@inproceedings{richardson-etal-2014-bilingual,
title = "Bilingual Dictionary Construction with Transliteration Filtering",
author = "Richardson, John and
Nakazawa, Toshiaki and
Kurohashi, Sadao",
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/102_Paper.pdf",
pages = "1013--1017",
abstract = "In this paper we present a bilingual transliteration lexicon of 170K Japanese-English technical terms in the scientific domain. Translation pairs are extracted by filtering a large list of transliteration candidates generated automatically from a phrase table trained on parallel corpora. Filtering uses a novel transliteration similarity measure based on a discriminative phrase-based machine translation approach. We demonstrate that the extracted dictionary is accurate and of high recall (F1 score 0.8). Our lexicon contains not only single words but also multi-word expressions, and is freely available. Our experiments focus on Katakana-English lexicon construction, however it would be possible to apply the proposed methods to transliteration extraction for a variety of language pairs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="richardson-etal-2014-bilingual">
<titleInfo>
<title>Bilingual Dictionary Construction with Transliteration Filtering</title>
</titleInfo>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Richardson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toshiaki</namePart>
<namePart type="family">Nakazawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</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 bilingual transliteration lexicon of 170K Japanese-English technical terms in the scientific domain. Translation pairs are extracted by filtering a large list of transliteration candidates generated automatically from a phrase table trained on parallel corpora. Filtering uses a novel transliteration similarity measure based on a discriminative phrase-based machine translation approach. We demonstrate that the extracted dictionary is accurate and of high recall (F1 score 0.8). Our lexicon contains not only single words but also multi-word expressions, and is freely available. Our experiments focus on Katakana-English lexicon construction, however it would be possible to apply the proposed methods to transliteration extraction for a variety of language pairs.</abstract>
<identifier type="citekey">richardson-etal-2014-bilingual</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/102_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1013</start>
<end>1017</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bilingual Dictionary Construction with Transliteration Filtering
%A Richardson, John
%A Nakazawa, Toshiaki
%A Kurohashi, Sadao
%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 richardson-etal-2014-bilingual
%X In this paper we present a bilingual transliteration lexicon of 170K Japanese-English technical terms in the scientific domain. Translation pairs are extracted by filtering a large list of transliteration candidates generated automatically from a phrase table trained on parallel corpora. Filtering uses a novel transliteration similarity measure based on a discriminative phrase-based machine translation approach. We demonstrate that the extracted dictionary is accurate and of high recall (F1 score 0.8). Our lexicon contains not only single words but also multi-word expressions, and is freely available. Our experiments focus on Katakana-English lexicon construction, however it would be possible to apply the proposed methods to transliteration extraction for a variety of language pairs.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/102_Paper.pdf
%P 1013-1017
Markdown (Informal)
[Bilingual Dictionary Construction with Transliteration Filtering](http://www.lrec-conf.org/proceedings/lrec2014/pdf/102_Paper.pdf) (Richardson et al., LREC 2014)
ACL