@inproceedings{kubo-etal-2010-automatic,
title = "Automatic Term Recognition Based on the Statistical Differences of Relative Frequencies in Different Corpora",
author = "Kubo, Junko and
Tsuji, Keita and
Sugimoto, Shigeo",
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/347_Paper.pdf",
abstract = "In this paper, we propose a method for automatic term recognition (ATR) which uses the statistical differences of relative frequencies of terms in target domain corpus and elsewhere. Generally, the target terms appear more frequently in target domain corpus than in other domain corpora. Utilizing such characteristics will lead to the improvement of extraction performance. Most of the ATR methods proposed so far only use the target domain corpus and do not take such characteristics into account. For the extraction experiment, we used the abstracts of a women's studies journal as a target domain corpus and those of academic journals of 39 domains as other domain corpora. The women's studies terms which were used for extraction evaluation were manually identified terms in the abstracts. The extraction performance was analyzed and we found that our method outperformed earlier methods. The previous methods were based on C-value, FLR and methods which were also used with other domain corpora.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kubo-etal-2010-automatic">
<titleInfo>
<title>Automatic Term Recognition Based on the Statistical Differences of Relative Frequencies in Different Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junko</namePart>
<namePart type="family">Kubo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keita</namePart>
<namePart type="family">Tsuji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shigeo</namePart>
<namePart type="family">Sugimoto</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>In this paper, we propose a method for automatic term recognition (ATR) which uses the statistical differences of relative frequencies of terms in target domain corpus and elsewhere. Generally, the target terms appear more frequently in target domain corpus than in other domain corpora. Utilizing such characteristics will lead to the improvement of extraction performance. Most of the ATR methods proposed so far only use the target domain corpus and do not take such characteristics into account. For the extraction experiment, we used the abstracts of a women’s studies journal as a target domain corpus and those of academic journals of 39 domains as other domain corpora. The women’s studies terms which were used for extraction evaluation were manually identified terms in the abstracts. The extraction performance was analyzed and we found that our method outperformed earlier methods. The previous methods were based on C-value, FLR and methods which were also used with other domain corpora.</abstract>
<identifier type="citekey">kubo-etal-2010-automatic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/347_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Term Recognition Based on the Statistical Differences of Relative Frequencies in Different Corpora
%A Kubo, Junko
%A Tsuji, Keita
%A Sugimoto, Shigeo
%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 kubo-etal-2010-automatic
%X In this paper, we propose a method for automatic term recognition (ATR) which uses the statistical differences of relative frequencies of terms in target domain corpus and elsewhere. Generally, the target terms appear more frequently in target domain corpus than in other domain corpora. Utilizing such characteristics will lead to the improvement of extraction performance. Most of the ATR methods proposed so far only use the target domain corpus and do not take such characteristics into account. For the extraction experiment, we used the abstracts of a women’s studies journal as a target domain corpus and those of academic journals of 39 domains as other domain corpora. The women’s studies terms which were used for extraction evaluation were manually identified terms in the abstracts. The extraction performance was analyzed and we found that our method outperformed earlier methods. The previous methods were based on C-value, FLR and methods which were also used with other domain corpora.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/347_Paper.pdf
Markdown (Informal)
[Automatic Term Recognition Based on the Statistical Differences of Relative Frequencies in Different Corpora](http://www.lrec-conf.org/proceedings/lrec2010/pdf/347_Paper.pdf) (Kubo et al., LREC 2010)
ACL