@inproceedings{diewald-etal-2016-korap,
title = "{K}or{AP} Architecture {\textemdash} Diving in the Deep Sea of Corpus Data",
author = "Diewald, Nils and
Hanl, Michael and
Margaretha, Eliza and
Bingel, Joachim and
Kupietz, Marc and
Ba{\'n}ski, Piotr and
Witt, Andreas",
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/L16-1569/",
pages = "3586--3591",
abstract = "KorAP is a corpus search and analysis platform, developed at the Institute for the German Language (IDS). It supports very large corpora with multiple annotation layers, multiple query languages, and complex licensing scenarios. KorAP{'}s design aims to be scalable, flexible, and sustainable to serve the German Reference Corpus DeReKo for at least the next decade. To meet these requirements, we have adopted a highly modular microservice-based architecture. This paper outlines our approach: An architecture consisting of small components that are easy to extend, replace, and maintain. The components include a search backend, a user and corpus license management system, and a web-based user frontend. We also describe a general corpus query protocol used by all microservices for internal communications. KorAP is open source, licensed under BSD-2, and available on GitHub."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="diewald-etal-2016-korap">
<titleInfo>
<title>KorAP Architecture — Diving in the Deep Sea of Corpus Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nils</namePart>
<namePart type="family">Diewald</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Hanl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eliza</namePart>
<namePart type="family">Margaretha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joachim</namePart>
<namePart type="family">Bingel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="family">Kupietz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Bański</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Witt</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>KorAP is a corpus search and analysis platform, developed at the Institute for the German Language (IDS). It supports very large corpora with multiple annotation layers, multiple query languages, and complex licensing scenarios. KorAP’s design aims to be scalable, flexible, and sustainable to serve the German Reference Corpus DeReKo for at least the next decade. To meet these requirements, we have adopted a highly modular microservice-based architecture. This paper outlines our approach: An architecture consisting of small components that are easy to extend, replace, and maintain. The components include a search backend, a user and corpus license management system, and a web-based user frontend. We also describe a general corpus query protocol used by all microservices for internal communications. KorAP is open source, licensed under BSD-2, and available on GitHub.</abstract>
<identifier type="citekey">diewald-etal-2016-korap</identifier>
<location>
<url>https://aclanthology.org/L16-1569/</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3586</start>
<end>3591</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KorAP Architecture — Diving in the Deep Sea of Corpus Data
%A Diewald, Nils
%A Hanl, Michael
%A Margaretha, Eliza
%A Bingel, Joachim
%A Kupietz, Marc
%A Bański, Piotr
%A Witt, Andreas
%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 diewald-etal-2016-korap
%X KorAP is a corpus search and analysis platform, developed at the Institute for the German Language (IDS). It supports very large corpora with multiple annotation layers, multiple query languages, and complex licensing scenarios. KorAP’s design aims to be scalable, flexible, and sustainable to serve the German Reference Corpus DeReKo for at least the next decade. To meet these requirements, we have adopted a highly modular microservice-based architecture. This paper outlines our approach: An architecture consisting of small components that are easy to extend, replace, and maintain. The components include a search backend, a user and corpus license management system, and a web-based user frontend. We also describe a general corpus query protocol used by all microservices for internal communications. KorAP is open source, licensed under BSD-2, and available on GitHub.
%U https://aclanthology.org/L16-1569/
%P 3586-3591
Markdown (Informal)
[KorAP Architecture ― Diving in the Deep Sea of Corpus Data](https://aclanthology.org/L16-1569/) (Diewald et al., LREC 2016)
ACL
- Nils Diewald, Michael Hanl, Eliza Margaretha, Joachim Bingel, Marc Kupietz, Piotr Bański, and Andreas Witt. 2016. KorAP Architecture ― Diving in the Deep Sea of Corpus Data. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 3586–3591, Portorož, Slovenia. European Language Resources Association (ELRA).