@inproceedings{krubinski-etal-2023-multi,
title = "Multi-Parallel Corpus of {N}orth {L}evantine {A}rabic",
author = "Krubi{\'n}ski, Mateusz and
Sellat, Hashem and
Saleh, Shadi and
Posp{\'i}{\v{s}}il, Adam and
Zem{\'a}nek, Petr and
Pecina, Pavel",
editor = "Sawaf, Hassan and
El-Beltagy, Samhaa and
Zaghouani, Wajdi and
Magdy, Walid and
Abdelali, Ahmed and
Tomeh, Nadi and
Abu Farha, Ibrahim and
Habash, Nizar and
Khalifa, Salam and
Keleg, Amr and
Haddad, Hatem and
Zitouni, Imed and
Mrini, Khalil and
Almatham, Rawan",
booktitle = "Proceedings of ArabicNLP 2023",
month = dec,
year = "2023",
address = "Singapore (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.arabicnlp-1.34/",
doi = "10.18653/v1/2023.arabicnlp-1.34",
pages = "411--417",
abstract = "Low-resource Machine Translation (MT) is characterized by the scarce availability of training data and/or standardized evaluation benchmarks. In the context of Dialectal Arabic, recent works introduced several evaluation benchmarks covering both Modern Standard Arabic (MSA) and dialects, mapping, however, mostly to a single Indo-European language - English. In this work, we introduce a multi-lingual corpus consisting of 120,600 multi-parallel sentences in English, French, German, Greek, Spanish, and MSA selected from the OpenSubtitles corpus, which were manually translated into the North Levantine Arabic. By conducting a series of training and fine-tuning experiments, we explore how this novel resource can contribute to the research on Arabic MT."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="krubinski-etal-2023-multi">
<titleInfo>
<title>Multi-Parallel Corpus of North Levantine Arabic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mateusz</namePart>
<namePart type="family">Krubiński</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hashem</namePart>
<namePart type="family">Sellat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shadi</namePart>
<namePart type="family">Saleh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Pospíšil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petr</namePart>
<namePart type="family">Zemánek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Pecina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of ArabicNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Sawaf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walid</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Abu Farha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amr</namePart>
<namePart type="family">Keleg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hatem</namePart>
<namePart type="family">Haddad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Mrini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rawan</namePart>
<namePart type="family">Almatham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Low-resource Machine Translation (MT) is characterized by the scarce availability of training data and/or standardized evaluation benchmarks. In the context of Dialectal Arabic, recent works introduced several evaluation benchmarks covering both Modern Standard Arabic (MSA) and dialects, mapping, however, mostly to a single Indo-European language - English. In this work, we introduce a multi-lingual corpus consisting of 120,600 multi-parallel sentences in English, French, German, Greek, Spanish, and MSA selected from the OpenSubtitles corpus, which were manually translated into the North Levantine Arabic. By conducting a series of training and fine-tuning experiments, we explore how this novel resource can contribute to the research on Arabic MT.</abstract>
<identifier type="citekey">krubinski-etal-2023-multi</identifier>
<identifier type="doi">10.18653/v1/2023.arabicnlp-1.34</identifier>
<location>
<url>https://aclanthology.org/2023.arabicnlp-1.34/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>411</start>
<end>417</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Parallel Corpus of North Levantine Arabic
%A Krubiński, Mateusz
%A Sellat, Hashem
%A Saleh, Shadi
%A Pospíšil, Adam
%A Zemánek, Petr
%A Pecina, Pavel
%Y Sawaf, Hassan
%Y El-Beltagy, Samhaa
%Y Zaghouani, Wajdi
%Y Magdy, Walid
%Y Abdelali, Ahmed
%Y Tomeh, Nadi
%Y Abu Farha, Ibrahim
%Y Habash, Nizar
%Y Khalifa, Salam
%Y Keleg, Amr
%Y Haddad, Hatem
%Y Zitouni, Imed
%Y Mrini, Khalil
%Y Almatham, Rawan
%S Proceedings of ArabicNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore (Hybrid)
%F krubinski-etal-2023-multi
%X Low-resource Machine Translation (MT) is characterized by the scarce availability of training data and/or standardized evaluation benchmarks. In the context of Dialectal Arabic, recent works introduced several evaluation benchmarks covering both Modern Standard Arabic (MSA) and dialects, mapping, however, mostly to a single Indo-European language - English. In this work, we introduce a multi-lingual corpus consisting of 120,600 multi-parallel sentences in English, French, German, Greek, Spanish, and MSA selected from the OpenSubtitles corpus, which were manually translated into the North Levantine Arabic. By conducting a series of training and fine-tuning experiments, we explore how this novel resource can contribute to the research on Arabic MT.
%R 10.18653/v1/2023.arabicnlp-1.34
%U https://aclanthology.org/2023.arabicnlp-1.34/
%U https://doi.org/10.18653/v1/2023.arabicnlp-1.34
%P 411-417
Markdown (Informal)
[Multi-Parallel Corpus of North Levantine Arabic](https://aclanthology.org/2023.arabicnlp-1.34/) (Krubiński et al., ArabicNLP 2023)
ACL
- Mateusz Krubiński, Hashem Sellat, Shadi Saleh, Adam Pospíšil, Petr Zemánek, and Pavel Pecina. 2023. Multi-Parallel Corpus of North Levantine Arabic. In Proceedings of ArabicNLP 2023, pages 411–417, Singapore (Hybrid). Association for Computational Linguistics.