@inproceedings{bustamante-etal-2020-data,
title = "No Data to Crawl? Monolingual Corpus Creation from {PDF} Files of Truly low-Resource Languages in {P}eru",
author = "Bustamante, Gina and
Oncevay, Arturo and
Zariquiey, Roberto",
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
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.356",
pages = "2914--2923",
abstract = "We introduce new monolingual corpora for four indigenous and endangered languages from Peru: Shipibo-konibo, Ashaninka, Yanesha and Yine. Given the total absence of these languages in the web, the extraction and processing of texts from PDF files is relevant in a truly low-resource language scenario. Our procedure for monolingual corpus creation considers language-specific and language-agnostic steps, and focuses on educational PDF files with multilingual sentences, noisy pages and low-structured content. Through an evaluation based on language modelling and character-level perplexity on a subset of manually extracted sentences, we determine that our method allows the creation of clean corpora for the four languages, a key resource for natural language processing tasks nowadays.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bustamante-etal-2020-data">
<titleInfo>
<title>No Data to Crawl? Monolingual Corpus Creation from PDF Files of Truly low-Resource Languages in Peru</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gina</namePart>
<namePart type="family">Bustamante</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>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Zariquiey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth 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">Asuncion</namePart>
<namePart type="family">Moreno</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>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>We introduce new monolingual corpora for four indigenous and endangered languages from Peru: Shipibo-konibo, Ashaninka, Yanesha and Yine. Given the total absence of these languages in the web, the extraction and processing of texts from PDF files is relevant in a truly low-resource language scenario. Our procedure for monolingual corpus creation considers language-specific and language-agnostic steps, and focuses on educational PDF files with multilingual sentences, noisy pages and low-structured content. Through an evaluation based on language modelling and character-level perplexity on a subset of manually extracted sentences, we determine that our method allows the creation of clean corpora for the four languages, a key resource for natural language processing tasks nowadays.</abstract>
<identifier type="citekey">bustamante-etal-2020-data</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.356</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>2914</start>
<end>2923</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T No Data to Crawl? Monolingual Corpus Creation from PDF Files of Truly low-Resource Languages in Peru
%A Bustamante, Gina
%A Oncevay, Arturo
%A Zariquiey, Roberto
%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 Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F bustamante-etal-2020-data
%X We introduce new monolingual corpora for four indigenous and endangered languages from Peru: Shipibo-konibo, Ashaninka, Yanesha and Yine. Given the total absence of these languages in the web, the extraction and processing of texts from PDF files is relevant in a truly low-resource language scenario. Our procedure for monolingual corpus creation considers language-specific and language-agnostic steps, and focuses on educational PDF files with multilingual sentences, noisy pages and low-structured content. Through an evaluation based on language modelling and character-level perplexity on a subset of manually extracted sentences, we determine that our method allows the creation of clean corpora for the four languages, a key resource for natural language processing tasks nowadays.
%U https://aclanthology.org/2020.lrec-1.356
%P 2914-2923
Markdown (Informal)
[No Data to Crawl? Monolingual Corpus Creation from PDF Files of Truly low-Resource Languages in Peru](https://aclanthology.org/2020.lrec-1.356) (Bustamante et al., LREC 2020)
ACL