Topic Modeling in Marathi

TL;DR

This paper explores and compares different topic modeling approaches for Marathi, an Indic language, highlighting that BERT-based models, especially BERTopic with Indic-trained BERT, outperform traditional LDA methods.

Contribution

It provides a comparative analysis of BERT and non-BERT topic modeling approaches specifically tailored for Marathi, addressing a gap in Indic language NLP research.

Findings

BERTopic with Indic BERT outperforms LDA in topic coherence and diversity

Multilingual BERT models show competitive performance for Marathi

The study offers insights into effective NLP techniques for low-resource Indic languages

Abstract

While topic modeling in English has become a prevalent and well-explored area, venturing into topic modeling for Indic languages remains relatively rare. The limited availability of resources, diverse linguistic structures, and unique challenges posed by Indic languages contribute to the scarcity of research and applications in this domain. Despite the growing interest in natural language processing and machine learning, there exists a noticeable gap in the comprehensive exploration of topic modeling methodologies tailored specifically for languages such as Hindi, Marathi, Tamil, and others. In this paper, we examine several topic modeling approaches applied to the Marathi language. Specifically, we compare various BERT and non-BERT approaches, including multilingual and monolingual BERT models, using topic coherence and topic diversity as evaluation metrics. Our analysis provides insights into the performance of these approaches for Marathi language topic modeling. The key finding of the paper is that BERTopic, when combined with BERT models trained on Indic languages, outperforms LDA in terms of topic modeling performance.