@inproceedings{feilmayr-etal-2012-evaliex,
title = "{EVALIEX} {---} A Proposal for an Extended Evaluation Methodology for Information Extraction Systems",
author = {Feilmayr, Christina and
Pr{\"o}ll, Birgit and
Linsmayr, Elisabeth},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/204_Paper.pdf",
pages = "2303--2310",
abstract = "Assessing the correctness of extracted data requires performance evaluation, which is accomplished by calculating quality metrics. The evaluation process must cope with the challenges posed by information extraction and natural language processing. In the previous work most of the existing methodologies have been shown that they support only traditional scoring metrics. Our research work addresses requirements, which arose during the development of three productive rule-based information extraction systems. The main contribution is twofold: First, we developed a proposal for an evaluation methodology that provides the flexibility and effectiveness needed for comprehensive performance measurement. The proposal extends state-of-the-art scoring metrics by measuring string and semantic similarities and by parameterization of metric scoring, and thus simulating with human judgment. Second, we implemented an IE evaluation tool named EVALIEX, which integrates these measurement concepts and provides an efficient user interface that supports evaluation control and the visualization of IE results. To guarantee domain independence, the tool additionally provides a Generic Mapper for XML Instances (GeMap) that maps domain-dependent XML files containing IE results to generic ones. Compared to other tools, it provides more flexible testing and better visualization of extraction results for the comparison of different (versions of) information extraction systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="feilmayr-etal-2012-evaliex">
<titleInfo>
<title>EVALIEX — A Proposal for an Extended Evaluation Methodology for Information Extraction Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christina</namePart>
<namePart type="family">Feilmayr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Birgit</namePart>
<namePart type="family">Pröll</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisabeth</namePart>
<namePart type="family">Linsmayr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Assessing the correctness of extracted data requires performance evaluation, which is accomplished by calculating quality metrics. The evaluation process must cope with the challenges posed by information extraction and natural language processing. In the previous work most of the existing methodologies have been shown that they support only traditional scoring metrics. Our research work addresses requirements, which arose during the development of three productive rule-based information extraction systems. The main contribution is twofold: First, we developed a proposal for an evaluation methodology that provides the flexibility and effectiveness needed for comprehensive performance measurement. The proposal extends state-of-the-art scoring metrics by measuring string and semantic similarities and by parameterization of metric scoring, and thus simulating with human judgment. Second, we implemented an IE evaluation tool named EVALIEX, which integrates these measurement concepts and provides an efficient user interface that supports evaluation control and the visualization of IE results. To guarantee domain independence, the tool additionally provides a Generic Mapper for XML Instances (GeMap) that maps domain-dependent XML files containing IE results to generic ones. Compared to other tools, it provides more flexible testing and better visualization of extraction results for the comparison of different (versions of) information extraction systems.</abstract>
<identifier type="citekey">feilmayr-etal-2012-evaliex</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/204_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2303</start>
<end>2310</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EVALIEX — A Proposal for an Extended Evaluation Methodology for Information Extraction Systems
%A Feilmayr, Christina
%A Pröll, Birgit
%A Linsmayr, Elisabeth
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F feilmayr-etal-2012-evaliex
%X Assessing the correctness of extracted data requires performance evaluation, which is accomplished by calculating quality metrics. The evaluation process must cope with the challenges posed by information extraction and natural language processing. In the previous work most of the existing methodologies have been shown that they support only traditional scoring metrics. Our research work addresses requirements, which arose during the development of three productive rule-based information extraction systems. The main contribution is twofold: First, we developed a proposal for an evaluation methodology that provides the flexibility and effectiveness needed for comprehensive performance measurement. The proposal extends state-of-the-art scoring metrics by measuring string and semantic similarities and by parameterization of metric scoring, and thus simulating with human judgment. Second, we implemented an IE evaluation tool named EVALIEX, which integrates these measurement concepts and provides an efficient user interface that supports evaluation control and the visualization of IE results. To guarantee domain independence, the tool additionally provides a Generic Mapper for XML Instances (GeMap) that maps domain-dependent XML files containing IE results to generic ones. Compared to other tools, it provides more flexible testing and better visualization of extraction results for the comparison of different (versions of) information extraction systems.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/204_Paper.pdf
%P 2303-2310
Markdown (Informal)
[EVALIEX — A Proposal for an Extended Evaluation Methodology for Information Extraction Systems](http://www.lrec-conf.org/proceedings/lrec2012/pdf/204_Paper.pdf) (Feilmayr et al., LREC 2012)
ACL