@inproceedings{gemeda-yigezu-etal-2022-word,
title = "Word Level Language Identification in Code-mixed {K}annada-{E}nglish Texts using Deep Learning Approach",
author = "Gemeda Yigezu, Mesay and
Lambebo Tonja, Atnafu and
Kolesnikova, Olga and
Shahiki Tash, Moein and
Sidorov, Grigori and
Gelbukh, Alexander",
editor = "Chakravarthi, Bharathi Raja and
Murugappan, Abirami and
Chinnappa, Dhivya and
Hane, Adeep and
Kumeresan, Prasanna Kumar and
Ponnusamy, Rahul",
booktitle = "Proceedings of the 19th International Conference on Natural Language Processing (ICON): Shared Task on Word Level Language Identification in Code-mixed Kannada-English Texts",
month = dec,
year = "2022",
address = "IIIT Delhi, New Delhi, India",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.icon-wlli.6",
pages = "29--33",
abstract = "The goal of code-mixed language identification (LID) is to determine which language is spoken or written in a given segment of a speech, word, sentence, or document. Our task is to identify English, Kannada, and mixed language from the provided data. To train a model we used the CoLI-Kenglish dataset, which contains English, Kannada, and mixed-language words. In our work, we conducted several experiments in order to obtain the best performing model. Then, we implemented the best model by using Bidirectional Long Short Term Memory (Bi-LSTM), which outperformed the other trained models with an F1-score of 0.61{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gemeda-yigezu-etal-2022-word">
<titleInfo>
<title>Word Level Language Identification in Code-mixed Kannada-English Texts using Deep Learning Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mesay</namePart>
<namePart type="family">Gemeda Yigezu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atnafu</namePart>
<namePart type="family">Lambebo Tonja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olga</namePart>
<namePart type="family">Kolesnikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Moein</namePart>
<namePart type="family">Shahiki Tash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grigori</namePart>
<namePart type="family">Sidorov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Gelbukh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th International Conference on Natural Language Processing (ICON): Shared Task on Word Level Language Identification in Code-mixed Kannada-English Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abirami</namePart>
<namePart type="family">Murugappan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhivya</namePart>
<namePart type="family">Chinnappa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adeep</namePart>
<namePart type="family">Hane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prasanna</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Kumeresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Ponnusamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">IIIT Delhi, New Delhi, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The goal of code-mixed language identification (LID) is to determine which language is spoken or written in a given segment of a speech, word, sentence, or document. Our task is to identify English, Kannada, and mixed language from the provided data. To train a model we used the CoLI-Kenglish dataset, which contains English, Kannada, and mixed-language words. In our work, we conducted several experiments in order to obtain the best performing model. Then, we implemented the best model by using Bidirectional Long Short Term Memory (Bi-LSTM), which outperformed the other trained models with an F1-score of 0.61%.</abstract>
<identifier type="citekey">gemeda-yigezu-etal-2022-word</identifier>
<location>
<url>https://aclanthology.org/2022.icon-wlli.6</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>29</start>
<end>33</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Word Level Language Identification in Code-mixed Kannada-English Texts using Deep Learning Approach
%A Gemeda Yigezu, Mesay
%A Lambebo Tonja, Atnafu
%A Kolesnikova, Olga
%A Shahiki Tash, Moein
%A Sidorov, Grigori
%A Gelbukh, Alexander
%Y Chakravarthi, Bharathi Raja
%Y Murugappan, Abirami
%Y Chinnappa, Dhivya
%Y Hane, Adeep
%Y Kumeresan, Prasanna Kumar
%Y Ponnusamy, Rahul
%S Proceedings of the 19th International Conference on Natural Language Processing (ICON): Shared Task on Word Level Language Identification in Code-mixed Kannada-English Texts
%D 2022
%8 December
%I Association for Computational Linguistics
%C IIIT Delhi, New Delhi, India
%F gemeda-yigezu-etal-2022-word
%X The goal of code-mixed language identification (LID) is to determine which language is spoken or written in a given segment of a speech, word, sentence, or document. Our task is to identify English, Kannada, and mixed language from the provided data. To train a model we used the CoLI-Kenglish dataset, which contains English, Kannada, and mixed-language words. In our work, we conducted several experiments in order to obtain the best performing model. Then, we implemented the best model by using Bidirectional Long Short Term Memory (Bi-LSTM), which outperformed the other trained models with an F1-score of 0.61%.
%U https://aclanthology.org/2022.icon-wlli.6
%P 29-33
Markdown (Informal)
[Word Level Language Identification in Code-mixed Kannada-English Texts using Deep Learning Approach](https://aclanthology.org/2022.icon-wlli.6) (Gemeda Yigezu et al., ICON 2022)
ACL