@inproceedings{chiruzzo-etal-2020-development,
title = "Development of a {G}uarani - {S}panish Parallel Corpus",
author = "Chiruzzo, Luis and
Amarilla, Pedro and
R{\'\i}os, Adolfo and
Gim{\'e}nez Lugo, Gustavo",
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-1.320",
pages = "2629--2633",
abstract = "This paper presents the development of a Guarani - Spanish parallel corpus with sentence-level alignment. The Guarani sentences of the corpus use the Jopara Guarani dialect, the dialect of Guarani spoken in Paraguay, which is based on Guarani grammar and may include several Spanish loanwords or neologisms. The corpus has around 14,500 sentence pairs aligned using a semi-automatic process, containing 228,000 Guarani tokens and 336,000 Spanish tokens extracted from web sources.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chiruzzo-etal-2020-development">
<titleInfo>
<title>Development of a Guarani - Spanish Parallel Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="family">Amarilla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adolfo</namePart>
<namePart type="family">Ríos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gustavo</namePart>
<namePart type="family">Giménez Lugo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<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>This paper presents the development of a Guarani - Spanish parallel corpus with sentence-level alignment. The Guarani sentences of the corpus use the Jopara Guarani dialect, the dialect of Guarani spoken in Paraguay, which is based on Guarani grammar and may include several Spanish loanwords or neologisms. The corpus has around 14,500 sentence pairs aligned using a semi-automatic process, containing 228,000 Guarani tokens and 336,000 Spanish tokens extracted from web sources.</abstract>
<identifier type="citekey">chiruzzo-etal-2020-development</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.320</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>2629</start>
<end>2633</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Development of a Guarani - Spanish Parallel Corpus
%A Chiruzzo, Luis
%A Amarilla, Pedro
%A Ríos, Adolfo
%A Giménez Lugo, Gustavo
%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 English
%F chiruzzo-etal-2020-development
%X This paper presents the development of a Guarani - Spanish parallel corpus with sentence-level alignment. The Guarani sentences of the corpus use the Jopara Guarani dialect, the dialect of Guarani spoken in Paraguay, which is based on Guarani grammar and may include several Spanish loanwords or neologisms. The corpus has around 14,500 sentence pairs aligned using a semi-automatic process, containing 228,000 Guarani tokens and 336,000 Spanish tokens extracted from web sources.
%U https://aclanthology.org/2020.lrec-1.320
%P 2629-2633
Markdown (Informal)
[Development of a Guarani - Spanish Parallel Corpus](https://aclanthology.org/2020.lrec-1.320) (Chiruzzo et al., LREC 2020)
ACL
- Luis Chiruzzo, Pedro Amarilla, Adolfo Ríos, and Gustavo Giménez Lugo. 2020. Development of a Guarani - Spanish Parallel Corpus. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 2629–2633, Marseille, France. European Language Resources Association.