@inproceedings{sankaran-etal-2008-common,
title = "A Common Parts-of-Speech Tagset Framework for {I}ndian Languages",
author = "Sankaran, Baskaran and
Bali, Kalika and
Choudhury, Monojit and
Bhattacharya, Tanmoy and
Bhattacharyya, Pushpak and
Jha, Girish Nath and
Rajendran, S. and
Saravanan, K. and
Sobha, L. and
Subbarao, K.V.",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/337_paper.pdf",
abstract = "We present a universal Parts-of-Speech (POS) tagset framework covering most of the Indian languages (ILs) following the hierarchical and decomposable tagset schema. In spite of significant number of speakers, there is no workable POS tagset and tagger for most ILs, which serve as fundamental building blocks for NLP research. Existing IL POS tagsets are often designed for a specific language; the few that have been designed for multiple languages cover only shallow linguistic features ignoring linguistic richness and the idiosyncrasies. The new framework that is proposed here addresses these deficiencies in an efficient and principled manner. We follow a hierarchical schema similar to that of EAGLES and this enables the framework to be flexible enough to capture rich features of a language/ language family, even while capturing the shared linguistic structures in a methodical way. The proposed common framework further facilitates the sharing and reusability of scarce resources in these languages and ensures cross-linguistic compatibility.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sankaran-etal-2008-common">
<titleInfo>
<title>A Common Parts-of-Speech Tagset Framework for Indian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Baskaran</namePart>
<namePart type="family">Sankaran</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">Monojit</namePart>
<namePart type="family">Choudhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Bhattacharya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Girish</namePart>
<namePart type="given">Nath</namePart>
<namePart type="family">Jha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">S</namePart>
<namePart type="family">Rajendran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">K</namePart>
<namePart type="family">Saravanan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">L</namePart>
<namePart type="family">Sobha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">K</namePart>
<namePart type="given">V</namePart>
<namePart type="family">Subbarao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a universal Parts-of-Speech (POS) tagset framework covering most of the Indian languages (ILs) following the hierarchical and decomposable tagset schema. In spite of significant number of speakers, there is no workable POS tagset and tagger for most ILs, which serve as fundamental building blocks for NLP research. Existing IL POS tagsets are often designed for a specific language; the few that have been designed for multiple languages cover only shallow linguistic features ignoring linguistic richness and the idiosyncrasies. The new framework that is proposed here addresses these deficiencies in an efficient and principled manner. We follow a hierarchical schema similar to that of EAGLES and this enables the framework to be flexible enough to capture rich features of a language/ language family, even while capturing the shared linguistic structures in a methodical way. The proposed common framework further facilitates the sharing and reusability of scarce resources in these languages and ensures cross-linguistic compatibility.</abstract>
<identifier type="citekey">sankaran-etal-2008-common</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/337_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Common Parts-of-Speech Tagset Framework for Indian Languages
%A Sankaran, Baskaran
%A Bali, Kalika
%A Choudhury, Monojit
%A Bhattacharya, Tanmoy
%A Bhattacharyya, Pushpak
%A Jha, Girish Nath
%A Rajendran, S.
%A Saravanan, K.
%A Sobha, L.
%A Subbarao, K. V.
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F sankaran-etal-2008-common
%X We present a universal Parts-of-Speech (POS) tagset framework covering most of the Indian languages (ILs) following the hierarchical and decomposable tagset schema. In spite of significant number of speakers, there is no workable POS tagset and tagger for most ILs, which serve as fundamental building blocks for NLP research. Existing IL POS tagsets are often designed for a specific language; the few that have been designed for multiple languages cover only shallow linguistic features ignoring linguistic richness and the idiosyncrasies. The new framework that is proposed here addresses these deficiencies in an efficient and principled manner. We follow a hierarchical schema similar to that of EAGLES and this enables the framework to be flexible enough to capture rich features of a language/ language family, even while capturing the shared linguistic structures in a methodical way. The proposed common framework further facilitates the sharing and reusability of scarce resources in these languages and ensures cross-linguistic compatibility.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/337_paper.pdf
Markdown (Informal)
[A Common Parts-of-Speech Tagset Framework for Indian Languages](http://www.lrec-conf.org/proceedings/lrec2008/pdf/337_paper.pdf) (Sankaran et al., LREC 2008)
ACL
- Baskaran Sankaran, Kalika Bali, Monojit Choudhury, Tanmoy Bhattacharya, Pushpak Bhattacharyya, Girish Nath Jha, S. Rajendran, K. Saravanan, L. Sobha, and K.V. Subbarao. 2008. A Common Parts-of-Speech Tagset Framework for Indian Languages. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).