@inproceedings{cordova-nouvel-2021-toward,
title = "Toward Creation of {A}ncash Lexical Resources from {OCR}",
author = "Cordova, Johanna and
Nouvel, Damien",
editor = "Mager, Manuel and
Oncevay, Arturo and
Rios, Annette and
Ruiz, Ivan Vladimir Meza and
Palmer, Alexis and
Neubig, Graham and
Kann, Katharina",
booktitle = "Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.americasnlp-1.18/",
doi = "10.18653/v1/2021.americasnlp-1.18",
pages = "163--167",
abstract = "The Quechua linguistic family has a limited number of NLP resources, most of them being dedicated to Southern Quechua, whereas the varieties of Central Quechua have, to the best of our knowledge, no specific resources (software, lexicon or corpus). Our work addresses this issue by producing two resources for the Ancash Quechua: a full digital version of a dictionary, and an OCR model adapted to the considered variety. In this paper, we describe the steps towards this goal: we first measure performances of existing models for the task of digitising a Quechua dictionary, then adapt a model for the Ancash variety, and finally create a reliable resource for NLP in XML-TEI format. We hope that this work will be a basis for initiating NLP projects for Central Quechua, and that it will encourage digitisation initiatives for under-resourced languages."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cordova-nouvel-2021-toward">
<titleInfo>
<title>Toward Creation of Ancash Lexical Resources from OCR</title>
</titleInfo>
<name type="personal">
<namePart type="given">Johanna</namePart>
<namePart type="family">Cordova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damien</namePart>
<namePart type="family">Nouvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manuel</namePart>
<namePart type="family">Mager</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arturo</namePart>
<namePart type="family">Oncevay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annette</namePart>
<namePart type="family">Rios</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="given">Meza</namePart>
<namePart type="family">Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">Kann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Quechua linguistic family has a limited number of NLP resources, most of them being dedicated to Southern Quechua, whereas the varieties of Central Quechua have, to the best of our knowledge, no specific resources (software, lexicon or corpus). Our work addresses this issue by producing two resources for the Ancash Quechua: a full digital version of a dictionary, and an OCR model adapted to the considered variety. In this paper, we describe the steps towards this goal: we first measure performances of existing models for the task of digitising a Quechua dictionary, then adapt a model for the Ancash variety, and finally create a reliable resource for NLP in XML-TEI format. We hope that this work will be a basis for initiating NLP projects for Central Quechua, and that it will encourage digitisation initiatives for under-resourced languages.</abstract>
<identifier type="citekey">cordova-nouvel-2021-toward</identifier>
<identifier type="doi">10.18653/v1/2021.americasnlp-1.18</identifier>
<location>
<url>https://aclanthology.org/2021.americasnlp-1.18/</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>163</start>
<end>167</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Toward Creation of Ancash Lexical Resources from OCR
%A Cordova, Johanna
%A Nouvel, Damien
%Y Mager, Manuel
%Y Oncevay, Arturo
%Y Rios, Annette
%Y Ruiz, Ivan Vladimir Meza
%Y Palmer, Alexis
%Y Neubig, Graham
%Y Kann, Katharina
%S Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F cordova-nouvel-2021-toward
%X The Quechua linguistic family has a limited number of NLP resources, most of them being dedicated to Southern Quechua, whereas the varieties of Central Quechua have, to the best of our knowledge, no specific resources (software, lexicon or corpus). Our work addresses this issue by producing two resources for the Ancash Quechua: a full digital version of a dictionary, and an OCR model adapted to the considered variety. In this paper, we describe the steps towards this goal: we first measure performances of existing models for the task of digitising a Quechua dictionary, then adapt a model for the Ancash variety, and finally create a reliable resource for NLP in XML-TEI format. We hope that this work will be a basis for initiating NLP projects for Central Quechua, and that it will encourage digitisation initiatives for under-resourced languages.
%R 10.18653/v1/2021.americasnlp-1.18
%U https://aclanthology.org/2021.americasnlp-1.18/
%U https://doi.org/10.18653/v1/2021.americasnlp-1.18
%P 163-167
Markdown (Informal)
[Toward Creation of Ancash Lexical Resources from OCR](https://aclanthology.org/2021.americasnlp-1.18/) (Cordova & Nouvel, AmericasNLP 2021)
ACL
- Johanna Cordova and Damien Nouvel. 2021. Toward Creation of Ancash Lexical Resources from OCR. In Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas, pages 163–167, Online. Association for Computational Linguistics.