@inproceedings{mori-etal-2014-japanese,
title = "A {J}apanese Word Dependency Corpus",
author = "Mori, Shinsuke and
Ogura, Hideki and
Sasada, Tetsuro",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/42_Paper.pdf",
pages = "753--758",
abstract = "In this paper, we present a corpus annotated with dependency relationships in Japanese. It contains about 30 thousand sentences in various domains. Six domains in Balanced Corpus of Contemporary Written Japanese have part-of-speech and pronunciation annotation as well. Dictionary example sentences have pronunciation annotation and cover basic vocabulary in Japanese with English sentence equivalent. Economic newspaper articles also have pronunciation annotation and the topics are similar to those of Penn Treebank. Invention disclosures do not have other annotation, but it has a clear application, machine translation. The unit of our corpus is word like other languages contrary to existing Japanese corpora whose unit is phrase called bunsetsu. Each sentence is manually segmented into words. We first present the specification of our corpus. Then we give a detailed explanation about our standard of word dependency. We also report some preliminary results of an MST-based dependency parser on our corpus.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mori-etal-2014-japanese">
<titleInfo>
<title>A Japanese Word Dependency Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shinsuke</namePart>
<namePart type="family">Mori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hideki</namePart>
<namePart type="family">Ogura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tetsuro</namePart>
<namePart type="family">Sasada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present a corpus annotated with dependency relationships in Japanese. It contains about 30 thousand sentences in various domains. Six domains in Balanced Corpus of Contemporary Written Japanese have part-of-speech and pronunciation annotation as well. Dictionary example sentences have pronunciation annotation and cover basic vocabulary in Japanese with English sentence equivalent. Economic newspaper articles also have pronunciation annotation and the topics are similar to those of Penn Treebank. Invention disclosures do not have other annotation, but it has a clear application, machine translation. The unit of our corpus is word like other languages contrary to existing Japanese corpora whose unit is phrase called bunsetsu. Each sentence is manually segmented into words. We first present the specification of our corpus. Then we give a detailed explanation about our standard of word dependency. We also report some preliminary results of an MST-based dependency parser on our corpus.</abstract>
<identifier type="citekey">mori-etal-2014-japanese</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/42_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>753</start>
<end>758</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Japanese Word Dependency Corpus
%A Mori, Shinsuke
%A Ogura, Hideki
%A Sasada, Tetsuro
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F mori-etal-2014-japanese
%X In this paper, we present a corpus annotated with dependency relationships in Japanese. It contains about 30 thousand sentences in various domains. Six domains in Balanced Corpus of Contemporary Written Japanese have part-of-speech and pronunciation annotation as well. Dictionary example sentences have pronunciation annotation and cover basic vocabulary in Japanese with English sentence equivalent. Economic newspaper articles also have pronunciation annotation and the topics are similar to those of Penn Treebank. Invention disclosures do not have other annotation, but it has a clear application, machine translation. The unit of our corpus is word like other languages contrary to existing Japanese corpora whose unit is phrase called bunsetsu. Each sentence is manually segmented into words. We first present the specification of our corpus. Then we give a detailed explanation about our standard of word dependency. We also report some preliminary results of an MST-based dependency parser on our corpus.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/42_Paper.pdf
%P 753-758
Markdown (Informal)
[A Japanese Word Dependency Corpus](http://www.lrec-conf.org/proceedings/lrec2014/pdf/42_Paper.pdf) (Mori et al., LREC 2014)
ACL
- Shinsuke Mori, Hideki Ogura, and Tetsuro Sasada. 2014. A Japanese Word Dependency Corpus. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 753–758, Reykjavik, Iceland. European Language Resources Association (ELRA).