@inproceedings{druskat-etal-2016-corpus,
title = "corpus-tools.org: An Interoperable Generic Software Tool Set for Multi-layer Linguistic Corpora",
author = "Druskat, Stephan and
Gast, Volker and
Krause, Thomas and
Zipser, Florian",
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/L16-1711/",
pages = "4492--4499",
abstract = "This paper introduces an open source, interoperable generic software tool set catering for the entire workflow of creation, migration, annotation, query and analysis of multi-layer linguistic corpora. It consists of four components: Salt, a graph-based meta model and API for linguistic data, the common data model for the rest of the tool set; Pepper, a conversion tool and platform for linguistic data that can be used to convert many different linguistic formats into each other; Atomic, an extensible, platform-independent multi-layer desktop annotation software for linguistic corpora; ANNIS, a search and visualization architecture for multi-layer linguistic corpora with many different visualizations and a powerful native query language. The set was designed to solve the following issues in a multi-layer corpus workflow: Lossless data transition between tools through a common data model generic enough to allow for a potentially unlimited number of different types of annotation, conversion capabilities for different linguistic formats to cater for the processing of data from different sources and/or with existing annotations, a high level of extensibility to enhance the sustainability of the whole tool set, analysis capabilities encompassing corpus and annotation query alongside multi-faceted visualizations of all annotation layers."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="druskat-etal-2016-corpus">
<titleInfo>
<title>corpus-tools.org: An Interoperable Generic Software Tool Set for Multi-layer Linguistic Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stephan</namePart>
<namePart type="family">Druskat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Volker</namePart>
<namePart type="family">Gast</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Krause</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Florian</namePart>
<namePart type="family">Zipser</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 introduces an open source, interoperable generic software tool set catering for the entire workflow of creation, migration, annotation, query and analysis of multi-layer linguistic corpora. It consists of four components: Salt, a graph-based meta model and API for linguistic data, the common data model for the rest of the tool set; Pepper, a conversion tool and platform for linguistic data that can be used to convert many different linguistic formats into each other; Atomic, an extensible, platform-independent multi-layer desktop annotation software for linguistic corpora; ANNIS, a search and visualization architecture for multi-layer linguistic corpora with many different visualizations and a powerful native query language. The set was designed to solve the following issues in a multi-layer corpus workflow: Lossless data transition between tools through a common data model generic enough to allow for a potentially unlimited number of different types of annotation, conversion capabilities for different linguistic formats to cater for the processing of data from different sources and/or with existing annotations, a high level of extensibility to enhance the sustainability of the whole tool set, analysis capabilities encompassing corpus and annotation query alongside multi-faceted visualizations of all annotation layers.</abstract>
<identifier type="citekey">druskat-etal-2016-corpus</identifier>
<location>
<url>https://aclanthology.org/L16-1711/</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4492</start>
<end>4499</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T corpus-tools.org: An Interoperable Generic Software Tool Set for Multi-layer Linguistic Corpora
%A Druskat, Stephan
%A Gast, Volker
%A Krause, Thomas
%A Zipser, Florian
%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 druskat-etal-2016-corpus
%X This paper introduces an open source, interoperable generic software tool set catering for the entire workflow of creation, migration, annotation, query and analysis of multi-layer linguistic corpora. It consists of four components: Salt, a graph-based meta model and API for linguistic data, the common data model for the rest of the tool set; Pepper, a conversion tool and platform for linguistic data that can be used to convert many different linguistic formats into each other; Atomic, an extensible, platform-independent multi-layer desktop annotation software for linguistic corpora; ANNIS, a search and visualization architecture for multi-layer linguistic corpora with many different visualizations and a powerful native query language. The set was designed to solve the following issues in a multi-layer corpus workflow: Lossless data transition between tools through a common data model generic enough to allow for a potentially unlimited number of different types of annotation, conversion capabilities for different linguistic formats to cater for the processing of data from different sources and/or with existing annotations, a high level of extensibility to enhance the sustainability of the whole tool set, analysis capabilities encompassing corpus and annotation query alongside multi-faceted visualizations of all annotation layers.
%U https://aclanthology.org/L16-1711/
%P 4492-4499
Markdown (Informal)
[corpus-tools.org: An Interoperable Generic Software Tool Set for Multi-layer Linguistic Corpora](https://aclanthology.org/L16-1711/) (Druskat et al., LREC 2016)
ACL