@inproceedings{kattenberg-etal-2016-two,
title = "Two Architectures for Parallel Processing of Huge Amounts of Text",
author = "Kattenberg, Mathijs and
Beloki, Zuhaitz and
Soroa, Aitor and
Artola, Xabier and
Fokkens, Antske and
Huygen, Paul and
Verstoep, Kees",
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/L16-1714/",
pages = "4513--4519",
abstract = "This paper presents two alternative NLP architectures to analyze massive amounts of documents, using parallel processing. The two architectures focus on different processing scenarios, namely batch-processing and streaming processing. The batch-processing scenario aims at optimizing the overall throughput of the system, i.e., minimizing the overall time spent on processing all documents. The streaming architecture aims to minimize the time to process real-time incoming documents and is therefore especially suitable for live feeds. The paper presents experiments with both architectures, and reports the overall gain when they are used for batch as well as for streaming processing. All the software described in the paper is publicly available under free licenses."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kattenberg-etal-2016-two">
<titleInfo>
<title>Two Architectures for Parallel Processing of Huge Amounts of Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mathijs</namePart>
<namePart type="family">Kattenberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zuhaitz</namePart>
<namePart type="family">Beloki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aitor</namePart>
<namePart type="family">Soroa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xabier</namePart>
<namePart type="family">Artola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antske</namePart>
<namePart type="family">Fokkens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Huygen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kees</namePart>
<namePart type="family">Verstoep</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>This paper presents two alternative NLP architectures to analyze massive amounts of documents, using parallel processing. The two architectures focus on different processing scenarios, namely batch-processing and streaming processing. The batch-processing scenario aims at optimizing the overall throughput of the system, i.e., minimizing the overall time spent on processing all documents. The streaming architecture aims to minimize the time to process real-time incoming documents and is therefore especially suitable for live feeds. The paper presents experiments with both architectures, and reports the overall gain when they are used for batch as well as for streaming processing. All the software described in the paper is publicly available under free licenses.</abstract>
<identifier type="citekey">kattenberg-etal-2016-two</identifier>
<location>
<url>https://aclanthology.org/L16-1714/</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4513</start>
<end>4519</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Two Architectures for Parallel Processing of Huge Amounts of Text
%A Kattenberg, Mathijs
%A Beloki, Zuhaitz
%A Soroa, Aitor
%A Artola, Xabier
%A Fokkens, Antske
%A Huygen, Paul
%A Verstoep, Kees
%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 kattenberg-etal-2016-two
%X This paper presents two alternative NLP architectures to analyze massive amounts of documents, using parallel processing. The two architectures focus on different processing scenarios, namely batch-processing and streaming processing. The batch-processing scenario aims at optimizing the overall throughput of the system, i.e., minimizing the overall time spent on processing all documents. The streaming architecture aims to minimize the time to process real-time incoming documents and is therefore especially suitable for live feeds. The paper presents experiments with both architectures, and reports the overall gain when they are used for batch as well as for streaming processing. All the software described in the paper is publicly available under free licenses.
%U https://aclanthology.org/L16-1714/
%P 4513-4519
Markdown (Informal)
[Two Architectures for Parallel Processing of Huge Amounts of Text](https://aclanthology.org/L16-1714/) (Kattenberg et al., LREC 2016)
ACL
- Mathijs Kattenberg, Zuhaitz Beloki, Aitor Soroa, Xabier Artola, Antske Fokkens, Paul Huygen, and Kees Verstoep. 2016. Two Architectures for Parallel Processing of Huge Amounts of Text. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 4513–4519, Portorož, Slovenia. European Language Resources Association (ELRA).