Marathi Text Summarization Using Machine Learning

Computer Engineering

Manual summarization of large documents of texts is tedious and error prone. Also, the results in such kind of summarization may lead to different results for a particular document. Thus, Automatic text summarization has become important due to the tremendous growth of information and data. It chooses the most informative part of text and forms summaries that reveal the main purpose of the given document. It yields summary produced by summarization system which allows readers to comprehend the content of document instead for reading each and every individual document. So, the overall intention of Text Summarizer is to provide the meaning of text in less words and sentences. Summarization can be categorized as: Abstractive summarization and Extractive summarization. This case study is based on an extractive concept implemented on the studied models. Numerous automatic text summarization systems are handy today for English and other foreign languages. But when it comes to Indian languages, we observe inadequate number of automatic summarizers. Our efforts in this direction are mainly for developing automatic text summarizer for marathi Language. We look forward to evaluate the obtained summaries using ROUGE metric. This paper describes a multi document marathi extractive summarizer. Keywords-Marathi Text Summarizer, Extractive Summarization, Graph based model, Feature Extraction, TextRank

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.