@inproceedings{l-r-etal-2019-parts,
title = "Parts of Speech Tagging for {K}annada",
author = "L R, Swaroop and
Gowda G S, Rakshith and
U, Sourabh and
Hegde, Shriram",
editor = "Kovatchev, Venelin and
Temnikova, Irina and
{\v{S}}andrih, Branislava and
Nikolova, Ivelina",
booktitle = "Proceedings of the Student Research Workshop Associated with RANLP 2019",
month = sep,
year = "2019",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd.",
url = "https://aclanthology.org/R19-2005",
doi = "10.26615/issn.2603-2821.2019_005",
pages = "28--31",
abstract = "Parts of speech (POS) tagging is the process of assigning the part of speech tag to each and every word in a sentence. In this paper, we have presented POS tagger for Kannada, a low resource south Asian language, using Condition Random Fields. POS tagger developed in the work uses novel features native to Kannada language. The novel features include Sandhi splitting, where a compound word is broken down into two or more meaningful constituent words. The proposed model is trained and tested on the tagged dataset which contains 21 thousand sentences and achieves a highest accuracy of 94.56{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="l-r-etal-2019-parts">
<titleInfo>
<title>Parts of Speech Tagging for Kannada</title>
</titleInfo>
<name type="personal">
<namePart type="given">Swaroop</namePart>
<namePart type="family">L R</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rakshith</namePart>
<namePart type="family">Gowda G S</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sourabh</namePart>
<namePart type="family">U</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shriram</namePart>
<namePart type="family">Hegde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Student Research Workshop Associated with RANLP 2019</title>
</titleInfo>
<name type="personal">
<namePart type="given">Venelin</namePart>
<namePart type="family">Kovatchev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Irina</namePart>
<namePart type="family">Temnikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Branislava</namePart>
<namePart type="family">Šandrih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivelina</namePart>
<namePart type="family">Nikolova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Parts of speech (POS) tagging is the process of assigning the part of speech tag to each and every word in a sentence. In this paper, we have presented POS tagger for Kannada, a low resource south Asian language, using Condition Random Fields. POS tagger developed in the work uses novel features native to Kannada language. The novel features include Sandhi splitting, where a compound word is broken down into two or more meaningful constituent words. The proposed model is trained and tested on the tagged dataset which contains 21 thousand sentences and achieves a highest accuracy of 94.56%.</abstract>
<identifier type="citekey">l-r-etal-2019-parts</identifier>
<identifier type="doi">10.26615/issn.2603-2821.2019_005</identifier>
<location>
<url>https://aclanthology.org/R19-2005</url>
</location>
<part>
<date>2019-09</date>
<extent unit="page">
<start>28</start>
<end>31</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Parts of Speech Tagging for Kannada
%A L R, Swaroop
%A Gowda G S, Rakshith
%A U, Sourabh
%A Hegde, Shriram
%Y Kovatchev, Venelin
%Y Temnikova, Irina
%Y Šandrih, Branislava
%Y Nikolova, Ivelina
%S Proceedings of the Student Research Workshop Associated with RANLP 2019
%D 2019
%8 September
%I INCOMA Ltd.
%C Varna, Bulgaria
%F l-r-etal-2019-parts
%X Parts of speech (POS) tagging is the process of assigning the part of speech tag to each and every word in a sentence. In this paper, we have presented POS tagger for Kannada, a low resource south Asian language, using Condition Random Fields. POS tagger developed in the work uses novel features native to Kannada language. The novel features include Sandhi splitting, where a compound word is broken down into two or more meaningful constituent words. The proposed model is trained and tested on the tagged dataset which contains 21 thousand sentences and achieves a highest accuracy of 94.56%.
%R 10.26615/issn.2603-2821.2019_005
%U https://aclanthology.org/R19-2005
%U https://doi.org/10.26615/issn.2603-2821.2019_005
%P 28-31
Markdown (Informal)
[Parts of Speech Tagging for Kannada](https://aclanthology.org/R19-2005) (L R et al., RANLP 2019)
ACL
- Swaroop L R, Rakshith Gowda G S, Sourabh U, and Shriram Hegde. 2019. Parts of Speech Tagging for Kannada. In Proceedings of the Student Research Workshop Associated with RANLP 2019, pages 28–31, Varna, Bulgaria. INCOMA Ltd..