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

Generating data for LSTMs


Here we will define how to extract a batch of data to train the LSTM. Whenever we process a fresh batch of data, the first input should be the image feature vector and the label should be SOS. We will define a batch of data, where, if the first_sample Boolean is True, then the input is extracted from the image feature vectors, and if first_sample is False, the input is extracted from the word embeddings. Also, after generating a batch of data, we will move the cursor by one, so we get the next item in the sequence next time we generate a batch of data. This way we can unroll a sequence of batches of data for the LSTM where the first batch of the sequence is the image feature vectors, followed by the word embeddings of the captions corresponding to that batch of images.

# Fill each of the batch indices
for b in range(self._batch_size):

    cap_id = cap_ids[b] # Current caption id
    # Current image feature vector
    cap_image_vec = self._image_data[self._fname_caption_tuples...