Word Level LSTM and Recurrent Neural Network for Automatic Text Generation
Harsha Vardhana Krishna Sai Buddana, Surampudi Sai Kaushik, PVS. Manogna, Shijin Kumar P.S.
Abstract
Sequence prediction problems have been a major problem for a long time. Recurrent Neural Network (RNN) has been a good solution for sequential prediction problems. This work aims to create a generative model for text. Even though, RNN has its own limitations such as vanishing and exploding gradient descent problems, and inefficiency to keep track of long-term dependencies. To overcome these drawbacks, Long Short Term Memory (LSTM) has been a path-breaking solution to deal with sequential data and text data in particular. This paper delineates the design and working of text generation using word-level LSTM-RNN.
Topics & Concepts
Recurrent neural networkComputer scienceWord (group theory)Artificial intelligenceText generationInefficiencySequence (biology)Long short term memoryGenerative grammarPath (computing)Gradient descentTerm (time)Stochastic gradient descentArtificial neural networkNatural language processingMachine learningQuantum mechanicsBiologyLinguisticsPhilosophyProgramming languageEconomicsGeneticsPhysicsMicroeconomicsTopic ModelingNatural Language Processing TechniquesAdvanced Text Analysis Techniques