@inproceedings{sierra-martinez-etal-2020-cplm,
title = "{CPLM}, a Parallel Corpus for {M}exican Languages: Development and Interface",
author = "Sierra Mart{\'i}nez, Gerardo and
Monta{\~n}o, Cynthia and
Bel-Enguix, Gemma and
C{\'o}rdova, Diego and
Mota Montoya, Margarita",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.360/",
pages = "2947--2952",
language = "eng",
ISBN = "979-10-95546-34-4",
abstract = "Mexico is a Spanish speaking country that has a great language diversity, with 68 linguistic groups and 364 varieties. As they face a lack of representation in education, government, public services and media, they present high levels of endangerment. Due to the lack of data available on social media and the internet, few technologies have been developed for these languages. To analyze different linguistic phenomena in the country, the Language Engineering Group developed the Corpus Paralelo de Lenguas Mexicanas (CPLM) [The Mexican Languages Parallel Corpus], a collaborative parallel corpus for the low-resourced languages of Mexico. The CPLM aligns Spanish with six indigenous languages: Maya, Ch`ol, Mazatec, Mixtec, Otomi, and Nahuatl. First, this paper describes the process of building the CPLM: text searching, digitalization and alignment process. Furthermore, we present some difficulties regarding dialectal and orthographic variations. Second, we present the interface and types of searching as well as the use of filters."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sierra-martinez-etal-2020-cplm">
<titleInfo>
<title>CPLM, a Parallel Corpus for Mexican Languages: Development and Interface</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gerardo</namePart>
<namePart type="family">Sierra Martínez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cynthia</namePart>
<namePart type="family">Montaño</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gemma</namePart>
<namePart type="family">Bel-Enguix</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Córdova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Margarita</namePart>
<namePart type="family">Mota Montoya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Mexico is a Spanish speaking country that has a great language diversity, with 68 linguistic groups and 364 varieties. As they face a lack of representation in education, government, public services and media, they present high levels of endangerment. Due to the lack of data available on social media and the internet, few technologies have been developed for these languages. To analyze different linguistic phenomena in the country, the Language Engineering Group developed the Corpus Paralelo de Lenguas Mexicanas (CPLM) [The Mexican Languages Parallel Corpus], a collaborative parallel corpus for the low-resourced languages of Mexico. The CPLM aligns Spanish with six indigenous languages: Maya, Ch‘ol, Mazatec, Mixtec, Otomi, and Nahuatl. First, this paper describes the process of building the CPLM: text searching, digitalization and alignment process. Furthermore, we present some difficulties regarding dialectal and orthographic variations. Second, we present the interface and types of searching as well as the use of filters.</abstract>
<identifier type="citekey">sierra-martinez-etal-2020-cplm</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.360/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>2947</start>
<end>2952</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CPLM, a Parallel Corpus for Mexican Languages: Development and Interface
%A Sierra Martínez, Gerardo
%A Montaño, Cynthia
%A Bel-Enguix, Gemma
%A Córdova, Diego
%A Mota Montoya, Margarita
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G eng
%F sierra-martinez-etal-2020-cplm
%X Mexico is a Spanish speaking country that has a great language diversity, with 68 linguistic groups and 364 varieties. As they face a lack of representation in education, government, public services and media, they present high levels of endangerment. Due to the lack of data available on social media and the internet, few technologies have been developed for these languages. To analyze different linguistic phenomena in the country, the Language Engineering Group developed the Corpus Paralelo de Lenguas Mexicanas (CPLM) [The Mexican Languages Parallel Corpus], a collaborative parallel corpus for the low-resourced languages of Mexico. The CPLM aligns Spanish with six indigenous languages: Maya, Ch‘ol, Mazatec, Mixtec, Otomi, and Nahuatl. First, this paper describes the process of building the CPLM: text searching, digitalization and alignment process. Furthermore, we present some difficulties regarding dialectal and orthographic variations. Second, we present the interface and types of searching as well as the use of filters.
%U https://aclanthology.org/2020.lrec-1.360/
%P 2947-2952
Markdown (Informal)
[CPLM, a Parallel Corpus for Mexican Languages: Development and Interface](https://aclanthology.org/2020.lrec-1.360/) (Sierra Martínez et al., LREC 2020)
ACL