@inproceedings{grobol-jouitteau-2024-arbres-kenstur,
title = "{ARBRES} Kenstur: A {B}reton-{F}rench Parallel Corpus Rooted in Field Linguistics",
author = {Grobol, Lo{\"\i}c and
Jouitteau, M{\'e}lanie},
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.130",
pages = "1466--1471",
abstract = "ARBRES is an ongoing project of open science implemented as a platform ({``}wikigrammar{''}) documenting both the Breton language itself and the state of research and engineering work in linguistics and NLP. Along its nearly 15 years of operation, it has aggregated a wealth of linguistic data in the form of interlinear glosses with translations illustrating lexical items, grammatical features, dialectal variations... While these glosses were primarily meant for human consumption, their volume and the regular format imposed by the wiki engine used for the website also make them suitable for machine processing. ARBRES Kenstur is a new parallel corpus derived from the glosses in ARBRES, including about 5k phrases and sentences in Breton along with translations in standard French. The nature of the original data {---} sourced from field linguistic inquiries meant to document the structure of Breton {---} leads to a resource that is mechanically more concerned with the internal variations of the language and rare phenomena than typical parallel corpora. Preliminaries experiments in using this corpus show that it can help improve machine translation for Breton, demonstrating that sourcing data from field linguistic documentation can be a way to help provide NLP tools for minority and low-resource languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="grobol-jouitteau-2024-arbres-kenstur">
<titleInfo>
<title>ARBRES Kenstur: A Breton-French Parallel Corpus Rooted in Field Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Loïc</namePart>
<namePart type="family">Grobol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mélanie</namePart>
<namePart type="family">Jouitteau</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 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</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">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</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>ARBRES is an ongoing project of open science implemented as a platform (“wikigrammar”) documenting both the Breton language itself and the state of research and engineering work in linguistics and NLP. Along its nearly 15 years of operation, it has aggregated a wealth of linguistic data in the form of interlinear glosses with translations illustrating lexical items, grammatical features, dialectal variations... While these glosses were primarily meant for human consumption, their volume and the regular format imposed by the wiki engine used for the website also make them suitable for machine processing. ARBRES Kenstur is a new parallel corpus derived from the glosses in ARBRES, including about 5k phrases and sentences in Breton along with translations in standard French. The nature of the original data — sourced from field linguistic inquiries meant to document the structure of Breton — leads to a resource that is mechanically more concerned with the internal variations of the language and rare phenomena than typical parallel corpora. Preliminaries experiments in using this corpus show that it can help improve machine translation for Breton, demonstrating that sourcing data from field linguistic documentation can be a way to help provide NLP tools for minority and low-resource languages.</abstract>
<identifier type="citekey">grobol-jouitteau-2024-arbres-kenstur</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.130</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>1466</start>
<end>1471</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ARBRES Kenstur: A Breton-French Parallel Corpus Rooted in Field Linguistics
%A Grobol, Loïc
%A Jouitteau, Mélanie
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F grobol-jouitteau-2024-arbres-kenstur
%X ARBRES is an ongoing project of open science implemented as a platform (“wikigrammar”) documenting both the Breton language itself and the state of research and engineering work in linguistics and NLP. Along its nearly 15 years of operation, it has aggregated a wealth of linguistic data in the form of interlinear glosses with translations illustrating lexical items, grammatical features, dialectal variations... While these glosses were primarily meant for human consumption, their volume and the regular format imposed by the wiki engine used for the website also make them suitable for machine processing. ARBRES Kenstur is a new parallel corpus derived from the glosses in ARBRES, including about 5k phrases and sentences in Breton along with translations in standard French. The nature of the original data — sourced from field linguistic inquiries meant to document the structure of Breton — leads to a resource that is mechanically more concerned with the internal variations of the language and rare phenomena than typical parallel corpora. Preliminaries experiments in using this corpus show that it can help improve machine translation for Breton, demonstrating that sourcing data from field linguistic documentation can be a way to help provide NLP tools for minority and low-resource languages.
%U https://aclanthology.org/2024.lrec-main.130
%P 1466-1471
Markdown (Informal)
[ARBRES Kenstur: A Breton-French Parallel Corpus Rooted in Field Linguistics](https://aclanthology.org/2024.lrec-main.130) (Grobol & Jouitteau, LREC-COLING 2024)
ACL