<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="boyacioglu-niehues-2024-first">
    <titleInfo>
        <title>The First Parallel Corpus and Neural Machine Translation Model of Western Armenian and English</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ari</namePart>
        <namePart type="given">Nubar</namePart>
        <namePart type="family">Boyacıoğlu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jan</namePart>
        <namePart type="family">Niehues</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 Annual Meeting of the Special Interest Group on Under-resourced Languages @ LREC-COLING 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maite</namePart>
            <namePart type="family">Melero</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sakriani</namePart>
            <namePart type="family">Sakti</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Claudia</namePart>
            <namePart type="family">Soria</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>Western Armenian is a low-resource language spoken by the Armenian Diaspora residing in various places of the world. Although having content on the internet as well as a relatively rich literary heritage for a minority language, there is no data for the machine translation task and only a very limited amount of labeled data for other NLP tasks. In this work, we build the first machine translation system between Western Armenian and English. We explore different techniques for data collection and evaluate their impact in this very low-resource scenario. Then, we build the machine translation system while focusing on the possibilities of performing knowledge transfer from Eastern Armenian. The system is finetuned with the data collected for the first Western Armenian-English parallel corpus, which contains a total of approximately 147k sentence pairs, whose shareable part of 52k examples was made open-source. The best system through the experiments performs with a BLEU score of 29.8 while translating into English and 17 into Western Armenian.</abstract>
    <identifier type="citekey">boyacioglu-niehues-2024-first</identifier>
    <location>
        <url>https://aclanthology.org/2024.sigul-1.42</url>
    </location>
    <part>
        <date>2024-05</date>
        <extent unit="page">
            <start>345</start>
            <end>356</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T The First Parallel Corpus and Neural Machine Translation Model of Western Armenian and English
%A Boyacıoğlu, Ari Nubar
%A Niehues, Jan
%Y Melero, Maite
%Y Sakti, Sakriani
%Y Soria, Claudia
%S Proceedings of the 3rd Annual Meeting of the Special Interest Group on Under-resourced Languages @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F boyacioglu-niehues-2024-first
%X Western Armenian is a low-resource language spoken by the Armenian Diaspora residing in various places of the world. Although having content on the internet as well as a relatively rich literary heritage for a minority language, there is no data for the machine translation task and only a very limited amount of labeled data for other NLP tasks. In this work, we build the first machine translation system between Western Armenian and English. We explore different techniques for data collection and evaluate their impact in this very low-resource scenario. Then, we build the machine translation system while focusing on the possibilities of performing knowledge transfer from Eastern Armenian. The system is finetuned with the data collected for the first Western Armenian-English parallel corpus, which contains a total of approximately 147k sentence pairs, whose shareable part of 52k examples was made open-source. The best system through the experiments performs with a BLEU score of 29.8 while translating into English and 17 into Western Armenian.
%U https://aclanthology.org/2024.sigul-1.42
%P 345-356

Markdown (Informal)

[The First Parallel Corpus and Neural Machine Translation Model of Western Armenian and English](https://aclanthology.org/2024.sigul-1.42) (Boyacıoğlu & Niehues, SIGUL-WS 2024)

• The First Parallel Corpus and Neural Machine Translation Model of Western Armenian and English (Boyacıoğlu & Niehues, SIGUL-WS 2024)

ACL

• Ari Nubar Boyacıoğlu and Jan Niehues. 2024. The First Parallel Corpus and Neural Machine Translation Model of Western Armenian and English. In Proceedings of the 3rd Annual Meeting of the Special Interest Group on Under-resourced Languages @ LREC-COLING 2024, pages 345–356, Torino, Italia. ELRA and ICCL.