@inproceedings{chiruzzo-etal-2023-initial,
title = "Initial Experiments for Building a {G}uarani {W}ord{N}et",
author = {Chiruzzo, Luis and
Ag{\"u}ero-Torales, Marvin and
Alvarez, Aldo and
Rodr{\'\i}guez, Yliana},
editor = "Rigau, German and
Bond, Francis and
Rademaker, Alexandre",
booktitle = "Proceedings of the 12th Global Wordnet Conference",
month = jan,
year = "2023",
address = "University of the Basque Country, Donostia - San Sebastian, Basque Country",
publisher = "Global Wordnet Association",
url = "https://aclanthology.org/2023.gwc-1.24",
pages = "197--204",
abstract = "This paper presents a work in progress about creating a Guarani version of the WordNet database. Guarani is an indigenous South American language and is a low-resource language from the NLP perspective. Following the expand approach, we aim to find Guarani lemmas that correspond to the concepts defined in WordNet. We do this through three strategies that try to select the correct lemmas from Guarani-Spanish datasets. We ran them through three different bilingual dictionaries and had native speakers assess the results. This procedure found Guarani lemmas for about 6.5 thousand synsets, including 27{\%} of the base WordNet concepts. However, more work on the quality of the selected words will be needed in order to create a final version of the dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chiruzzo-etal-2023-initial">
<titleInfo>
<title>Initial Experiments for Building a Guarani WordNet</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">Marvin</namePart>
<namePart type="family">Agüero-Torales</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">Yliana</namePart>
<namePart type="family">Rodríguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Global Wordnet Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="family">Rigau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandre</namePart>
<namePart type="family">Rademaker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Global Wordnet Association</publisher>
<place>
<placeTerm type="text">University of the Basque Country, Donostia - San Sebastian, Basque Country</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a work in progress about creating a Guarani version of the WordNet database. Guarani is an indigenous South American language and is a low-resource language from the NLP perspective. Following the expand approach, we aim to find Guarani lemmas that correspond to the concepts defined in WordNet. We do this through three strategies that try to select the correct lemmas from Guarani-Spanish datasets. We ran them through three different bilingual dictionaries and had native speakers assess the results. This procedure found Guarani lemmas for about 6.5 thousand synsets, including 27% of the base WordNet concepts. However, more work on the quality of the selected words will be needed in order to create a final version of the dataset.</abstract>
<identifier type="citekey">chiruzzo-etal-2023-initial</identifier>
<location>
<url>https://aclanthology.org/2023.gwc-1.24</url>
</location>
<part>
<date>2023-01</date>
<extent unit="page">
<start>197</start>
<end>204</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Initial Experiments for Building a Guarani WordNet
%A Chiruzzo, Luis
%A Agüero-Torales, Marvin
%A Alvarez, Aldo
%A Rodríguez, Yliana
%Y Rigau, German
%Y Bond, Francis
%Y Rademaker, Alexandre
%S Proceedings of the 12th Global Wordnet Conference
%D 2023
%8 January
%I Global Wordnet Association
%C University of the Basque Country, Donostia - San Sebastian, Basque Country
%F chiruzzo-etal-2023-initial
%X This paper presents a work in progress about creating a Guarani version of the WordNet database. Guarani is an indigenous South American language and is a low-resource language from the NLP perspective. Following the expand approach, we aim to find Guarani lemmas that correspond to the concepts defined in WordNet. We do this through three strategies that try to select the correct lemmas from Guarani-Spanish datasets. We ran them through three different bilingual dictionaries and had native speakers assess the results. This procedure found Guarani lemmas for about 6.5 thousand synsets, including 27% of the base WordNet concepts. However, more work on the quality of the selected words will be needed in order to create a final version of the dataset.
%U https://aclanthology.org/2023.gwc-1.24
%P 197-204
Markdown (Informal)
[Initial Experiments for Building a Guarani WordNet](https://aclanthology.org/2023.gwc-1.24) (Chiruzzo et al., GWC 2023)
ACL
- Luis Chiruzzo, Marvin Agüero-Torales, Aldo Alvarez, and Yliana Rodríguez. 2023. Initial Experiments for Building a Guarani WordNet. In Proceedings of the 12th Global Wordnet Conference, pages 197–204, University of the Basque Country, Donostia - San Sebastian, Basque Country. Global Wordnet Association.