@inproceedings{ehsan-etal-2023-alphabrains,
title = "{A}lpha{B}rains@{D}ravidian{L}ang{T}ech: Sentiment Analysis of Code-Mixed {T}amil and {T}ulu by Training Contextualized {ELM}o Word Representations",
author = "Ehsan, Toqeer and
Tehseen, Amina and
Sarveswaran, Kengatharaiyer and
Ali, Amjad",
editor = "Chakravarthi, Bharathi R. and
Priyadharshini, Ruba and
M, Anand Kumar and
Thavareesan, Sajeetha and
Sherly, Elizabeth",
booktitle = "Proceedings of the Third Workshop on Speech and Language Technologies for Dravidian Languages",
month = sep,
year = "2023",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2023.dravidianlangtech-1.20",
pages = "152--159",
abstract = "Sentiment analysis in natural language processing (NLP), endeavors to computationally identify and extract subjective information from textual data. In code-mixed text, sentiment analysis presents a unique challenge due to the mixing of languages within a single textual context. For low-resourced languages such as Tamil and Tulu, predicting sentiment becomes a challenging task due to the presence of text comprising various scripts. In this research, we present the sentiment analysis of code-mixed Tamil and Tulu Youtube comments. We have developed a Bidirectional Long-Short Term Memory (BiLSTM) networks based models for both languages which further uses contextualized word embeddings at input layers of the models. For that purpose, ELMo embeddings have been trained on larger unannotated code-mixed text like corpora. Our models performed with macro average F1-scores of 0.2877 and 0.5133 on Tamil and Tulu code-mixed datasets respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ehsan-etal-2023-alphabrains">
<titleInfo>
<title>AlphaBrains@DravidianLangTech: Sentiment Analysis of Code-Mixed Tamil and Tulu by Training Contextualized ELMo Word Representations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Toqeer</namePart>
<namePart type="family">Ehsan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amina</namePart>
<namePart type="family">Tehseen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kengatharaiyer</namePart>
<namePart type="family">Sarveswaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amjad</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Speech and Language Technologies for Dravidian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruba</namePart>
<namePart type="family">Priyadharshini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anand</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">M</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sajeetha</namePart>
<namePart type="family">Thavareesan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Sherly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Sentiment analysis in natural language processing (NLP), endeavors to computationally identify and extract subjective information from textual data. In code-mixed text, sentiment analysis presents a unique challenge due to the mixing of languages within a single textual context. For low-resourced languages such as Tamil and Tulu, predicting sentiment becomes a challenging task due to the presence of text comprising various scripts. In this research, we present the sentiment analysis of code-mixed Tamil and Tulu Youtube comments. We have developed a Bidirectional Long-Short Term Memory (BiLSTM) networks based models for both languages which further uses contextualized word embeddings at input layers of the models. For that purpose, ELMo embeddings have been trained on larger unannotated code-mixed text like corpora. Our models performed with macro average F1-scores of 0.2877 and 0.5133 on Tamil and Tulu code-mixed datasets respectively.</abstract>
<identifier type="citekey">ehsan-etal-2023-alphabrains</identifier>
<location>
<url>https://aclanthology.org/2023.dravidianlangtech-1.20</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>152</start>
<end>159</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AlphaBrains@DravidianLangTech: Sentiment Analysis of Code-Mixed Tamil and Tulu by Training Contextualized ELMo Word Representations
%A Ehsan, Toqeer
%A Tehseen, Amina
%A Sarveswaran, Kengatharaiyer
%A Ali, Amjad
%Y Chakravarthi, Bharathi R.
%Y Priyadharshini, Ruba
%Y M, Anand Kumar
%Y Thavareesan, Sajeetha
%Y Sherly, Elizabeth
%S Proceedings of the Third Workshop on Speech and Language Technologies for Dravidian Languages
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F ehsan-etal-2023-alphabrains
%X Sentiment analysis in natural language processing (NLP), endeavors to computationally identify and extract subjective information from textual data. In code-mixed text, sentiment analysis presents a unique challenge due to the mixing of languages within a single textual context. For low-resourced languages such as Tamil and Tulu, predicting sentiment becomes a challenging task due to the presence of text comprising various scripts. In this research, we present the sentiment analysis of code-mixed Tamil and Tulu Youtube comments. We have developed a Bidirectional Long-Short Term Memory (BiLSTM) networks based models for both languages which further uses contextualized word embeddings at input layers of the models. For that purpose, ELMo embeddings have been trained on larger unannotated code-mixed text like corpora. Our models performed with macro average F1-scores of 0.2877 and 0.5133 on Tamil and Tulu code-mixed datasets respectively.
%U https://aclanthology.org/2023.dravidianlangtech-1.20
%P 152-159
Markdown (Informal)
[AlphaBrains@DravidianLangTech: Sentiment Analysis of Code-Mixed Tamil and Tulu by Training Contextualized ELMo Word Representations](https://aclanthology.org/2023.dravidianlangtech-1.20) (Ehsan et al., DravidianLangTech-WS 2023)
ACL