@inproceedings{gupta-etal-2012-mining,
title = "Mining {H}indi-{E}nglish Transliteration Pairs from Online {H}indi Lyrics",
author = "Gupta, Kanika and
Choudhury, Monojit and
Bali, Kalika",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/365_Paper.pdf",
pages = "2459--2465",
abstract = "This paper describes a method to mine Hindi-English transliteration pairs from online Hindi song lyrics. The technique is based on the observations that lyrics are transliterated word-by-word, maintaining the precise word order. The mining task is nevertheless challenging because the Hindi lyrics and its transliterations are usually available from different, often unrelated, websites. Therefore, it is a non-trivial task to match the Hindi lyrics to their transliterated counterparts. Moreover, there are various types of noise in lyrics data that needs to be appropriately handled before songs can be aligned at word level. The mined data of 30823 unique Hindi-English transliteration pairs with an accuracy of more than 92{\%} is available publicly. Although the present work reports mining of Hindi-English word pairs, the same technique can be easily adapted for other languages for which song lyrics are available online in native and Roman scripts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gupta-etal-2012-mining">
<titleInfo>
<title>Mining Hindi-English Transliteration Pairs from Online Hindi Lyrics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kanika</namePart>
<namePart type="family">Gupta</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>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes a method to mine Hindi-English transliteration pairs from online Hindi song lyrics. The technique is based on the observations that lyrics are transliterated word-by-word, maintaining the precise word order. The mining task is nevertheless challenging because the Hindi lyrics and its transliterations are usually available from different, often unrelated, websites. Therefore, it is a non-trivial task to match the Hindi lyrics to their transliterated counterparts. Moreover, there are various types of noise in lyrics data that needs to be appropriately handled before songs can be aligned at word level. The mined data of 30823 unique Hindi-English transliteration pairs with an accuracy of more than 92% is available publicly. Although the present work reports mining of Hindi-English word pairs, the same technique can be easily adapted for other languages for which song lyrics are available online in native and Roman scripts.</abstract>
<identifier type="citekey">gupta-etal-2012-mining</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/365_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2459</start>
<end>2465</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mining Hindi-English Transliteration Pairs from Online Hindi Lyrics
%A Gupta, Kanika
%A Choudhury, Monojit
%A Bali, Kalika
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F gupta-etal-2012-mining
%X This paper describes a method to mine Hindi-English transliteration pairs from online Hindi song lyrics. The technique is based on the observations that lyrics are transliterated word-by-word, maintaining the precise word order. The mining task is nevertheless challenging because the Hindi lyrics and its transliterations are usually available from different, often unrelated, websites. Therefore, it is a non-trivial task to match the Hindi lyrics to their transliterated counterparts. Moreover, there are various types of noise in lyrics data that needs to be appropriately handled before songs can be aligned at word level. The mined data of 30823 unique Hindi-English transliteration pairs with an accuracy of more than 92% is available publicly. Although the present work reports mining of Hindi-English word pairs, the same technique can be easily adapted for other languages for which song lyrics are available online in native and Roman scripts.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/365_Paper.pdf
%P 2459-2465
Markdown (Informal)
[Mining Hindi-English Transliteration Pairs from Online Hindi Lyrics](http://www.lrec-conf.org/proceedings/lrec2012/pdf/365_Paper.pdf) (Gupta et al., LREC 2012)
ACL