@inproceedings{b-etal-2010-resource,
title = "Resource Creation for Training and Testing of Transliteration Systems for {I}ndian Languages",
author = "B., Sowmya V. and
Choudhury, Monojit and
Bali, Kalika and
Dasgupta, Tirthankar and
Basu, Anupam",
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/182_Paper.pdf",
abstract = "Machine transliteration is used in a number of NLP applications ranging from machine translation and information retrieval to input mechanisms for non-roman scripts. Many popular Input Method Editors for Indian languages, like Baraha, Akshara, Quillpad etc, use back-transliteration as a mechanism to allow users to input text in a number of Indian language. The lack of a standard dataset to evaluate these systems makes it difficult to make any meaningful comparisons of their relative accuracies. In this paper, we describe the methodology for the creation of a dataset of {\textasciitilde}2500 transliterated sentence pairs each in Bangla, Hindi and Telugu. The data was collected across three different modes from a total of 60 users. We believe that this dataset will prove useful not only for the evaluation and training of back-transliteration systems but also help in the linguistic analysis of the process of transliterating Indian languages from native scripts to Roman.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="b-etal-2010-resource">
<titleInfo>
<title>Resource Creation for Training and Testing of Transliteration Systems for Indian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sowmya</namePart>
<namePart type="given">V</namePart>
<namePart type="family">B.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Monojit</namePart>
<namePart type="family">Choudhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tirthankar</namePart>
<namePart type="family">Dasgupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anupam</namePart>
<namePart type="family">Basu</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>Machine transliteration is used in a number of NLP applications ranging from machine translation and information retrieval to input mechanisms for non-roman scripts. Many popular Input Method Editors for Indian languages, like Baraha, Akshara, Quillpad etc, use back-transliteration as a mechanism to allow users to input text in a number of Indian language. The lack of a standard dataset to evaluate these systems makes it difficult to make any meaningful comparisons of their relative accuracies. In this paper, we describe the methodology for the creation of a dataset of ~2500 transliterated sentence pairs each in Bangla, Hindi and Telugu. The data was collected across three different modes from a total of 60 users. We believe that this dataset will prove useful not only for the evaluation and training of back-transliteration systems but also help in the linguistic analysis of the process of transliterating Indian languages from native scripts to Roman.</abstract>
<identifier type="citekey">b-etal-2010-resource</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/182_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Resource Creation for Training and Testing of Transliteration Systems for Indian Languages
%A B., Sowmya V.
%A Choudhury, Monojit
%A Bali, Kalika
%A Dasgupta, Tirthankar
%A Basu, Anupam
%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 b-etal-2010-resource
%X Machine transliteration is used in a number of NLP applications ranging from machine translation and information retrieval to input mechanisms for non-roman scripts. Many popular Input Method Editors for Indian languages, like Baraha, Akshara, Quillpad etc, use back-transliteration as a mechanism to allow users to input text in a number of Indian language. The lack of a standard dataset to evaluate these systems makes it difficult to make any meaningful comparisons of their relative accuracies. In this paper, we describe the methodology for the creation of a dataset of ~2500 transliterated sentence pairs each in Bangla, Hindi and Telugu. The data was collected across three different modes from a total of 60 users. We believe that this dataset will prove useful not only for the evaluation and training of back-transliteration systems but also help in the linguistic analysis of the process of transliterating Indian languages from native scripts to Roman.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/182_Paper.pdf
Markdown (Informal)
[Resource Creation for Training and Testing of Transliteration Systems for Indian Languages](http://www.lrec-conf.org/proceedings/lrec2010/pdf/182_Paper.pdf) (B. et al., LREC 2010)
ACL