@inproceedings{bhowmick-jana-2021-sentiment,
title = "Sentiment Analysis For {B}engali Using Transformer Based Models",
author = "Bhowmick, Anirban and
Jana, Abhik",
editor = "Bandyopadhyay, Sivaji and
Devi, Sobha Lalitha and
Bhattacharyya, Pushpak",
booktitle = "Proceedings of the 18th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2021",
address = "National Institute of Technology Silchar, Silchar, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2021.icon-main.58",
pages = "481--486",
abstract = "Sentiment analysis is one of the key Natural Language Processing (NLP) tasks that has been attempted by researchers extensively for resource-rich languages like English. But for low resource languages like Bengali very few attempts have been made due to various reasons including lack of corpora to train machine learning models or lack of gold standard datasets for evaluation. However, with the emergence of transformer models pre-trained in several languages, researchers are showing interest to investigate the applicability of these models in several NLP tasks, especially for low resource languages. In this paper, we investigate the usefulness of two pre-trained transformers models namely multilingual BERT and XLM-RoBERTa (with fine-tuning) for sentiment analysis for the Bengali Language. We use three datasets for the Bengali language for evaluation and produce state-of-the-art performance, even reaching a maximum of 95{\%} accuracy for a two-class sentiment classification task. We believe, this work can serve as a good benchmark as far as sentiment analysis for the Bengali language is concerned.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhowmick-jana-2021-sentiment">
<titleInfo>
<title>Sentiment Analysis For Bengali Using Transformer Based Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anirban</namePart>
<namePart type="family">Bhowmick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhik</namePart>
<namePart type="family">Jana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sivaji</namePart>
<namePart type="family">Bandyopadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sobha</namePart>
<namePart type="given">Lalitha</namePart>
<namePart type="family">Devi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">National Institute of Technology Silchar, Silchar, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Sentiment analysis is one of the key Natural Language Processing (NLP) tasks that has been attempted by researchers extensively for resource-rich languages like English. But for low resource languages like Bengali very few attempts have been made due to various reasons including lack of corpora to train machine learning models or lack of gold standard datasets for evaluation. However, with the emergence of transformer models pre-trained in several languages, researchers are showing interest to investigate the applicability of these models in several NLP tasks, especially for low resource languages. In this paper, we investigate the usefulness of two pre-trained transformers models namely multilingual BERT and XLM-RoBERTa (with fine-tuning) for sentiment analysis for the Bengali Language. We use three datasets for the Bengali language for evaluation and produce state-of-the-art performance, even reaching a maximum of 95% accuracy for a two-class sentiment classification task. We believe, this work can serve as a good benchmark as far as sentiment analysis for the Bengali language is concerned.</abstract>
<identifier type="citekey">bhowmick-jana-2021-sentiment</identifier>
<location>
<url>https://aclanthology.org/2021.icon-main.58</url>
</location>
<part>
<date>2021-12</date>
<extent unit="page">
<start>481</start>
<end>486</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sentiment Analysis For Bengali Using Transformer Based Models
%A Bhowmick, Anirban
%A Jana, Abhik
%Y Bandyopadhyay, Sivaji
%Y Devi, Sobha Lalitha
%Y Bhattacharyya, Pushpak
%S Proceedings of the 18th International Conference on Natural Language Processing (ICON)
%D 2021
%8 December
%I NLP Association of India (NLPAI)
%C National Institute of Technology Silchar, Silchar, India
%F bhowmick-jana-2021-sentiment
%X Sentiment analysis is one of the key Natural Language Processing (NLP) tasks that has been attempted by researchers extensively for resource-rich languages like English. But for low resource languages like Bengali very few attempts have been made due to various reasons including lack of corpora to train machine learning models or lack of gold standard datasets for evaluation. However, with the emergence of transformer models pre-trained in several languages, researchers are showing interest to investigate the applicability of these models in several NLP tasks, especially for low resource languages. In this paper, we investigate the usefulness of two pre-trained transformers models namely multilingual BERT and XLM-RoBERTa (with fine-tuning) for sentiment analysis for the Bengali Language. We use three datasets for the Bengali language for evaluation and produce state-of-the-art performance, even reaching a maximum of 95% accuracy for a two-class sentiment classification task. We believe, this work can serve as a good benchmark as far as sentiment analysis for the Bengali language is concerned.
%U https://aclanthology.org/2021.icon-main.58
%P 481-486
Markdown (Informal)
[Sentiment Analysis For Bengali Using Transformer Based Models](https://aclanthology.org/2021.icon-main.58) (Bhowmick & Jana, ICON 2021)
ACL