@inproceedings{bourgeade-etal-2024-data,
title = "Data Augmentation through Back-Translation for Stereotypes and Irony Detection",
author = "Bourgeade, Tom and
Casola, Silvia and
Mahmoud Wizan, Adel and
Bosco, Cristina",
editor = "Dell'Orletta, Felice and
Lenci, Alessandro and
Montemagni, Simonetta and
Sprugnoli, Rachele",
booktitle = "Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)",
month = dec,
year = "2024",
address = "Pisa, Italy",
publisher = "CEUR Workshop Proceedings",
url = "https://aclanthology.org/2024.clicit-1.12/",
pages = "90--97",
ISBN = "979-12-210-7060-6",
abstract = "Complex linguistic phenomena such as stereotypes or irony are still challenging to detect, particularly due to the lower availability of annotated data. In this paper, we explore Back-Translation (BT) as a data augmentation method to enhance such datasets by artificially introducing semantics-preserving variations. We investigate French and Italian as source languages on two multilingual datasets annotated for the presence of stereotypes or irony and evaluate French/Italian, English, andArabic as pivot languages for the BT process. We also investigate cross-translation, i.e., augmenting one language subset of a multilingual dataset with translated instances from the other languages. We conduct an intrinsic evaluation of the quality of back-translated instances, identifying linguistic or translation model-specific errors that may occur with BT. We also perform an extrinsic evaluation of different data augmentation configurations to train a multilingual Transformer-based classifier forstereotype or irony detection on mono-lingual data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bourgeade-etal-2024-data">
<titleInfo>
<title>Data Augmentation through Back-Translation for Stereotypes and Irony Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Bourgeade</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Silvia</namePart>
<namePart type="family">Casola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adel</namePart>
<namePart type="family">Mahmoud Wizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">Bosco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Felice</namePart>
<namePart type="family">Dell’Orletta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simonetta</namePart>
<namePart type="family">Montemagni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>CEUR Workshop Proceedings</publisher>
<place>
<placeTerm type="text">Pisa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-12-210-7060-6</identifier>
</relatedItem>
<abstract>Complex linguistic phenomena such as stereotypes or irony are still challenging to detect, particularly due to the lower availability of annotated data. In this paper, we explore Back-Translation (BT) as a data augmentation method to enhance such datasets by artificially introducing semantics-preserving variations. We investigate French and Italian as source languages on two multilingual datasets annotated for the presence of stereotypes or irony and evaluate French/Italian, English, andArabic as pivot languages for the BT process. We also investigate cross-translation, i.e., augmenting one language subset of a multilingual dataset with translated instances from the other languages. We conduct an intrinsic evaluation of the quality of back-translated instances, identifying linguistic or translation model-specific errors that may occur with BT. We also perform an extrinsic evaluation of different data augmentation configurations to train a multilingual Transformer-based classifier forstereotype or irony detection on mono-lingual data.</abstract>
<identifier type="citekey">bourgeade-etal-2024-data</identifier>
<location>
<url>https://aclanthology.org/2024.clicit-1.12/</url>
</location>
<part>
<date>2024-12</date>
<extent unit="page">
<start>90</start>
<end>97</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Data Augmentation through Back-Translation for Stereotypes and Irony Detection
%A Bourgeade, Tom
%A Casola, Silvia
%A Mahmoud Wizan, Adel
%A Bosco, Cristina
%Y Dell’Orletta, Felice
%Y Lenci, Alessandro
%Y Montemagni, Simonetta
%Y Sprugnoli, Rachele
%S Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)
%D 2024
%8 December
%I CEUR Workshop Proceedings
%C Pisa, Italy
%@ 979-12-210-7060-6
%F bourgeade-etal-2024-data
%X Complex linguistic phenomena such as stereotypes or irony are still challenging to detect, particularly due to the lower availability of annotated data. In this paper, we explore Back-Translation (BT) as a data augmentation method to enhance such datasets by artificially introducing semantics-preserving variations. We investigate French and Italian as source languages on two multilingual datasets annotated for the presence of stereotypes or irony and evaluate French/Italian, English, andArabic as pivot languages for the BT process. We also investigate cross-translation, i.e., augmenting one language subset of a multilingual dataset with translated instances from the other languages. We conduct an intrinsic evaluation of the quality of back-translated instances, identifying linguistic or translation model-specific errors that may occur with BT. We also perform an extrinsic evaluation of different data augmentation configurations to train a multilingual Transformer-based classifier forstereotype or irony detection on mono-lingual data.
%U https://aclanthology.org/2024.clicit-1.12/
%P 90-97
Markdown (Informal)
[Data Augmentation through Back-Translation for Stereotypes and Irony Detection](https://aclanthology.org/2024.clicit-1.12/) (Bourgeade et al., CLiC-it 2024)
ACL