Book Image

Natural Language Processing with TensorFlow

By : Motaz Saad, Thushan Ganegedara
Book Image

Natural Language Processing with TensorFlow

By: Motaz Saad, Thushan Ganegedara

Overview of this book

Natural language processing (NLP) supplies the majority of data available to deep learning applications, while TensorFlow is the most important deep learning framework currently available. Natural Language Processing with TensorFlow brings TensorFlow and NLP together to give you invaluable tools to work with the immense volume of unstructured data in today’s data streams, and apply these tools to specific NLP tasks. Thushan Ganegedara starts by giving you a grounding in NLP and TensorFlow basics. You'll then learn how to use Word2vec, including advanced extensions, to create word embeddings that turn sequences of words into vectors accessible to deep learning algorithms. Chapters on classical deep learning algorithms, like convolutional neural networks (CNN) and recurrent neural networks (RNN), demonstrate important NLP tasks as sentence classification and language generation. You will learn how to apply high-performance RNN models, like long short-term memory (LSTM) cells, to NLP tasks. You will also explore neural machine translation and implement a neural machine translator. After reading this book, you will gain an understanding of NLP and you'll have the skills to apply TensorFlow in deep learning NLP applications, and how to perform specific NLP tasks.
Table of Contents (16 chapters)
Natural Language Processing with TensorFlow
Contributors
Preface
Index

Recurrent Neural Networks with Context Features – RNNs with longer memory


Earlier, we discussed two important challenges in training a simple RNN: the exploding gradient and the vanishing gradient. We also know that we can prevent gradient explosion with a simple trick such as gradient clipping, leading to more stable training. However, solving the vanishing gradient takes much more effort, because there is no simple scaling/clipping mechanism to solve the gradient vanishing, as we did for gradient explosion. Therefore, we need to modify the structure of the RNN itself, giving explicitly the ability for it to remember longer patterns in sequences of data .The RNN-CF proposed in the paper, Learning Longer Memory in Recurrent Neural Networks, Tomas Mikolov and others, International Conference on Learning Representations (2015), is one such modification to the standard RNN, helping RNNs to memorize patterns in sequences of data for longer.

An RNN-CF provides an improvement to reduce the vanishing...