Book Image

Natural Language Processing with TensorFlow - Second Edition

By : Thushan Ganegedara
2 (1)
Book Image

Natural Language Processing with TensorFlow - Second Edition

2 (1)
By: Thushan Ganegedara

Overview of this book

Learning how to solve natural language processing (NLP) problems is an important skill to master due to the explosive growth of data combined with the demand for machine learning solutions in production. Natural Language Processing with TensorFlow, Second Edition, will teach you how to solve common real-world NLP problems with a variety of deep learning model architectures. The book starts by getting readers familiar with NLP and the basics of TensorFlow. Then, it gradually teaches you different facets of TensorFlow 2.x. In the following chapters, you then learn how to generate powerful word vectors, classify text, generate new text, and generate image captions, among other exciting use-cases of real-world NLP. TensorFlow has evolved to be an ecosystem that supports a machine learning workflow through ingesting and transforming data, building models, monitoring, and productionization. We will then read text directly from files and perform the required transformations through a TensorFlow data pipeline. We will also see how to use a versatile visualization tool known as TensorBoard to visualize our models. By the end of this NLP book, you will be comfortable with using TensorFlow to build deep learning models with many different architectures, and efficiently ingest data using TensorFlow Additionally, you’ll be able to confidently use TensorFlow throughout your machine learning workflow.

Related Content you might be interested in

Current Title:

Small book image
Natural Language Processing with TensorFlow - Second Edition
Thushan Ganegedara
Jul, 2022 | 514 pages
Small book image
Advanced Natural Language Processing with TensorFlow 2
Ashish Bansal
Feb, 2021 | 380 pages
Small book image
Deep Learning Essentials
Wei Di | Anurag Bhardwaj | Jianing Wei
Jan, 2018 | 284 pages
Small book image
Hands-On Natural Language Processing with PyTorch 1.x
Thomas Dop
Jul, 2020 | 276 pages
Table of Contents (15 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Get in touch
Free Chapter
1
Introduction to Natural Language Processing
Introduction to Natural Language Processing
What is Natural Language Processing?
Tasks of Natural Language Processing
The traditional approach to Natural Language Processing
The deep learning approach to Natural Language Processing
Introduction to the technical tools
Summary
2
Understanding TensorFlow 2
Understanding TensorFlow 2
What is TensorFlow?
Inputs, variables, outputs, and operations
Keras: The model building API of TensorFlow
Implementing our first neural network
Summary
3
Word2vec – Learning Word Embeddings
Word2vec – Learning Word Embeddings
What is a word representation or meaning?
Classical approaches to learning word representation
An intuitive understanding of Word2vec – an approach to learning word representation
The skip-gram algorithm
The Continuous Bag-of-Words algorithm
Summary
4
Advanced Word Vector Algorithms
Advanced Word Vector Algorithms
GloVe – Global Vectors representation
ELMo – Taking ambiguities out of word vectors
Document classification with ELMo
Summary
5
Sentence Classification with Convolutional Neural Networks
Sentence Classification with Convolutional Neural Networks
Introducing CNNs
Understanding CNNs
Exercise – image classification on Fashion-MNIST with CNN
Using CNNs for sentence classification
Summary
6
Recurrent Neural Networks
Recurrent Neural Networks
Understanding RNNs
Backpropagation Through Time
Applications of RNNs
Named Entity Recognition with RNNs
NER with character and token embeddings
Summary
7
Understanding Long Short-Term Memory Networks
Understanding Long Short-Term Memory Networks
Understanding Long Short-Term Memory Networks
How LSTMs solve the vanishing gradient problem
Improving LSTMs
Other variants of LSTMs
Summary
8
Applications of LSTM – Generating Text
Applications of LSTM – Generating Text
Our data
Implementing the language model
Comparing LSTMs to LSTMs with peephole connections and GRUs
Improving sequential models – beam search
Improving LSTMs – generating text with words instead of n-grams
Summary
9
Sequence-to-Sequence Learning – Neural Machine Translation
Sequence-to-Sequence Learning – Neural Machine Translation
Machine translation
A brief historical tour of machine translation
Understanding neural machine translation
Preparing data for the NMT system
Defining the model
Training the NMT
The BLEU score – evaluating the machine translation systems
Visualizing Attention patterns
Inference with NMT
Other applications of Seq2Seq models – chatbots
Summary
10
Transformers
Transformers
Transformer architecture
Understanding BERT
Use case: Using BERT to answer questions
Summary
11
Image Captioning with Transformers
Image Captioning with Transformers
Getting to know the data
Downloading the data
Processing and tokenizing data
Defining a tf.data.Dataset
The machine learning pipeline for image caption generation
Implementing the model with TensorFlow
Training the model
Evaluating the results quantitatively
Evaluating the model
Captions generated for test images
Summary
12
Other Books You May Enjoy
Other Books You May Enjoy
13
Index
Index
Appendix A: Mathematical Foundations and Advanced TensorFlow
Appendix A: Mathematical Foundations and Advanced TensorFlow
Basic data structures
Special types of matrices
Tensor/matrix operations
Probability
Visualizing word embeddings with TensorBoard
Summary

Understanding BERT

BERT (Bidirectional Encoder Representation from Transformers) is a Transformer model among a plethora of Transformer models that have come to light over the past few years.

BERT was introduced in the paper BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding by Delvin et al. (https://arxiv.org/pdf/1810.04805.pdf). The Transformer models are divided into two main factions:

  • Encoder-based models
  • Decoder-based (autoregressive) models

In other words, either the encoder or the decoder part of the Transformer provides the foundation for these models, compared to using both the encoder and the decoder. The main difference between the two is how attention is used. Encoder-based models use bidirectional attention, whereas decoder-based models use autoregressive (that is, left to right) attention.

BERT is an encoder-based Transformer model. It takes an input sequence (a collection of tokens) and produces an encoded...

Previous Section
End of Section 3
Next Section