@inproceedings{passonneau-etal-2006-inter,
title = "Inter-annotator Agreement on a Multilingual Semantic Annotation Task",
author = "Passonneau, Rebecca and
Habash, Nizar and
Rambow, Owen",
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/634_pdf.pdf",
abstract = "Six sites participated in the Interlingual Annotation of Multilingual Text Corpora (IAMTC) project (Dorr et al., 2004; Farwell et al., 2004; Mitamura et al., 2004). Parsed versions of English translations of news articles in Arabic, French, Hindi, Japanese, Korean and Spanish were annotated by up to ten annotators. Their task was to match open-class lexical items (nouns, verbs, adjectives, adverbs) to one or more concepts taken from the Omega ontology (Philpot et al., 2003), and to identify theta roles for verb arguments. The annotated corpus is intended to be a resource for meaning-based approaches to machine translation. Here we discuss inter-annotator agreement for the corpus. The annotation task is characterized by annotators freedom to select multiple concepts or roles per lexical item. As a result, the annotation categories are sets, the number of which is bounded only by the number of distinct annotator-lexical item pairs. We use a reliability metric designed to handle partial agreement between sets. The best results pertain to the part of the ontology derived from WordNet. We examine change over the course of the project, differences among annotators, and differences across parts of speech. Our results suggest a strong learning effect early in the project.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="passonneau-etal-2006-inter">
<titleInfo>
<title>Inter-annotator Agreement on a Multilingual Semantic Annotation Task</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>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</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>Six sites participated in the Interlingual Annotation of Multilingual Text Corpora (IAMTC) project (Dorr et al., 2004; Farwell et al., 2004; Mitamura et al., 2004). Parsed versions of English translations of news articles in Arabic, French, Hindi, Japanese, Korean and Spanish were annotated by up to ten annotators. Their task was to match open-class lexical items (nouns, verbs, adjectives, adverbs) to one or more concepts taken from the Omega ontology (Philpot et al., 2003), and to identify theta roles for verb arguments. The annotated corpus is intended to be a resource for meaning-based approaches to machine translation. Here we discuss inter-annotator agreement for the corpus. The annotation task is characterized by annotators freedom to select multiple concepts or roles per lexical item. As a result, the annotation categories are sets, the number of which is bounded only by the number of distinct annotator-lexical item pairs. We use a reliability metric designed to handle partial agreement between sets. The best results pertain to the part of the ontology derived from WordNet. We examine change over the course of the project, differences among annotators, and differences across parts of speech. Our results suggest a strong learning effect early in the project.</abstract>
<identifier type="citekey">passonneau-etal-2006-inter</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/634_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Inter-annotator Agreement on a Multilingual Semantic Annotation Task
%A Passonneau, Rebecca
%A Habash, Nizar
%A Rambow, Owen
%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-etal-2006-inter
%X Six sites participated in the Interlingual Annotation of Multilingual Text Corpora (IAMTC) project (Dorr et al., 2004; Farwell et al., 2004; Mitamura et al., 2004). Parsed versions of English translations of news articles in Arabic, French, Hindi, Japanese, Korean and Spanish were annotated by up to ten annotators. Their task was to match open-class lexical items (nouns, verbs, adjectives, adverbs) to one or more concepts taken from the Omega ontology (Philpot et al., 2003), and to identify theta roles for verb arguments. The annotated corpus is intended to be a resource for meaning-based approaches to machine translation. Here we discuss inter-annotator agreement for the corpus. The annotation task is characterized by annotators freedom to select multiple concepts or roles per lexical item. As a result, the annotation categories are sets, the number of which is bounded only by the number of distinct annotator-lexical item pairs. We use a reliability metric designed to handle partial agreement between sets. The best results pertain to the part of the ontology derived from WordNet. We examine change over the course of the project, differences among annotators, and differences across parts of speech. Our results suggest a strong learning effect early in the project.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/634_pdf.pdf
Markdown (Informal)
[Inter-annotator Agreement on a Multilingual Semantic Annotation Task](http://www.lrec-conf.org/proceedings/lrec2006/pdf/634_pdf.pdf) (Passonneau et al., LREC 2006)
ACL