@inproceedings{schafer-beck-2006-automatic,
title = "Automatic Testing and Evaluation of Multilingual Language Technology Resources and Components",
author = {Sch{\"a}fer, Ulrich and
Beck, Daniel},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/91_pdf.pdf",
abstract = "We describe SProUTomat, a tool for daily building, testing and evaluating a complex general-purpose multilingual natural language text processor including its linguistic resources (lingware). Software and lingware are developed, maintained and extended in a distributed manner by multiple authors and projects, i.e., the source code stored in a version control system is modified frequently. The modular design of different, dedicated lingware modules like tokenizers, morphology, gazetteers, type hierarchy, rule formalism on the one hand increases flexibility and re-usability, but on the other hand may lead to fragility with respect to changes. Therefore, frequent testing as known from software engineering is necessary also for lingware to warrant a high level of quality and overall stability of the system. We describe the build, testing and evaluation methods for LT software and lingware we have developed on the basis of the open source, platform-independent Apache Ant tool and the configurable evaluation tool JTaCo.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schafer-beck-2006-automatic">
<titleInfo>
<title>Automatic Testing and Evaluation of Multilingual Language Technology Resources and Components</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ulrich</namePart>
<namePart type="family">Schäfer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Beck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">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">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe SProUTomat, a tool for daily building, testing and evaluating a complex general-purpose multilingual natural language text processor including its linguistic resources (lingware). Software and lingware are developed, maintained and extended in a distributed manner by multiple authors and projects, i.e., the source code stored in a version control system is modified frequently. The modular design of different, dedicated lingware modules like tokenizers, morphology, gazetteers, type hierarchy, rule formalism on the one hand increases flexibility and re-usability, but on the other hand may lead to fragility with respect to changes. Therefore, frequent testing as known from software engineering is necessary also for lingware to warrant a high level of quality and overall stability of the system. We describe the build, testing and evaluation methods for LT software and lingware we have developed on the basis of the open source, platform-independent Apache Ant tool and the configurable evaluation tool JTaCo.</abstract>
<identifier type="citekey">schafer-beck-2006-automatic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/91_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Testing and Evaluation of Multilingual Language Technology Resources and Components
%A Schäfer, Ulrich
%A Beck, Daniel
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F schafer-beck-2006-automatic
%X We describe SProUTomat, a tool for daily building, testing and evaluating a complex general-purpose multilingual natural language text processor including its linguistic resources (lingware). Software and lingware are developed, maintained and extended in a distributed manner by multiple authors and projects, i.e., the source code stored in a version control system is modified frequently. The modular design of different, dedicated lingware modules like tokenizers, morphology, gazetteers, type hierarchy, rule formalism on the one hand increases flexibility and re-usability, but on the other hand may lead to fragility with respect to changes. Therefore, frequent testing as known from software engineering is necessary also for lingware to warrant a high level of quality and overall stability of the system. We describe the build, testing and evaluation methods for LT software and lingware we have developed on the basis of the open source, platform-independent Apache Ant tool and the configurable evaluation tool JTaCo.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/91_pdf.pdf
Markdown (Informal)
[Automatic Testing and Evaluation of Multilingual Language Technology Resources and Components](http://www.lrec-conf.org/proceedings/lrec2006/pdf/91_pdf.pdf) (Schäfer & Beck, LREC 2006)
ACL