@inproceedings{kageura-kikui-2006-self,
title = "A Self-Referring Quantitative Evaluation of the {ATR} Basic Travel Expression Corpus ({BTEC})",
author = "Kageura, Kyo and
Kikui, Genichiro",
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/55_pdf.pdf",
abstract = "In this paper we evaluate the Basic Travel Expression Corpus (BTEC), developed by ATR (Advanced Telecommunication Research Laboratory), Japan. BTEC was specifically developed as a wide-coverage, consistent corpus containing basic Japanese travel expressions with English counterparts, for the purpose of providing basic data for the development of high quality speech translation systems. To evaluate the corpus, we introduce a quantitative method for evaluating the sufficiency of qualitatively well-defined corpora, on the basis of LNRE methods that can estimate the potential growth patterns of various sparse data by fitting various skewed distributions such as the Zipfian group of distributions, lognormal distribution, and inverse Gauss-Poisson distribution to them. The analyses show the coverage of lexical items of BTEC vis-a-vis the possible targets implicitly defined by the corpus itself, and thus provides basic insights into strategies for enhancing BTEC in future.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kageura-kikui-2006-self">
<titleInfo>
<title>A Self-Referring Quantitative Evaluation of the ATR Basic Travel Expression Corpus (BTEC)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kyo</namePart>
<namePart type="family">Kageura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Genichiro</namePart>
<namePart type="family">Kikui</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>In this paper we evaluate the Basic Travel Expression Corpus (BTEC), developed by ATR (Advanced Telecommunication Research Laboratory), Japan. BTEC was specifically developed as a wide-coverage, consistent corpus containing basic Japanese travel expressions with English counterparts, for the purpose of providing basic data for the development of high quality speech translation systems. To evaluate the corpus, we introduce a quantitative method for evaluating the sufficiency of qualitatively well-defined corpora, on the basis of LNRE methods that can estimate the potential growth patterns of various sparse data by fitting various skewed distributions such as the Zipfian group of distributions, lognormal distribution, and inverse Gauss-Poisson distribution to them. The analyses show the coverage of lexical items of BTEC vis-a-vis the possible targets implicitly defined by the corpus itself, and thus provides basic insights into strategies for enhancing BTEC in future.</abstract>
<identifier type="citekey">kageura-kikui-2006-self</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/55_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Self-Referring Quantitative Evaluation of the ATR Basic Travel Expression Corpus (BTEC)
%A Kageura, Kyo
%A Kikui, Genichiro
%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 kageura-kikui-2006-self
%X In this paper we evaluate the Basic Travel Expression Corpus (BTEC), developed by ATR (Advanced Telecommunication Research Laboratory), Japan. BTEC was specifically developed as a wide-coverage, consistent corpus containing basic Japanese travel expressions with English counterparts, for the purpose of providing basic data for the development of high quality speech translation systems. To evaluate the corpus, we introduce a quantitative method for evaluating the sufficiency of qualitatively well-defined corpora, on the basis of LNRE methods that can estimate the potential growth patterns of various sparse data by fitting various skewed distributions such as the Zipfian group of distributions, lognormal distribution, and inverse Gauss-Poisson distribution to them. The analyses show the coverage of lexical items of BTEC vis-a-vis the possible targets implicitly defined by the corpus itself, and thus provides basic insights into strategies for enhancing BTEC in future.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/55_pdf.pdf
Markdown (Informal)
[A Self-Referring Quantitative Evaluation of the ATR Basic Travel Expression Corpus (BTEC)](http://www.lrec-conf.org/proceedings/lrec2006/pdf/55_pdf.pdf) (Kageura & Kikui, LREC 2006)
ACL