@inproceedings{dmonte-etal-2025-machine,
title = "Does Machine Translation Impact Offensive Language Identification? The Case of {I}ndo-{A}ryan Languages",
author = "Dmonte, Alphaeus and
Satapara, Shrey and
Alsudais, Rehab and
Ranasinghe, Tharindu and
Zampieri, Marcos",
editor = "Hettiarachchi, Hansi and
Ranasinghe, Tharindu and
Rayson, Paul and
Mitkov, Ruslan and
Gaber, Mohamed and
Premasiri, Damith and
Tan, Fiona Anting and
Uyangodage, Lasitha",
booktitle = "Proceedings of the First Workshop on Language Models for Low-Resource Languages",
month = jan,
year = "2025",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.loreslm-1.34/",
pages = "460--468",
abstract = "The accessibility to social media platforms can be improved with the use of machine translation (MT). Non-standard features present in user-generated on social media content such as hashtags, emojis, and alternative spellings can lead to mistranslated instances by the MT systems. In this paper, we investigate the impact of MT on offensive language identification in Indo-Aryan languages. We use both original and MT datasets to evaluate the performance of various offensive language models. Our evaluation indicates that offensive language identification models achieve superior performance on original data than on MT data, and that the models trained on MT data identify offensive language more precisely on MT data than the models trained on original data."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dmonte-etal-2025-machine">
<titleInfo>
<title>Does Machine Translation Impact Offensive Language Identification? The Case of Indo-Aryan Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alphaeus</namePart>
<namePart type="family">Dmonte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shrey</namePart>
<namePart type="family">Satapara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rehab</namePart>
<namePart type="family">Alsudais</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Language Models for Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hansi</namePart>
<namePart type="family">Hettiarachchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Gaber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damith</namePart>
<namePart type="family">Premasiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fiona</namePart>
<namePart type="given">Anting</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lasitha</namePart>
<namePart type="family">Uyangodage</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The accessibility to social media platforms can be improved with the use of machine translation (MT). Non-standard features present in user-generated on social media content such as hashtags, emojis, and alternative spellings can lead to mistranslated instances by the MT systems. In this paper, we investigate the impact of MT on offensive language identification in Indo-Aryan languages. We use both original and MT datasets to evaluate the performance of various offensive language models. Our evaluation indicates that offensive language identification models achieve superior performance on original data than on MT data, and that the models trained on MT data identify offensive language more precisely on MT data than the models trained on original data.</abstract>
<identifier type="citekey">dmonte-etal-2025-machine</identifier>
<location>
<url>https://aclanthology.org/2025.loreslm-1.34/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>460</start>
<end>468</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Does Machine Translation Impact Offensive Language Identification? The Case of Indo-Aryan Languages
%A Dmonte, Alphaeus
%A Satapara, Shrey
%A Alsudais, Rehab
%A Ranasinghe, Tharindu
%A Zampieri, Marcos
%Y Hettiarachchi, Hansi
%Y Ranasinghe, Tharindu
%Y Rayson, Paul
%Y Mitkov, Ruslan
%Y Gaber, Mohamed
%Y Premasiri, Damith
%Y Tan, Fiona Anting
%Y Uyangodage, Lasitha
%S Proceedings of the First Workshop on Language Models for Low-Resource Languages
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F dmonte-etal-2025-machine
%X The accessibility to social media platforms can be improved with the use of machine translation (MT). Non-standard features present in user-generated on social media content such as hashtags, emojis, and alternative spellings can lead to mistranslated instances by the MT systems. In this paper, we investigate the impact of MT on offensive language identification in Indo-Aryan languages. We use both original and MT datasets to evaluate the performance of various offensive language models. Our evaluation indicates that offensive language identification models achieve superior performance on original data than on MT data, and that the models trained on MT data identify offensive language more precisely on MT data than the models trained on original data.
%U https://aclanthology.org/2025.loreslm-1.34/
%P 460-468
Markdown (Informal)
[Does Machine Translation Impact Offensive Language Identification? The Case of Indo-Aryan Languages](https://aclanthology.org/2025.loreslm-1.34/) (Dmonte et al., LoResLM 2025)
ACL