@inproceedings{stefanovitch-2022-recovering,
title = "Recovering Text from Endangered Languages Corrupted {PDF} documents",
author = "Stefanovitch, Nicolas",
editor = "Moeller, Sarah and
Anastasopoulos, Antonios and
Arppe, Antti and
Chaudhary, Aditi and
Harrigan, Atticus and
Holden, Josh and
Lachler, Jordan and
Palmer, Alexis and
Rijhwani, Shruti and
Schwartz, Lane",
booktitle = "Proceedings of the Fifth Workshop on the Use of Computational Methods in the Study of Endangered Languages",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.computel-1.10/",
doi = "10.18653/v1/2022.computel-1.10",
pages = "78--82",
abstract = "In this paper we present an approach to efficiently recover texts from corrupted documents of endangered languages. Textual resources for such languages are scarce, and sometimes the few available resources are corrupted PDF documents. Endangered languages are not supported by standard tools and present even the additional difficulties of not possessing any corpus over which to train language models to assist with the recovery. The approach presented is able to fully recover born digital PDF documents with minimal effort, thereby helping the preservation effort of endangered languages, by extending the range of documents usable for corpus building."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stefanovitch-2022-recovering">
<titleInfo>
<title>Recovering Text from Endangered Languages Corrupted PDF documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Stefanovitch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on the Use of Computational Methods in the Study of Endangered Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Moeller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antti</namePart>
<namePart type="family">Arppe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aditi</namePart>
<namePart type="family">Chaudhary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atticus</namePart>
<namePart type="family">Harrigan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josh</namePart>
<namePart type="family">Holden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Lachler</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">Shruti</namePart>
<namePart type="family">Rijhwani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lane</namePart>
<namePart type="family">Schwartz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we present an approach to efficiently recover texts from corrupted documents of endangered languages. Textual resources for such languages are scarce, and sometimes the few available resources are corrupted PDF documents. Endangered languages are not supported by standard tools and present even the additional difficulties of not possessing any corpus over which to train language models to assist with the recovery. The approach presented is able to fully recover born digital PDF documents with minimal effort, thereby helping the preservation effort of endangered languages, by extending the range of documents usable for corpus building.</abstract>
<identifier type="citekey">stefanovitch-2022-recovering</identifier>
<identifier type="doi">10.18653/v1/2022.computel-1.10</identifier>
<location>
<url>https://aclanthology.org/2022.computel-1.10/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>78</start>
<end>82</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Recovering Text from Endangered Languages Corrupted PDF documents
%A Stefanovitch, Nicolas
%Y Moeller, Sarah
%Y Anastasopoulos, Antonios
%Y Arppe, Antti
%Y Chaudhary, Aditi
%Y Harrigan, Atticus
%Y Holden, Josh
%Y Lachler, Jordan
%Y Palmer, Alexis
%Y Rijhwani, Shruti
%Y Schwartz, Lane
%S Proceedings of the Fifth Workshop on the Use of Computational Methods in the Study of Endangered Languages
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F stefanovitch-2022-recovering
%X In this paper we present an approach to efficiently recover texts from corrupted documents of endangered languages. Textual resources for such languages are scarce, and sometimes the few available resources are corrupted PDF documents. Endangered languages are not supported by standard tools and present even the additional difficulties of not possessing any corpus over which to train language models to assist with the recovery. The approach presented is able to fully recover born digital PDF documents with minimal effort, thereby helping the preservation effort of endangered languages, by extending the range of documents usable for corpus building.
%R 10.18653/v1/2022.computel-1.10
%U https://aclanthology.org/2022.computel-1.10/
%U https://doi.org/10.18653/v1/2022.computel-1.10
%P 78-82
Markdown (Informal)
[Recovering Text from Endangered Languages Corrupted PDF documents](https://aclanthology.org/2022.computel-1.10/) (Stefanovitch, ComputEL 2022)
ACL