@inproceedings{utsumi-2014-character,
title = "A Character-based Approach to Distributional Semantic Models: Exploiting Kanji Characters for Constructing {J}apanese{W}ord Vectors",
author = "Utsumi, Akira",
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/144_Paper.pdf",
pages = "4444--4450",
abstract = "Many Japanese words are made of kanji characters, which themselves represent meanings. However traditional word-based distributional semantic models (DSMs) do not benefit from the useful semantic information of kanji characters. In this paper, we propose a method for exploiting the semantic information of kanji characters for constructing Japanese word vectors in DSMs. In the proposed method, the semantic representations of kanji characters (i.e, kanji vectors) are constructed first using the techniques of DSMs, and then word vectors are computed by combining the vectors of constituent kanji characters using vector composition methods. The evaluation experiment using a synonym identification task demonstrates that the kanji-based DSM achieves the best performance when a kanji-kanji matrix is weighted by positive pointwise mutual information and word vectors are composed by weighted multiplication. Comparison between kanji-based DSMs and word-based DSMs reveals that our kanji-based DSMs generally outperform latent semantic analysis, and also surpasses the best score word-based DSM for infrequent words comprising only frequent kanji characters. These findings clearly indicate that kanji-based DSMs are beneficial in improvement of quality of Japanese word vectors.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="utsumi-2014-character">
<titleInfo>
<title>A Character-based Approach to Distributional Semantic Models: Exploiting Kanji Characters for Constructing JapaneseWord Vectors</title>
</titleInfo>
<name type="personal">
<namePart type="given">Akira</namePart>
<namePart type="family">Utsumi</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>Many Japanese words are made of kanji characters, which themselves represent meanings. However traditional word-based distributional semantic models (DSMs) do not benefit from the useful semantic information of kanji characters. In this paper, we propose a method for exploiting the semantic information of kanji characters for constructing Japanese word vectors in DSMs. In the proposed method, the semantic representations of kanji characters (i.e, kanji vectors) are constructed first using the techniques of DSMs, and then word vectors are computed by combining the vectors of constituent kanji characters using vector composition methods. The evaluation experiment using a synonym identification task demonstrates that the kanji-based DSM achieves the best performance when a kanji-kanji matrix is weighted by positive pointwise mutual information and word vectors are composed by weighted multiplication. Comparison between kanji-based DSMs and word-based DSMs reveals that our kanji-based DSMs generally outperform latent semantic analysis, and also surpasses the best score word-based DSM for infrequent words comprising only frequent kanji characters. These findings clearly indicate that kanji-based DSMs are beneficial in improvement of quality of Japanese word vectors.</abstract>
<identifier type="citekey">utsumi-2014-character</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/144_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>4444</start>
<end>4450</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Character-based Approach to Distributional Semantic Models: Exploiting Kanji Characters for Constructing JapaneseWord Vectors
%A Utsumi, Akira
%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 utsumi-2014-character
%X Many Japanese words are made of kanji characters, which themselves represent meanings. However traditional word-based distributional semantic models (DSMs) do not benefit from the useful semantic information of kanji characters. In this paper, we propose a method for exploiting the semantic information of kanji characters for constructing Japanese word vectors in DSMs. In the proposed method, the semantic representations of kanji characters (i.e, kanji vectors) are constructed first using the techniques of DSMs, and then word vectors are computed by combining the vectors of constituent kanji characters using vector composition methods. The evaluation experiment using a synonym identification task demonstrates that the kanji-based DSM achieves the best performance when a kanji-kanji matrix is weighted by positive pointwise mutual information and word vectors are composed by weighted multiplication. Comparison between kanji-based DSMs and word-based DSMs reveals that our kanji-based DSMs generally outperform latent semantic analysis, and also surpasses the best score word-based DSM for infrequent words comprising only frequent kanji characters. These findings clearly indicate that kanji-based DSMs are beneficial in improvement of quality of Japanese word vectors.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/144_Paper.pdf
%P 4444-4450
Markdown (Informal)
[A Character-based Approach to Distributional Semantic Models: Exploiting Kanji Characters for Constructing JapaneseWord Vectors](http://www.lrec-conf.org/proceedings/lrec2014/pdf/144_Paper.pdf) (Utsumi, LREC 2014)
ACL