@inproceedings{gutierrez-vasques-etal-2016-axolotl,
title = "{A}xolotl: a Web Accessible Parallel Corpus for {S}panish-{N}ahuatl",
author = "Gutierrez-Vasques, Ximena and
Sierra, Gerardo and
Pompa, Isaac Hernandez",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1666",
pages = "4210--4214",
abstract = "This paper describes the project called Axolotl which comprises a Spanish-Nahuatl parallel corpus and its search interface. Spanish and Nahuatl are distant languages spoken in the same country. Due to the scarcity of digital resources, we describe the several problems that arose when compiling this corpus: most of our sources were non-digital books, we faced errors when digitizing the sources and there were difficulties in the sentence alignment process, just to mention some. The documents of the parallel corpus are not homogeneous, they were extracted from different sources, there is dialectal, diachronical, and orthographical variation. Additionally, we present a web search interface that allows to make queries through the whole parallel corpus, the system is capable to retrieve the parallel fragments that contain a word or phrase searched by a user in any of the languages. To our knowledge, this is the first Spanish-Nahuatl public available digital parallel corpus. We think that this resource can be useful to develop language technologies and linguistic studies for this language pair.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gutierrez-vasques-etal-2016-axolotl">
<titleInfo>
<title>Axolotl: a Web Accessible Parallel Corpus for Spanish-Nahuatl</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ximena</namePart>
<namePart type="family">Gutierrez-Vasques</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerardo</namePart>
<namePart type="family">Sierra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isaac</namePart>
<namePart type="given">Hernandez</namePart>
<namePart type="family">Pompa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the project called Axolotl which comprises a Spanish-Nahuatl parallel corpus and its search interface. Spanish and Nahuatl are distant languages spoken in the same country. Due to the scarcity of digital resources, we describe the several problems that arose when compiling this corpus: most of our sources were non-digital books, we faced errors when digitizing the sources and there were difficulties in the sentence alignment process, just to mention some. The documents of the parallel corpus are not homogeneous, they were extracted from different sources, there is dialectal, diachronical, and orthographical variation. Additionally, we present a web search interface that allows to make queries through the whole parallel corpus, the system is capable to retrieve the parallel fragments that contain a word or phrase searched by a user in any of the languages. To our knowledge, this is the first Spanish-Nahuatl public available digital parallel corpus. We think that this resource can be useful to develop language technologies and linguistic studies for this language pair.</abstract>
<identifier type="citekey">gutierrez-vasques-etal-2016-axolotl</identifier>
<location>
<url>https://aclanthology.org/L16-1666</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4210</start>
<end>4214</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Axolotl: a Web Accessible Parallel Corpus for Spanish-Nahuatl
%A Gutierrez-Vasques, Ximena
%A Sierra, Gerardo
%A Pompa, Isaac Hernandez
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F gutierrez-vasques-etal-2016-axolotl
%X This paper describes the project called Axolotl which comprises a Spanish-Nahuatl parallel corpus and its search interface. Spanish and Nahuatl are distant languages spoken in the same country. Due to the scarcity of digital resources, we describe the several problems that arose when compiling this corpus: most of our sources were non-digital books, we faced errors when digitizing the sources and there were difficulties in the sentence alignment process, just to mention some. The documents of the parallel corpus are not homogeneous, they were extracted from different sources, there is dialectal, diachronical, and orthographical variation. Additionally, we present a web search interface that allows to make queries through the whole parallel corpus, the system is capable to retrieve the parallel fragments that contain a word or phrase searched by a user in any of the languages. To our knowledge, this is the first Spanish-Nahuatl public available digital parallel corpus. We think that this resource can be useful to develop language technologies and linguistic studies for this language pair.
%U https://aclanthology.org/L16-1666
%P 4210-4214
Markdown (Informal)
[Axolotl: a Web Accessible Parallel Corpus for Spanish-Nahuatl](https://aclanthology.org/L16-1666) (Gutierrez-Vasques et al., LREC 2016)
ACL
- Ximena Gutierrez-Vasques, Gerardo Sierra, and Isaac Hernandez Pompa. 2016. Axolotl: a Web Accessible Parallel Corpus for Spanish-Nahuatl. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 4210–4214, Portorož, Slovenia. European Language Resources Association (ELRA).