the MilaNLP team for the Explainable Detection of Online Sexism (EDOS) shared task. We propose an ensemble modeling approach to combine different classifiers trained with domain adaptation objectives and standard fine-tuning. Our results show that the ensemble is more robust than individual models and that regularized models generate more “conservative” predictions, mitigating the effects of lexical overfitting.However, our error analysis also finds that many of the misclassified instances are debatable, raising questions about the objective annotatability of hate speech data.
%R 10.18653/v1/2023.semeval-1.285
%U https://aclanthology.org/2023.semeval-1.285
%U https://doi.org/10.18653/v1/2023.semeval-1.285
%P 2067-2074
Markdown (Informal)
[MilaNLP at SemEval-2023 Task 10: Ensembling Domain-Adapted and Regularized Pretrained Language Models for Robust Sexism Detection](https://aclanthology.org/2023.semeval-1.285) (Cercas Curry et al., SemEval 2023)
ACL