@inproceedings{lapponi-etal-2014-road,
title = "Off-Road {LAF}: Encoding and Processing Annotations in {NLP} Workflows",
author = "Lapponi, Emanuele and
Velldal, Erik and
Oepen, Stephan and
Knudsen, Rune Lain",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/978_Paper.pdf",
abstract = "The Linguistic Annotation Framework (LAF) provides an abstract data model for specifying interchange representations to ensure interoperability among different annotation formats. This paper describes an ongoing effort to adapt the LAF data model as the interchange representation in complex workflows as used in the Language Analysis Portal (LAP), an on-line and large-scale processing service that is developed as part of the Norwegian branch of the Common Language Resources and Technology Infrastructure (CLARIN) initiative. Unlike several related on-line processing environments, which predominantly instantiate a distributed architecture of web services, LAP achives scalability to potentially very large data volumes through integration with the Norwegian national e-Infrastructure, and in particular job sumission to a capacity compute cluster. This setup leads to tighter integration requirements and also calls for efficient, low-overhead communication of (intermediate) processing results with workflows. We meet these demands by coupling the LAF data model with a lean, non-redundant JSON-based interchange format and integration of an agile and performant NoSQL database, allowing parallel access from cluster nodes, as the central repository of linguistic annotation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lapponi-etal-2014-road">
<titleInfo>
<title>Off-Road LAF: Encoding and Processing Annotations in NLP Workflows</title>
</titleInfo>
<name type="personal">
<namePart type="given">Emanuele</namePart>
<namePart type="family">Lapponi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Velldal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephan</namePart>
<namePart type="family">Oepen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rune</namePart>
<namePart type="given">Lain</namePart>
<namePart type="family">Knudsen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Linguistic Annotation Framework (LAF) provides an abstract data model for specifying interchange representations to ensure interoperability among different annotation formats. This paper describes an ongoing effort to adapt the LAF data model as the interchange representation in complex workflows as used in the Language Analysis Portal (LAP), an on-line and large-scale processing service that is developed as part of the Norwegian branch of the Common Language Resources and Technology Infrastructure (CLARIN) initiative. Unlike several related on-line processing environments, which predominantly instantiate a distributed architecture of web services, LAP achives scalability to potentially very large data volumes through integration with the Norwegian national e-Infrastructure, and in particular job sumission to a capacity compute cluster. This setup leads to tighter integration requirements and also calls for efficient, low-overhead communication of (intermediate) processing results with workflows. We meet these demands by coupling the LAF data model with a lean, non-redundant JSON-based interchange format and integration of an agile and performant NoSQL database, allowing parallel access from cluster nodes, as the central repository of linguistic annotation.</abstract>
<identifier type="citekey">lapponi-etal-2014-road</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/978_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Off-Road LAF: Encoding and Processing Annotations in NLP Workflows
%A Lapponi, Emanuele
%A Velldal, Erik
%A Oepen, Stephan
%A Knudsen, Rune Lain
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F lapponi-etal-2014-road
%X The Linguistic Annotation Framework (LAF) provides an abstract data model for specifying interchange representations to ensure interoperability among different annotation formats. This paper describes an ongoing effort to adapt the LAF data model as the interchange representation in complex workflows as used in the Language Analysis Portal (LAP), an on-line and large-scale processing service that is developed as part of the Norwegian branch of the Common Language Resources and Technology Infrastructure (CLARIN) initiative. Unlike several related on-line processing environments, which predominantly instantiate a distributed architecture of web services, LAP achives scalability to potentially very large data volumes through integration with the Norwegian national e-Infrastructure, and in particular job sumission to a capacity compute cluster. This setup leads to tighter integration requirements and also calls for efficient, low-overhead communication of (intermediate) processing results with workflows. We meet these demands by coupling the LAF data model with a lean, non-redundant JSON-based interchange format and integration of an agile and performant NoSQL database, allowing parallel access from cluster nodes, as the central repository of linguistic annotation.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/978_Paper.pdf
Markdown (Informal)
[Off-Road LAF: Encoding and Processing Annotations in NLP Workflows](http://www.lrec-conf.org/proceedings/lrec2014/pdf/978_Paper.pdf) (Lapponi et al., LREC 2014)
ACL