@inproceedings{mastromattei-zanzotto-2024-linguistic,
title = "Linguistic Fingerprint in Transformer Models: How Language Variation Influences Parameter Selection in Irony Detection",
author = "Mastromattei, Michele and
Zanzotto, Fabio Massimo",
editor = "Abercrombie, Gavin and
Basile, Valerio and
Bernadi, Davide and
Dudy, Shiran and
Frenda, Simona and
Havens, Lucy and
Tonelli, Sara",
booktitle = "Proceedings of the 3rd Workshop on Perspectivist Approaches to NLP (NLPerspectives) @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.nlperspectives-1.14/",
pages = "123--130",
abstract = "This paper explores the correlation between linguistic diversity, sentiment analysis and transformer model architectures. We aim to investigate how different English variations impact transformer-based models for irony detection. To conduct our study, we used the EPIC corpus to extract five diverse English variation-specific datasets and applied the KEN pruning algorithm on five different architectures. Our results reveal several similarities between optimal subnetworks, which provide insights into the linguistic variations that share strong resemblances and those that exhibit greater dissimilarities. We discovered that optimal subnetworks across models share at least 60{\%} of their parameters, emphasizing the significance of parameter values in capturing and interpreting linguistic variations. This study highlights the inherent structural similarities between models trained on different variants of the same language and also the critical role of parameter values in capturing these nuances."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mastromattei-zanzotto-2024-linguistic">
<titleInfo>
<title>Linguistic Fingerprint in Transformer Models: How Language Variation Influences Parameter Selection in Irony Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michele</namePart>
<namePart type="family">Mastromattei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="given">Massimo</namePart>
<namePart type="family">Zanzotto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Perspectivist Approaches to NLP (NLPerspectives) @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gavin</namePart>
<namePart type="family">Abercrombie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valerio</namePart>
<namePart type="family">Basile</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davide</namePart>
<namePart type="family">Bernadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiran</namePart>
<namePart type="family">Dudy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simona</namePart>
<namePart type="family">Frenda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucy</namePart>
<namePart type="family">Havens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Tonelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper explores the correlation between linguistic diversity, sentiment analysis and transformer model architectures. We aim to investigate how different English variations impact transformer-based models for irony detection. To conduct our study, we used the EPIC corpus to extract five diverse English variation-specific datasets and applied the KEN pruning algorithm on five different architectures. Our results reveal several similarities between optimal subnetworks, which provide insights into the linguistic variations that share strong resemblances and those that exhibit greater dissimilarities. We discovered that optimal subnetworks across models share at least 60% of their parameters, emphasizing the significance of parameter values in capturing and interpreting linguistic variations. This study highlights the inherent structural similarities between models trained on different variants of the same language and also the critical role of parameter values in capturing these nuances.</abstract>
<identifier type="citekey">mastromattei-zanzotto-2024-linguistic</identifier>
<location>
<url>https://aclanthology.org/2024.nlperspectives-1.14/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>123</start>
<end>130</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Linguistic Fingerprint in Transformer Models: How Language Variation Influences Parameter Selection in Irony Detection
%A Mastromattei, Michele
%A Zanzotto, Fabio Massimo
%Y Abercrombie, Gavin
%Y Basile, Valerio
%Y Bernadi, Davide
%Y Dudy, Shiran
%Y Frenda, Simona
%Y Havens, Lucy
%Y Tonelli, Sara
%S Proceedings of the 3rd Workshop on Perspectivist Approaches to NLP (NLPerspectives) @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F mastromattei-zanzotto-2024-linguistic
%X This paper explores the correlation between linguistic diversity, sentiment analysis and transformer model architectures. We aim to investigate how different English variations impact transformer-based models for irony detection. To conduct our study, we used the EPIC corpus to extract five diverse English variation-specific datasets and applied the KEN pruning algorithm on five different architectures. Our results reveal several similarities between optimal subnetworks, which provide insights into the linguistic variations that share strong resemblances and those that exhibit greater dissimilarities. We discovered that optimal subnetworks across models share at least 60% of their parameters, emphasizing the significance of parameter values in capturing and interpreting linguistic variations. This study highlights the inherent structural similarities between models trained on different variants of the same language and also the critical role of parameter values in capturing these nuances.
%U https://aclanthology.org/2024.nlperspectives-1.14/
%P 123-130
Markdown (Informal)
[Linguistic Fingerprint in Transformer Models: How Language Variation Influences Parameter Selection in Irony Detection](https://aclanthology.org/2024.nlperspectives-1.14/) (Mastromattei & Zanzotto, NLPerspectives 2024)
ACL