@inproceedings{qian-etal-2010-python,
title = "A Python Toolkit for Universal Transliteration",
author = "Qian, Ting and
Hollingshead, Kristy and
Yoon, Su-youn and
Kim, Kyoung-young and
Sproat, Richard",
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/30_Paper.pdf",
abstract = "We describe ScriptTranscriber, an open source toolkit for extracting transliterations in comparable corpora from languages written in different scripts. The system includes various methods for extracting potential terms of interest from raw text, for providing guesses on the pronunciations of terms, and for comparing two strings as possible transliterations using both phonetic and temporal measures. The system works with any script in the Unicode Basic Multilingual Plane and is easily extended to include new modules. Given comparable corpora, such as newswire text, in a pair of languages that use different scripts, ScriptTranscriber provides an easy way to mine transliterations from the comparable texts. This is particularly useful for underresourced languages, where training data for transliteration may be lacking, and where it is thus hard to train good transliterators. ScriptTranscriber provides an open source package that allows for ready incorporation of more sophisticated modules ― e.g. a trained transliteration model for a particular language pair. ScriptTranscriber is available as part of the nltk contrib source tree at \url{http://code.google.com/p/nltk/}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qian-etal-2010-python">
<titleInfo>
<title>A Python Toolkit for Universal Transliteration</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Qian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kristy</namePart>
<namePart type="family">Hollingshead</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Su-youn</namePart>
<namePart type="family">Yoon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyoung-young</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Sproat</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>We describe ScriptTranscriber, an open source toolkit for extracting transliterations in comparable corpora from languages written in different scripts. The system includes various methods for extracting potential terms of interest from raw text, for providing guesses on the pronunciations of terms, and for comparing two strings as possible transliterations using both phonetic and temporal measures. The system works with any script in the Unicode Basic Multilingual Plane and is easily extended to include new modules. Given comparable corpora, such as newswire text, in a pair of languages that use different scripts, ScriptTranscriber provides an easy way to mine transliterations from the comparable texts. This is particularly useful for underresourced languages, where training data for transliteration may be lacking, and where it is thus hard to train good transliterators. ScriptTranscriber provides an open source package that allows for ready incorporation of more sophisticated modules ― e.g. a trained transliteration model for a particular language pair. ScriptTranscriber is available as part of the nltk contrib source tree at http://code.google.com/p/nltk/.</abstract>
<identifier type="citekey">qian-etal-2010-python</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/30_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Python Toolkit for Universal Transliteration
%A Qian, Ting
%A Hollingshead, Kristy
%A Yoon, Su-youn
%A Kim, Kyoung-young
%A Sproat, Richard
%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 qian-etal-2010-python
%X We describe ScriptTranscriber, an open source toolkit for extracting transliterations in comparable corpora from languages written in different scripts. The system includes various methods for extracting potential terms of interest from raw text, for providing guesses on the pronunciations of terms, and for comparing two strings as possible transliterations using both phonetic and temporal measures. The system works with any script in the Unicode Basic Multilingual Plane and is easily extended to include new modules. Given comparable corpora, such as newswire text, in a pair of languages that use different scripts, ScriptTranscriber provides an easy way to mine transliterations from the comparable texts. This is particularly useful for underresourced languages, where training data for transliteration may be lacking, and where it is thus hard to train good transliterators. ScriptTranscriber provides an open source package that allows for ready incorporation of more sophisticated modules ― e.g. a trained transliteration model for a particular language pair. ScriptTranscriber is available as part of the nltk contrib source tree at http://code.google.com/p/nltk/.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/30_Paper.pdf
Markdown (Informal)
[A Python Toolkit for Universal Transliteration](http://www.lrec-conf.org/proceedings/lrec2010/pdf/30_Paper.pdf) (Qian et al., LREC 2010)
ACL
- Ting Qian, Kristy Hollingshead, Su-youn Yoon, Kyoung-young Kim, and Richard Sproat. 2010. A Python Toolkit for Universal Transliteration. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).