@inproceedings{appidi-etal-2020-creation-corpus,
title = "Creation of Corpus and Analysis in Code-Mixed {K}annada-{E}nglish Social Media Data for {POS} Tagging",
author = "Appidi, Abhinav Reddy and
Srirangam, Vamshi Krishna and
Suhas, Darsi and
Shrivastava, Manish",
editor = "Bhattacharyya, Pushpak and
Sharma, Dipti Misra and
Sangal, Rajeev",
booktitle = "Proceedings of the 17th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2020",
address = "Indian Institute of Technology Patna, Patna, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2020.icon-main.13",
pages = "101--107",
abstract = "Part-of-Speech (POS) is one of the essential tasks for many Natural Language Processing (NLP) applications. There has been a significant amount of work done in POS tagging for resource-rich languages. POS tagging is an essential phase of text analysis in understanding the semantics and context of language. These tags are useful for higher-level tasks such as building parse trees, which can be used for Named Entity Recognition, Coreference resolution, Sentiment Analysis, and Question Answering. There has been work done on code-mixed social media corpus but not on POS tagging of Kannada-English code-mixed data. Here, we present Kannada-English code- mixed social media corpus annotated with corresponding POS tags. We also experimented with machine learning classification models CRF, Bi-LSTM, and Bi-LSTM-CRF models on our corpus.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="appidi-etal-2020-creation-corpus">
<titleInfo>
<title>Creation of Corpus and Analysis in Code-Mixed Kannada-English Social Media Data for POS Tagging</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="given">Reddy</namePart>
<namePart type="family">Appidi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vamshi</namePart>
<namePart type="given">Krishna</namePart>
<namePart type="family">Srirangam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Darsi</namePart>
<namePart type="family">Suhas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manish</namePart>
<namePart type="family">Shrivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipti</namePart>
<namePart type="given">Misra</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajeev</namePart>
<namePart type="family">Sangal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">Indian Institute of Technology Patna, Patna, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Part-of-Speech (POS) is one of the essential tasks for many Natural Language Processing (NLP) applications. There has been a significant amount of work done in POS tagging for resource-rich languages. POS tagging is an essential phase of text analysis in understanding the semantics and context of language. These tags are useful for higher-level tasks such as building parse trees, which can be used for Named Entity Recognition, Coreference resolution, Sentiment Analysis, and Question Answering. There has been work done on code-mixed social media corpus but not on POS tagging of Kannada-English code-mixed data. Here, we present Kannada-English code- mixed social media corpus annotated with corresponding POS tags. We also experimented with machine learning classification models CRF, Bi-LSTM, and Bi-LSTM-CRF models on our corpus.</abstract>
<identifier type="citekey">appidi-etal-2020-creation-corpus</identifier>
<location>
<url>https://aclanthology.org/2020.icon-main.13</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>101</start>
<end>107</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Creation of Corpus and Analysis in Code-Mixed Kannada-English Social Media Data for POS Tagging
%A Appidi, Abhinav Reddy
%A Srirangam, Vamshi Krishna
%A Suhas, Darsi
%A Shrivastava, Manish
%Y Bhattacharyya, Pushpak
%Y Sharma, Dipti Misra
%Y Sangal, Rajeev
%S Proceedings of the 17th International Conference on Natural Language Processing (ICON)
%D 2020
%8 December
%I NLP Association of India (NLPAI)
%C Indian Institute of Technology Patna, Patna, India
%F appidi-etal-2020-creation-corpus
%X Part-of-Speech (POS) is one of the essential tasks for many Natural Language Processing (NLP) applications. There has been a significant amount of work done in POS tagging for resource-rich languages. POS tagging is an essential phase of text analysis in understanding the semantics and context of language. These tags are useful for higher-level tasks such as building parse trees, which can be used for Named Entity Recognition, Coreference resolution, Sentiment Analysis, and Question Answering. There has been work done on code-mixed social media corpus but not on POS tagging of Kannada-English code-mixed data. Here, we present Kannada-English code- mixed social media corpus annotated with corresponding POS tags. We also experimented with machine learning classification models CRF, Bi-LSTM, and Bi-LSTM-CRF models on our corpus.
%U https://aclanthology.org/2020.icon-main.13
%P 101-107
Markdown (Informal)
[Creation of Corpus and Analysis in Code-Mixed Kannada-English Social Media Data for POS Tagging](https://aclanthology.org/2020.icon-main.13) (Appidi et al., ICON 2020)
ACL