@inproceedings{lambebo-tonja-etal-2022-transformer,
title = "Transformer-based Model for Word Level Language Identification in Code-mixed {K}annada-{E}nglish Texts",
author = "Lambebo Tonja, Atnafu and
Gemeda Yigezu, Mesay 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.4",
pages = "18--24",
abstract = "Language Identification at the Word Level in Kannada-English Texts. This paper describes the system paper of CoLI-Kanglish 2022 shared task. The goal of this task is to identify the different languages used in CoLI-Kanglish 2022. This dataset is distributed into different categories including Kannada, English, Mixed-Language, Location, Name, and Others. This Code-Mix was compiled by CoLI-Kanglish 2022 organizers from posts on social media. We use two classification techniques, KNN and SVM, and achieve an F1-score of 0.58 and place third out of nine competitors.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lambebo-tonja-etal-2022-transformer">
<titleInfo>
<title>Transformer-based Model for Word Level Language Identification in Code-mixed Kannada-English Texts</title>
</titleInfo>
<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">Mesay</namePart>
<namePart type="family">Gemeda Yigezu</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>Language Identification at the Word Level in Kannada-English Texts. This paper describes the system paper of CoLI-Kanglish 2022 shared task. The goal of this task is to identify the different languages used in CoLI-Kanglish 2022. This dataset is distributed into different categories including Kannada, English, Mixed-Language, Location, Name, and Others. This Code-Mix was compiled by CoLI-Kanglish 2022 organizers from posts on social media. We use two classification techniques, KNN and SVM, and achieve an F1-score of 0.58 and place third out of nine competitors.</abstract>
<identifier type="citekey">lambebo-tonja-etal-2022-transformer</identifier>
<location>
<url>https://aclanthology.org/2022.icon-wlli.4</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>18</start>
<end>24</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Transformer-based Model for Word Level Language Identification in Code-mixed Kannada-English Texts
%A Lambebo Tonja, Atnafu
%A Gemeda Yigezu, Mesay
%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 lambebo-tonja-etal-2022-transformer
%X Language Identification at the Word Level in Kannada-English Texts. This paper describes the system paper of CoLI-Kanglish 2022 shared task. The goal of this task is to identify the different languages used in CoLI-Kanglish 2022. This dataset is distributed into different categories including Kannada, English, Mixed-Language, Location, Name, and Others. This Code-Mix was compiled by CoLI-Kanglish 2022 organizers from posts on social media. We use two classification techniques, KNN and SVM, and achieve an F1-score of 0.58 and place third out of nine competitors.
%U https://aclanthology.org/2022.icon-wlli.4
%P 18-24
Markdown (Informal)
[Transformer-based Model for Word Level Language Identification in Code-mixed Kannada-English Texts](https://aclanthology.org/2022.icon-wlli.4) (Lambebo Tonja et al., ICON 2022)
ACL
- Atnafu Lambebo Tonja, Mesay Gemeda Yigezu, Olga Kolesnikova, Moein Shahiki Tash, Grigori Sidorov, and Alexander Gelbukh. 2022. Transformer-based Model for Word Level Language Identification in Code-mixed Kannada-English Texts. In Proceedings of the 19th International Conference on Natural Language Processing (ICON): Shared Task on Word Level Language Identification in Code-mixed Kannada-English Texts, pages 18–24, IIIT Delhi, New Delhi, India. Association for Computational Linguistics.