@inproceedings{baker-brew-2008-statistical,
title = "Statistical Identification of {E}nglish Loanwords in {K}orean Using Automatically Generated Training Data",
author = "Baker, Kirk and
Brew, Chris",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/295_paper.pdf",
abstract = "This paper describes an accurate, extensible method for automatically classifying unknown foreign words that requires minimal monolingual resources and no bilingual training data (which is often difficult to obtain for an arbitrary language pair). We use a small set of phonologically-based transliteration rules to generate a potentially unlimited amount of pseudo-data that can be used to train a classifier to distinguish etymological classes of actual words. We ran a series of experiments on identifying English loanwords in Korean, in order to explore the consequences of using pseudo-data in place of the original training data. Results show that a sufficient quantity of automatically generated training data, even produced by fairly low precision transliteration rules, can be used to train a classifier that performs within 0.3{\%} of one trained on actual English loanwords (96{\%} accuracy).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="baker-brew-2008-statistical">
<titleInfo>
<title>Statistical Identification of English Loanwords in Korean Using Automatically Generated Training Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Baker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Brew</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes an accurate, extensible method for automatically classifying unknown foreign words that requires minimal monolingual resources and no bilingual training data (which is often difficult to obtain for an arbitrary language pair). We use a small set of phonologically-based transliteration rules to generate a potentially unlimited amount of pseudo-data that can be used to train a classifier to distinguish etymological classes of actual words. We ran a series of experiments on identifying English loanwords in Korean, in order to explore the consequences of using pseudo-data in place of the original training data. Results show that a sufficient quantity of automatically generated training data, even produced by fairly low precision transliteration rules, can be used to train a classifier that performs within 0.3% of one trained on actual English loanwords (96% accuracy).</abstract>
<identifier type="citekey">baker-brew-2008-statistical</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/295_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Statistical Identification of English Loanwords in Korean Using Automatically Generated Training Data
%A Baker, Kirk
%A Brew, Chris
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F baker-brew-2008-statistical
%X This paper describes an accurate, extensible method for automatically classifying unknown foreign words that requires minimal monolingual resources and no bilingual training data (which is often difficult to obtain for an arbitrary language pair). We use a small set of phonologically-based transliteration rules to generate a potentially unlimited amount of pseudo-data that can be used to train a classifier to distinguish etymological classes of actual words. We ran a series of experiments on identifying English loanwords in Korean, in order to explore the consequences of using pseudo-data in place of the original training data. Results show that a sufficient quantity of automatically generated training data, even produced by fairly low precision transliteration rules, can be used to train a classifier that performs within 0.3% of one trained on actual English loanwords (96% accuracy).
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/295_paper.pdf
Markdown (Informal)
[Statistical Identification of English Loanwords in Korean Using Automatically Generated Training Data](http://www.lrec-conf.org/proceedings/lrec2008/pdf/295_paper.pdf) (Baker & Brew, LREC 2008)
ACL