• Karan Mehta
• Sahaja Mahaty

One of the most important issue in assisting computers to learn languages is correction of sentences. Some errors in sentences that occurs frequently can not be tackled by machine translation based on stastics or dening grammar rules . So, need of hour is to correct the sentences using RNNs and NLP while preserving sentiments, named entities etc. We will be using Recurrent Neural Networks (RNNs), because they have the capability of dealing with capable of dealing with sequential data. Till now there are some systems available for sentence correction but the problem is that they dont have long range dependencies .i.e. they just see the previous word and correct the next word like the most common word similar to previous word but with RNN we can have long range dependencies i.e. we can check what word will come next given a set of words.

NLP - Natural Language Programming, RNN - Recurrent Neural Network

"Deep Learning for Sentence Correction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.407-412, June 2019, Available :http://www.jetir.org/papers/JETIR1906U90.pdf

"Deep Learning for Sentence Correction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp407-412, June 2019, Available at : http://www.jetir.org/papers/JETIR1906U90.pdf