Hashing generation using recurrent neural networks for text documents

In this paper a novel technique is proposed to generate hashing values for text documents. The approach uses Recurrent Neural Networks (RNNs) for this purpose. RNNs are dynamic and temporal type of Neural Networks (NNs) that evolve continuously based on subsequent vectors of inputs. The capabilities of RNNs to incorporate present values of inputs with previous values exploiting relations and semantics of the text make it a competitive paradigm to discover the internal representations within text data in a unique way. Two types of RNNs are tested and compared to traditional methods. Ade-quate review has been done to existing techniques and the results obtained in this work demonstrate the applicability of this artificial intelligence paradigm in generating hashing values for plain text. RNNs are highly flexible, compact, and parallel in nature. Their capabilities are exploited in this paper as future competent technique in text hashing.