@inproceedings{hanaoka-etal-2010-japanese,
title = "A {J}apanese Particle Corpus Built by Example-Based Annotation",
author = "Hanaoka, Hiroki and
Mima, Hideki and
Tsujii, Jun{'}ichi",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/617_Paper.pdf",
abstract = "This paper is a report on an on-going project of creating a new corpus focusing on Japanese particles. The corpus will provide deeper syntactic/semantic information than the existing resources. The initial target particle is ``to'' which occurs 22,006 times in 38,400 sentences of the existing corpus: the Kyoto Text Corpus. In this annotation task, an ``example-based'' methodology is adopted for the corpus annotation, which is different from the traditional annotation style. This approach provides the annotators with an example sentence rather than a linguistic category label. By avoiding linguistic technical terms, it is expected that any native speakers, with no special knowledge on linguistic analysis, can be an annotator without long training, and hence it can reduce the annotation cost. So far, 10,475 occurrences have been already annotated, with an inter-annotator agreement of 0.66 calculated by Cohen's kappa. The initial disagreement analyses and future directions are discussed in the paper.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hanaoka-etal-2010-japanese">
<titleInfo>
<title>A Japanese Particle Corpus Built by Example-Based Annotation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hiroki</namePart>
<namePart type="family">Hanaoka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hideki</namePart>
<namePart type="family">Mima</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun’ichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</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">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper is a report on an on-going project of creating a new corpus focusing on Japanese particles. The corpus will provide deeper syntactic/semantic information than the existing resources. The initial target particle is “to” which occurs 22,006 times in 38,400 sentences of the existing corpus: the Kyoto Text Corpus. In this annotation task, an “example-based” methodology is adopted for the corpus annotation, which is different from the traditional annotation style. This approach provides the annotators with an example sentence rather than a linguistic category label. By avoiding linguistic technical terms, it is expected that any native speakers, with no special knowledge on linguistic analysis, can be an annotator without long training, and hence it can reduce the annotation cost. So far, 10,475 occurrences have been already annotated, with an inter-annotator agreement of 0.66 calculated by Cohen’s kappa. The initial disagreement analyses and future directions are discussed in the paper.</abstract>
<identifier type="citekey">hanaoka-etal-2010-japanese</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/617_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Japanese Particle Corpus Built by Example-Based Annotation
%A Hanaoka, Hiroki
%A Mima, Hideki
%A Tsujii, Jun’ichi
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F hanaoka-etal-2010-japanese
%X This paper is a report on an on-going project of creating a new corpus focusing on Japanese particles. The corpus will provide deeper syntactic/semantic information than the existing resources. The initial target particle is “to” which occurs 22,006 times in 38,400 sentences of the existing corpus: the Kyoto Text Corpus. In this annotation task, an “example-based” methodology is adopted for the corpus annotation, which is different from the traditional annotation style. This approach provides the annotators with an example sentence rather than a linguistic category label. By avoiding linguistic technical terms, it is expected that any native speakers, with no special knowledge on linguistic analysis, can be an annotator without long training, and hence it can reduce the annotation cost. So far, 10,475 occurrences have been already annotated, with an inter-annotator agreement of 0.66 calculated by Cohen’s kappa. The initial disagreement analyses and future directions are discussed in the paper.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/617_Paper.pdf
Markdown (Informal)
[A Japanese Particle Corpus Built by Example-Based Annotation](http://www.lrec-conf.org/proceedings/lrec2010/pdf/617_Paper.pdf) (Hanaoka et al., LREC 2010)
ACL