@inproceedings{javorsek-erjavec-2010-experimental,
title = "Experimental Deployment of a Grid Virtual Organization for Human Language Technologies",
author = "Javor{\v{s}}ek, Jan Jona and
Erjavec, Toma{\v{z}}",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}`10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L10-1617/",
abstract = "We propose to create a grid virtual organization for human language technologies, at first chiefly with the task of enabling linguistic researches to use existing distributed computing facilities of the European grid infrastructure for more efficient processing of large data sets. After a brief overview of modern grid computing, a number of common use-cases of natural language processing tasks running on the grid are presented, notably corpus annotation with morpho-syntactic tagging (600+ million-word corpus annotated in less than a day), {\$}n{\$}-gram statistics processing of a corpus and creation of grid-backed web-accessible services with annotation and term-extraction as examples. Implementation considerations and common problems of using grid for this type of tasks are laid out. We conclude with an outline of a simple action plan for evolving the infrastructure created for these experiments into a fully functional Human Language Technology grid Virtual Organization with the goal of making the power of European grid infrastructure available to the linguistic community."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="javorsek-erjavec-2010-experimental">
<titleInfo>
<title>Experimental Deployment of a Grid Virtual Organization for Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="given">Jona</namePart>
<namePart type="family">Javoršek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomaž</namePart>
<namePart type="family">Erjavec</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC‘10)</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">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">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>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose to create a grid virtual organization for human language technologies, at first chiefly with the task of enabling linguistic researches to use existing distributed computing facilities of the European grid infrastructure for more efficient processing of large data sets. After a brief overview of modern grid computing, a number of common use-cases of natural language processing tasks running on the grid are presented, notably corpus annotation with morpho-syntactic tagging (600+ million-word corpus annotated in less than a day), $n$-gram statistics processing of a corpus and creation of grid-backed web-accessible services with annotation and term-extraction as examples. Implementation considerations and common problems of using grid for this type of tasks are laid out. We conclude with an outline of a simple action plan for evolving the infrastructure created for these experiments into a fully functional Human Language Technology grid Virtual Organization with the goal of making the power of European grid infrastructure available to the linguistic community.</abstract>
<identifier type="citekey">javorsek-erjavec-2010-experimental</identifier>
<location>
<url>https://aclanthology.org/L10-1617/</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Experimental Deployment of a Grid Virtual Organization for Human Language Technologies
%A Javoršek, Jan Jona
%A Erjavec, Tomaž
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC‘10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F javorsek-erjavec-2010-experimental
%X We propose to create a grid virtual organization for human language technologies, at first chiefly with the task of enabling linguistic researches to use existing distributed computing facilities of the European grid infrastructure for more efficient processing of large data sets. After a brief overview of modern grid computing, a number of common use-cases of natural language processing tasks running on the grid are presented, notably corpus annotation with morpho-syntactic tagging (600+ million-word corpus annotated in less than a day), $n$-gram statistics processing of a corpus and creation of grid-backed web-accessible services with annotation and term-extraction as examples. Implementation considerations and common problems of using grid for this type of tasks are laid out. We conclude with an outline of a simple action plan for evolving the infrastructure created for these experiments into a fully functional Human Language Technology grid Virtual Organization with the goal of making the power of European grid infrastructure available to the linguistic community.
%U https://aclanthology.org/L10-1617/
Markdown (Informal)
[Experimental Deployment of a Grid Virtual Organization for Human Language Technologies](https://aclanthology.org/L10-1617/) (Javoršek & Erjavec, LREC 2010)
ACL