This paper presents an application of Recurrent Neural Network for retrieving text from a given sequence of words of Gitanjali dataset. A Recurrent Neural Network (RNN) is trained to predict the poem corresponding to which the sequence of words are given. We demonstrate the experiment with two major RNN architectures and state the results to show which hyper-parameters like RNN size, sequence length, number of stacked layers affect the RNN most while completely memorizing the content of the poem. We also state the challenges to train the model in both forward and backward ways. We largely emphasis on the memorizing capability of RNN and put forward an application which depends on it.
CITATION STYLE
Bhowmick, R. S., & Sil, J. (2020). Memorizing and Retrieving of Text Using Recurrent Neural Network—A Case Study on Gitanjali Dataset. In Advances in Intelligent Systems and Computing (Vol. 999, pp. 413–422). Springer. https://doi.org/10.1007/978-981-13-9042-5_35
Mendeley helps you to discover research relevant for your work.