@inproceedings{chiruzzo-etal-2022-jojajovai,
title = "Jojajovai: A Parallel {G}uarani-{S}panish Corpus for {MT} Benchmarking",
author = {Chiruzzo, Luis and
G{\'o}ngora, Santiago and
Alvarez, Aldo and
Gim{\'e}nez-Lugo, Gustavo and
Ag{\"u}ero-Torales, Marvin and
Rodr{\'i}guez, Yliana},
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
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.226/",
pages = "2098--2107",
abstract = "This work presents a parallel corpus of Guarani-Spanish text aligned at sentence level. The corpus contains about 30,000 sentence pairs, and is structured as a collection of subsets from different sources, further split into training, development and test sets. A sample of sentences from the test set was manually annotated by native speakers in order to incorporate meta-linguistic annotations about the Guarani dialects present in the corpus and also the correctness of the alignment and translation. We also present some baseline MT experiments and analyze the results in terms of the subsets. We hope this corpus can be used as a benchmark for testing Guarani-Spanish MT systems, and aim to expand and improve the quality of the corpus in future iterations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chiruzzo-etal-2022-jojajovai">
<titleInfo>
<title>Jojajovai: A Parallel Guarani-Spanish Corpus for MT Benchmarking</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">Santiago</namePart>
<namePart type="family">Góngora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aldo</namePart>
<namePart type="family">Alvarez</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>
<name type="personal">
<namePart type="given">Marvin</namePart>
<namePart type="family">Agüero-Torales</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yliana</namePart>
<namePart type="family">Rodríguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth 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">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>
</relatedItem>
<abstract>This work presents a parallel corpus of Guarani-Spanish text aligned at sentence level. The corpus contains about 30,000 sentence pairs, and is structured as a collection of subsets from different sources, further split into training, development and test sets. A sample of sentences from the test set was manually annotated by native speakers in order to incorporate meta-linguistic annotations about the Guarani dialects present in the corpus and also the correctness of the alignment and translation. We also present some baseline MT experiments and analyze the results in terms of the subsets. We hope this corpus can be used as a benchmark for testing Guarani-Spanish MT systems, and aim to expand and improve the quality of the corpus in future iterations.</abstract>
<identifier type="citekey">chiruzzo-etal-2022-jojajovai</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.226/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>2098</start>
<end>2107</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Jojajovai: A Parallel Guarani-Spanish Corpus for MT Benchmarking
%A Chiruzzo, Luis
%A Góngora, Santiago
%A Alvarez, Aldo
%A Giménez-Lugo, Gustavo
%A Agüero-Torales, Marvin
%A Rodríguez, Yliana
%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 Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F chiruzzo-etal-2022-jojajovai
%X This work presents a parallel corpus of Guarani-Spanish text aligned at sentence level. The corpus contains about 30,000 sentence pairs, and is structured as a collection of subsets from different sources, further split into training, development and test sets. A sample of sentences from the test set was manually annotated by native speakers in order to incorporate meta-linguistic annotations about the Guarani dialects present in the corpus and also the correctness of the alignment and translation. We also present some baseline MT experiments and analyze the results in terms of the subsets. We hope this corpus can be used as a benchmark for testing Guarani-Spanish MT systems, and aim to expand and improve the quality of the corpus in future iterations.
%U https://aclanthology.org/2022.lrec-1.226/
%P 2098-2107
Markdown (Informal)
[Jojajovai: A Parallel Guarani-Spanish Corpus for MT Benchmarking](https://aclanthology.org/2022.lrec-1.226/) (Chiruzzo et al., LREC 2022)
ACL
- Luis Chiruzzo, Santiago Góngora, Aldo Alvarez, Gustavo Giménez-Lugo, Marvin Agüero-Torales, and Yliana Rodríguez. 2022. Jojajovai: A Parallel Guarani-Spanish Corpus for MT Benchmarking. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 2098–2107, Marseille, France. European Language Resources Association.