Marathi Text Summarization using Extractive Technique

Abstract: Multilingualism has played a key role in India, where people speak and understand more than one language. Marathi, as one of the official languages in Maharashtra state, is often used in sources such as newspapers or blogs. However, manually summarizing bulky Marathi paragraphs or texts for easy comprehension can be challenging. To address this, text summarization becomes essential to make large documents easily readable and understandable. This research article focuses on single document text summarization using the Natural Language Processing (NLP) approach, a subfield of Artificial Intelligence. Automatic text summarization is employed to extract relevant information in a concise manner. Information Extraction is particularly useful when summarizing documents consisting of multiple sentences into three or four sentences. While extensive research has been conducted on English Text Summarization, the field of Marathi document summarization remains largely unexplored. This research paper explores extractive text summarization techniques specifically for Marathi documents, utilizing the LexRank algorithm along with Genism, a graph-based technique, to generate informative summaries within word limit constraints. The experiment was conducted on the IndicNLP Marathi news article dataset, resulting in 78% precision, 72% recall, and 75% F-measure using the frequency-based method, and 78% precision, 78% recall, and 78% F-measure using the Lex Rank algorithm.