Volume 4, Issue 11

Volume 4, Issue 11

November, 2019

Research Paper

1. Marathi text summarization using Neural Networks

The internet is comprised of web pages, news articles, status updates, blogs and much more. It is difficult to navigate through this data as it is unstructured and usually discursive. Condensed versions of this data are generated so we can navigate it more effectively as well as check whether the larger documents contain the information that we are looking for. We propose a system for extractive text summarization method using neural networks for Marathi text. Extractive summaries or extracts are produced by identifying important sentences or words which are directly selected from the document. To perform extractive text summarization we propose to use a Recurrent Neural Network (RNN) – a type of neural network that can perform calculations on sequential data (e.g. sequences of words) – as it has become the standard approach for many Natural Language Processing tasks. The translation of the Marathi text to English will be done using the Google translate API for this proposed system.

Published by: Anishka Chaudhari, Akash Dole, Deepali KadamResearch Area: Neural Networks

Organisation: Datta Meghe College of Engineering, Navi Mumbai, MaharashtraKeywords: Text summarizer, Google translate, Neural machine translation, NLP, Neural Networks, Encoder-Decoder, Bahdanau Attention model, Extractive summarization