@inproceedings{passonneau-2006-measuring,
title = "Measuring Agreement on Set-valued Items ({MASI}) for Semantic and Pragmatic Annotation",
author = "Passonneau, Rebecca",
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/636_pdf.pdf",
abstract = "Annotation projects dealing with complex semantic or pragmatic phenomena face the dilemma of creating annotation schemes that oversimplify the phenomena, or that capture distinctions conventional reliability metrics cannot measure adequately. The solution to the dilemma is to develop metrics that quantify the decisions that annotators are asked to make. This paper discusses MASI, distance metric for comparing sets, and illustrates its use in quantifying the reliability of a specific dataset. Annotations of Summary Content Units (SCUs) generate models referred to as pyramids which can be used to evaluate unseen human summaries or machine summaries. The paper presents reliability results for five pairs of pyramids created for document sets from the 2003 Document Understanding Conference (DUC). The annotators worked independently of each other. Differences between application of MASI to pyramid annotation and its previous application to co-reference annotation are discussed. In addition, it is argued that a paradigmatic reliability study should relate measures of inter-annotator agreement to independent assessments, such as significance tests of the annotated variables with respect to other phenomena. In effect, what counts as sufficiently reliable intera-annotator agreement depends on the use the annotated data will be put to.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="passonneau-2006-measuring">
<titleInfo>
<title>Measuring Agreement on Set-valued Items (MASI) for Semantic and Pragmatic Annotation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Passonneau</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>Annotation projects dealing with complex semantic or pragmatic phenomena face the dilemma of creating annotation schemes that oversimplify the phenomena, or that capture distinctions conventional reliability metrics cannot measure adequately. The solution to the dilemma is to develop metrics that quantify the decisions that annotators are asked to make. This paper discusses MASI, distance metric for comparing sets, and illustrates its use in quantifying the reliability of a specific dataset. Annotations of Summary Content Units (SCUs) generate models referred to as pyramids which can be used to evaluate unseen human summaries or machine summaries. The paper presents reliability results for five pairs of pyramids created for document sets from the 2003 Document Understanding Conference (DUC). The annotators worked independently of each other. Differences between application of MASI to pyramid annotation and its previous application to co-reference annotation are discussed. In addition, it is argued that a paradigmatic reliability study should relate measures of inter-annotator agreement to independent assessments, such as significance tests of the annotated variables with respect to other phenomena. In effect, what counts as sufficiently reliable intera-annotator agreement depends on the use the annotated data will be put to.</abstract>
<identifier type="citekey">passonneau-2006-measuring</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/636_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Measuring Agreement on Set-valued Items (MASI) for Semantic and Pragmatic Annotation
%A Passonneau, Rebecca
%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 passonneau-2006-measuring
%X Annotation projects dealing with complex semantic or pragmatic phenomena face the dilemma of creating annotation schemes that oversimplify the phenomena, or that capture distinctions conventional reliability metrics cannot measure adequately. The solution to the dilemma is to develop metrics that quantify the decisions that annotators are asked to make. This paper discusses MASI, distance metric for comparing sets, and illustrates its use in quantifying the reliability of a specific dataset. Annotations of Summary Content Units (SCUs) generate models referred to as pyramids which can be used to evaluate unseen human summaries or machine summaries. The paper presents reliability results for five pairs of pyramids created for document sets from the 2003 Document Understanding Conference (DUC). The annotators worked independently of each other. Differences between application of MASI to pyramid annotation and its previous application to co-reference annotation are discussed. In addition, it is argued that a paradigmatic reliability study should relate measures of inter-annotator agreement to independent assessments, such as significance tests of the annotated variables with respect to other phenomena. In effect, what counts as sufficiently reliable intera-annotator agreement depends on the use the annotated data will be put to.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/636_pdf.pdf
Markdown (Informal)
[Measuring Agreement on Set-valued Items (MASI) for Semantic and Pragmatic Annotation](http://www.lrec-conf.org/proceedings/lrec2006/pdf/636_pdf.pdf) (Passonneau, LREC 2006)
ACL