@inproceedings{weisberg-mitelman-etal-2024-code,
title = "Code-Switching and Back-Transliteration Using a Bilingual Model",
author = "Weisberg Mitelman, Daniel and
Dershowitz, Nachum and
Bar, Kfir",
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2024",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-eacl.102/",
pages = "1501--1511",
abstract = "The challenges of automated transliteration and code-switching{--}detection in Judeo-Arabic texts are addressed. We introduce two novel machine-learning models, one focused on transliterating Judeo-Arabic into Arabic, and another aimed at identifying non-Arabic words, predominantly Hebrew and Aramaic. Unlike prior work, our models are based on a bilingual Arabic-Hebrew language model, providing a unique advantage in capturing shared linguistic nuances. Evaluation results show that our models outperform prior solutions for the same tasks. As a practical contribution, we present a comprehensive pipeline capable of taking Judeo-Arabic text, identifying non-Arabic words, and then transliterating the Arabic portions into Arabic script. This work not only advances the state of the art but also offers a valuable toolset for making Judeo-Arabic texts more accessible to a broader Arabic-speaking audience."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="weisberg-mitelman-etal-2024-code">
<titleInfo>
<title>Code-Switching and Back-Transliteration Using a Bilingual Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Weisberg Mitelman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nachum</namePart>
<namePart type="family">Dershowitz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kfir</namePart>
<namePart type="family">Bar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The challenges of automated transliteration and code-switching–detection in Judeo-Arabic texts are addressed. We introduce two novel machine-learning models, one focused on transliterating Judeo-Arabic into Arabic, and another aimed at identifying non-Arabic words, predominantly Hebrew and Aramaic. Unlike prior work, our models are based on a bilingual Arabic-Hebrew language model, providing a unique advantage in capturing shared linguistic nuances. Evaluation results show that our models outperform prior solutions for the same tasks. As a practical contribution, we present a comprehensive pipeline capable of taking Judeo-Arabic text, identifying non-Arabic words, and then transliterating the Arabic portions into Arabic script. This work not only advances the state of the art but also offers a valuable toolset for making Judeo-Arabic texts more accessible to a broader Arabic-speaking audience.</abstract>
<identifier type="citekey">weisberg-mitelman-etal-2024-code</identifier>
<location>
<url>https://aclanthology.org/2024.findings-eacl.102/</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>1501</start>
<end>1511</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Code-Switching and Back-Transliteration Using a Bilingual Model
%A Weisberg Mitelman, Daniel
%A Dershowitz, Nachum
%A Bar, Kfir
%Y Graham, Yvette
%Y Purver, Matthew
%S Findings of the Association for Computational Linguistics: EACL 2024
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F weisberg-mitelman-etal-2024-code
%X The challenges of automated transliteration and code-switching–detection in Judeo-Arabic texts are addressed. We introduce two novel machine-learning models, one focused on transliterating Judeo-Arabic into Arabic, and another aimed at identifying non-Arabic words, predominantly Hebrew and Aramaic. Unlike prior work, our models are based on a bilingual Arabic-Hebrew language model, providing a unique advantage in capturing shared linguistic nuances. Evaluation results show that our models outperform prior solutions for the same tasks. As a practical contribution, we present a comprehensive pipeline capable of taking Judeo-Arabic text, identifying non-Arabic words, and then transliterating the Arabic portions into Arabic script. This work not only advances the state of the art but also offers a valuable toolset for making Judeo-Arabic texts more accessible to a broader Arabic-speaking audience.
%U https://aclanthology.org/2024.findings-eacl.102/
%P 1501-1511
Markdown (Informal)
[Code-Switching and Back-Transliteration Using a Bilingual Model](https://aclanthology.org/2024.findings-eacl.102/) (Weisberg Mitelman et al., Findings 2024)
ACL