• Siddhesh Kasar
• Shubham Bobade
• Nitesh Gaikwad
• Sonali Bhoite

: In this research, we present the development of an automated text summarization system tailored specifically for the Marathi language. By analyzing previous work from various research papers, we implement the TextRank algorithm, leveraging a statistical approach to enhance the accuracy of the summaries. Our system is developed using Python and the NLTK library, and undergoes an extensive pre-processing phase that involves tasks such as punctuation removal, stop word elimination, tokenization, stemming, and normalization of the text. By applying advanced machine learning techniques and linguistic analysis, the system efficiently identifies and extracts key features from the text, producing extractive summaries that retain the essential information. The effectiveness of the system will be validated through a comparative analysis with human-generated summaries. This research contributes to the growing field of natural language processing tools for the Marathi language, with future plans to incorporate additional machine learning techniques to further refine and improve the system's performance.

Automated text summarization, TextRank algorithm, Machine learning, Extractive summaries, Pre-processing, Linguistic analysis, NLP tools.

"Marathi Text Summarization Using NLP & ML", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 11, page no.d854-d864, November-2024, Available :http://www.jetir.org/papers/JETIR2411399.pdf

"Marathi Text Summarization Using NLP & ML", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 11, page no. ppd854-d864, November-2024, Available at : http://www.jetir.org/papers/JETIR2411399.pdf