@inproceedings{himoro-pareja-lora-2022-preliminary,
title = "Preliminary Results on the Evaluation of Computational Tools for the Analysis of {Q}uechua and {A}ymara",
author = "Himoro, Marcelo Yuji and
Pareja-Lora, Antonio",
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-1.584",
pages = "5450--5459",
abstract = "This research has focused on evaluating the existing open-source morphological analyzers for two of the most widely spoken indigenous macrolanguages in South America, namely Quechua and Aymara. Firstly, we have evaluated their performance (precision, recall and F1 score) for the individual languages for which they were developed (Cuzco Quechua and Aymara). Secondly, in order to assess how these tools handle other individual languages of the macrolanguage, we have extracted some sample text from school textbooks and educational resources. This sample text was edited in the different countries where these macrolanguages are spoken (Colombia, Ecuador, Peru, Bolivia, Chile and Argentina for Quechua; and Bolivia, Peru and Chile for Aymara), and it includes their different standardized forms (10 individual languages of Quechua and 3 of Aymara). Processing this text by means of the tools, we have (i) calculated their coverage (number of words recognized and analyzed) and (ii) studied in detail the cases for which each tool was unable to generate any output. Finally, we discuss different ways in which these tools could be optimized, either to improve their performances or, in the specific case of Quechua, to cover more individual languages of this macrolanguage in future works as well.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="himoro-pareja-lora-2022-preliminary">
<titleInfo>
<title>Preliminary Results on the Evaluation of Computational Tools for the Analysis of Quechua and Aymara</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcelo</namePart>
<namePart type="given">Yuji</namePart>
<namePart type="family">Himoro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Pareja-Lora</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 research has focused on evaluating the existing open-source morphological analyzers for two of the most widely spoken indigenous macrolanguages in South America, namely Quechua and Aymara. Firstly, we have evaluated their performance (precision, recall and F1 score) for the individual languages for which they were developed (Cuzco Quechua and Aymara). Secondly, in order to assess how these tools handle other individual languages of the macrolanguage, we have extracted some sample text from school textbooks and educational resources. This sample text was edited in the different countries where these macrolanguages are spoken (Colombia, Ecuador, Peru, Bolivia, Chile and Argentina for Quechua; and Bolivia, Peru and Chile for Aymara), and it includes their different standardized forms (10 individual languages of Quechua and 3 of Aymara). Processing this text by means of the tools, we have (i) calculated their coverage (number of words recognized and analyzed) and (ii) studied in detail the cases for which each tool was unable to generate any output. Finally, we discuss different ways in which these tools could be optimized, either to improve their performances or, in the specific case of Quechua, to cover more individual languages of this macrolanguage in future works as well.</abstract>
<identifier type="citekey">himoro-pareja-lora-2022-preliminary</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.584</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>5450</start>
<end>5459</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Preliminary Results on the Evaluation of Computational Tools for the Analysis of Quechua and Aymara
%A Himoro, Marcelo Yuji
%A Pareja-Lora, Antonio
%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 himoro-pareja-lora-2022-preliminary
%X This research has focused on evaluating the existing open-source morphological analyzers for two of the most widely spoken indigenous macrolanguages in South America, namely Quechua and Aymara. Firstly, we have evaluated their performance (precision, recall and F1 score) for the individual languages for which they were developed (Cuzco Quechua and Aymara). Secondly, in order to assess how these tools handle other individual languages of the macrolanguage, we have extracted some sample text from school textbooks and educational resources. This sample text was edited in the different countries where these macrolanguages are spoken (Colombia, Ecuador, Peru, Bolivia, Chile and Argentina for Quechua; and Bolivia, Peru and Chile for Aymara), and it includes their different standardized forms (10 individual languages of Quechua and 3 of Aymara). Processing this text by means of the tools, we have (i) calculated their coverage (number of words recognized and analyzed) and (ii) studied in detail the cases for which each tool was unable to generate any output. Finally, we discuss different ways in which these tools could be optimized, either to improve their performances or, in the specific case of Quechua, to cover more individual languages of this macrolanguage in future works as well.
%U https://aclanthology.org/2022.lrec-1.584
%P 5450-5459
Markdown (Informal)
[Preliminary Results on the Evaluation of Computational Tools for the Analysis of Quechua and Aymara](https://aclanthology.org/2022.lrec-1.584) (Himoro & Pareja-Lora, LREC 2022)
ACL