Marathi text summarization through NLP and deep learning mechanism

Abstract

<p>Every day, an ever-increasing amount of people gain access to the internet platform. This has proven to be efficient in creating cost-effective internet platform deployments and applications. The growth in the amount of people using the platform has resulted in a rise in the quantity of information accessible on the internet in the form of news, media, and other forms of communication. This causes evaluating and comprehending a significant amount of textual information a very challenging task. For the objective of generating textual summaries for Marathi texts, an effective and trustworthy approach is required. Through the use of machine learning methods, a successful strategy for extracting summary for the Marathi text has been generated for this objective. To obtain the Marathi text summary, the proposed method uses feature extraction as well as deep belief networks and decision tree methodologies. The experimentation was carried out on the performance of the Term Frequency-Inverse Document Frequency (TF-IDF) in the stopword elimination procedure, along with the evaluation of the summarization outcome which achieves a Mean Absolute Error (MAE) of 2.8 for the stopword removal approach through TF-IDF technique and a precision of 95.49% with an accuracy of 92.76%.</p>