@inproceedings{aswani-gaizauskas-2010-english,
title = "{E}nglish-{H}indi Transliteration using Multiple Similarity Metrics",
author = "Aswani, Niraj and
Gaizauskas, Robert",
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/694_Paper.pdf",
abstract = "In this paper, we present an approach to measure the transliteration similarity of English-Hindi word pairs. Our approach has two components. First we propose a bi-directional mapping between one or more characters in the Devanagari script and one or more characters in the Roman script (pronounced as in English). This allows a given Hindi word written in Devanagari to be transliterated into the Roman script and vice-versa. Second, we present an algorithm for computing a similarity measure that is a variant of Dices coefficient measure and the LCSR measure and which also takes into account the constraints needed to match English-Hindi transliterated words. Finally, by evaluating various similarity metrics individually and together under a multiple measure agreement scenario, we show that it is possible to achieve a 0.92 f-measure in identifying English-Hindi word pairs that are transliterations. In order to assess the portability of our approach to other similar languages we adapt our system to the Gujarati language.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aswani-gaizauskas-2010-english">
<titleInfo>
<title>English-Hindi Transliteration using Multiple Similarity Metrics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Niraj</namePart>
<namePart type="family">Aswani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Gaizauskas</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 present an approach to measure the transliteration similarity of English-Hindi word pairs. Our approach has two components. First we propose a bi-directional mapping between one or more characters in the Devanagari script and one or more characters in the Roman script (pronounced as in English). This allows a given Hindi word written in Devanagari to be transliterated into the Roman script and vice-versa. Second, we present an algorithm for computing a similarity measure that is a variant of Dices coefficient measure and the LCSR measure and which also takes into account the constraints needed to match English-Hindi transliterated words. Finally, by evaluating various similarity metrics individually and together under a multiple measure agreement scenario, we show that it is possible to achieve a 0.92 f-measure in identifying English-Hindi word pairs that are transliterations. In order to assess the portability of our approach to other similar languages we adapt our system to the Gujarati language.</abstract>
<identifier type="citekey">aswani-gaizauskas-2010-english</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/694_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T English-Hindi Transliteration using Multiple Similarity Metrics
%A Aswani, Niraj
%A Gaizauskas, Robert
%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 aswani-gaizauskas-2010-english
%X In this paper, we present an approach to measure the transliteration similarity of English-Hindi word pairs. Our approach has two components. First we propose a bi-directional mapping between one or more characters in the Devanagari script and one or more characters in the Roman script (pronounced as in English). This allows a given Hindi word written in Devanagari to be transliterated into the Roman script and vice-versa. Second, we present an algorithm for computing a similarity measure that is a variant of Dices coefficient measure and the LCSR measure and which also takes into account the constraints needed to match English-Hindi transliterated words. Finally, by evaluating various similarity metrics individually and together under a multiple measure agreement scenario, we show that it is possible to achieve a 0.92 f-measure in identifying English-Hindi word pairs that are transliterations. In order to assess the portability of our approach to other similar languages we adapt our system to the Gujarati language.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/694_Paper.pdf
Markdown (Informal)
[English-Hindi Transliteration using Multiple Similarity Metrics](http://www.lrec-conf.org/proceedings/lrec2010/pdf/694_Paper.pdf) (Aswani & Gaizauskas, LREC 2010)
ACL