@inproceedings{klang-nugues-2016-wikiparq,
title = "{WIKIPARQ}: A Tabulated {W}ikipedia Resource Using the Parquet Format",
author = "Klang, Marcus and
Nugues, Pierre",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1654",
pages = "4141--4148",
abstract = "Wikipedia has become one of the most popular resources in natural language processing and it is used in quantities of applications. However, Wikipedia requires a substantial pre-processing step before it can be used. For instance, its set of nonstandardized annotations, referred to as the wiki markup, is language-dependent and needs specific parsers from language to language, for English, French, Italian, etc. In addition, the intricacies of the different Wikipedia resources: main article text, categories, wikidata, infoboxes, scattered into the article document or in different files make it difficult to have global view of this outstanding resource. In this paper, we describe WikiParq, a unified format based on the Parquet standard to tabulate and package the Wikipedia corpora. In combination with Spark, a map-reduce computing framework, and the SQL query language, WikiParq makes it much easier to write database queries to extract specific information or subcorpora from Wikipedia, such as all the first paragraphs of the articles in French, or all the articles on persons in Spanish, or all the articles on persons that have versions in French, English, and Spanish. WikiParq is available in six language versions and is potentially extendible to all the languages of Wikipedia. The WikiParq files are downloadable as tarball archives from this location: \url{http://semantica.cs.lth.se/wikiparq/}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="klang-nugues-2016-wikiparq">
<titleInfo>
<title>WIKIPARQ: A Tabulated Wikipedia Resource Using the Parquet Format</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcus</namePart>
<namePart type="family">Klang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Nugues</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Wikipedia has become one of the most popular resources in natural language processing and it is used in quantities of applications. However, Wikipedia requires a substantial pre-processing step before it can be used. For instance, its set of nonstandardized annotations, referred to as the wiki markup, is language-dependent and needs specific parsers from language to language, for English, French, Italian, etc. In addition, the intricacies of the different Wikipedia resources: main article text, categories, wikidata, infoboxes, scattered into the article document or in different files make it difficult to have global view of this outstanding resource. In this paper, we describe WikiParq, a unified format based on the Parquet standard to tabulate and package the Wikipedia corpora. In combination with Spark, a map-reduce computing framework, and the SQL query language, WikiParq makes it much easier to write database queries to extract specific information or subcorpora from Wikipedia, such as all the first paragraphs of the articles in French, or all the articles on persons in Spanish, or all the articles on persons that have versions in French, English, and Spanish. WikiParq is available in six language versions and is potentially extendible to all the languages of Wikipedia. The WikiParq files are downloadable as tarball archives from this location: http://semantica.cs.lth.se/wikiparq/.</abstract>
<identifier type="citekey">klang-nugues-2016-wikiparq</identifier>
<location>
<url>https://aclanthology.org/L16-1654</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4141</start>
<end>4148</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WIKIPARQ: A Tabulated Wikipedia Resource Using the Parquet Format
%A Klang, Marcus
%A Nugues, Pierre
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F klang-nugues-2016-wikiparq
%X Wikipedia has become one of the most popular resources in natural language processing and it is used in quantities of applications. However, Wikipedia requires a substantial pre-processing step before it can be used. For instance, its set of nonstandardized annotations, referred to as the wiki markup, is language-dependent and needs specific parsers from language to language, for English, French, Italian, etc. In addition, the intricacies of the different Wikipedia resources: main article text, categories, wikidata, infoboxes, scattered into the article document or in different files make it difficult to have global view of this outstanding resource. In this paper, we describe WikiParq, a unified format based on the Parquet standard to tabulate and package the Wikipedia corpora. In combination with Spark, a map-reduce computing framework, and the SQL query language, WikiParq makes it much easier to write database queries to extract specific information or subcorpora from Wikipedia, such as all the first paragraphs of the articles in French, or all the articles on persons in Spanish, or all the articles on persons that have versions in French, English, and Spanish. WikiParq is available in six language versions and is potentially extendible to all the languages of Wikipedia. The WikiParq files are downloadable as tarball archives from this location: http://semantica.cs.lth.se/wikiparq/.
%U https://aclanthology.org/L16-1654
%P 4141-4148
Markdown (Informal)
[WIKIPARQ: A Tabulated Wikipedia Resource Using the Parquet Format](https://aclanthology.org/L16-1654) (Klang & Nugues, LREC 2016)
ACL