@inproceedings{sanchez-carrera-etal-2024-unlocking,
title = "Unlocking Knowledge with {OCR}-Driven Document Digitization for {P}eruvian Indigenous Languages",
author = "Sanchez Carrera, Shadya and
Zariquiey, Roberto and
Oncevay, Arturo",
editor = "Mager, Manuel and
Ebrahimi, Abteen and
Rijhwani, Shruti and
Oncevay, Arturo and
Chiruzzo, Luis and
Pugh, Robert and
von der Wense, Katharina",
booktitle = "Proceedings of the 4th Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP 2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.americasnlp-1.11/",
doi = "10.18653/v1/2024.americasnlp-1.11",
pages = "103--111",
abstract = "The current focus on resource-rich languages poses a challenge to linguistic diversity, affecting minority languages with limited digital presence and relatively old published and unpublished resources. In addressing this issue, this study targets the digitalization of old scanned textbooks written in four Peruvian indigenous languages (Ash{\'a}ninka, Shipibo-Konibo, Yanesha, and Yine) using Optical Character Recognition (OCR) technology. This is complemented with text correction methods to minimize extraction errors. Contributions include the creation of an annotated dataset with 454 scanned page images, for a rigorous evaluation, and the development of a module to correct OCR-generated transcription alignments."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sanchez-carrera-etal-2024-unlocking">
<titleInfo>
<title>Unlocking Knowledge with OCR-Driven Document Digitization for Peruvian Indigenous Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shadya</namePart>
<namePart type="family">Sanchez Carrera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Zariquiey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arturo</namePart>
<namePart type="family">Oncevay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP 2024)</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">Abteen</namePart>
<namePart type="family">Ebrahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shruti</namePart>
<namePart type="family">Rijhwani</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">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Pugh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">von der Wense</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The current focus on resource-rich languages poses a challenge to linguistic diversity, affecting minority languages with limited digital presence and relatively old published and unpublished resources. In addressing this issue, this study targets the digitalization of old scanned textbooks written in four Peruvian indigenous languages (Asháninka, Shipibo-Konibo, Yanesha, and Yine) using Optical Character Recognition (OCR) technology. This is complemented with text correction methods to minimize extraction errors. Contributions include the creation of an annotated dataset with 454 scanned page images, for a rigorous evaluation, and the development of a module to correct OCR-generated transcription alignments.</abstract>
<identifier type="citekey">sanchez-carrera-etal-2024-unlocking</identifier>
<identifier type="doi">10.18653/v1/2024.americasnlp-1.11</identifier>
<location>
<url>https://aclanthology.org/2024.americasnlp-1.11/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>103</start>
<end>111</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unlocking Knowledge with OCR-Driven Document Digitization for Peruvian Indigenous Languages
%A Sanchez Carrera, Shadya
%A Zariquiey, Roberto
%A Oncevay, Arturo
%Y Mager, Manuel
%Y Ebrahimi, Abteen
%Y Rijhwani, Shruti
%Y Oncevay, Arturo
%Y Chiruzzo, Luis
%Y Pugh, Robert
%Y von der Wense, Katharina
%S Proceedings of the 4th Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP 2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F sanchez-carrera-etal-2024-unlocking
%X The current focus on resource-rich languages poses a challenge to linguistic diversity, affecting minority languages with limited digital presence and relatively old published and unpublished resources. In addressing this issue, this study targets the digitalization of old scanned textbooks written in four Peruvian indigenous languages (Asháninka, Shipibo-Konibo, Yanesha, and Yine) using Optical Character Recognition (OCR) technology. This is complemented with text correction methods to minimize extraction errors. Contributions include the creation of an annotated dataset with 454 scanned page images, for a rigorous evaluation, and the development of a module to correct OCR-generated transcription alignments.
%R 10.18653/v1/2024.americasnlp-1.11
%U https://aclanthology.org/2024.americasnlp-1.11/
%U https://doi.org/10.18653/v1/2024.americasnlp-1.11
%P 103-111
Markdown (Informal)
[Unlocking Knowledge with OCR-Driven Document Digitization for Peruvian Indigenous Languages](https://aclanthology.org/2024.americasnlp-1.11/) (Sanchez Carrera et al., AmericasNLP 2024)
ACL