Applied Natural Language Processing with Python: Implementing Machine Learning and Deep Learning Algorithms for Natural Language

✍ Scribed by IT Pro - York University.; Skillsoft Books - York University.; Ii, Taweh Beysolow

• Publisher: Apress
• Year: 2018
• Tongue: English
• Leaves: 158
• Category: Library

✦ Synopsis

Learn to harness the power of AI for natural language processing, performing tasks such as spell check, text summarization, document classification, and natural language generation. Along the way, you will learn the skills to implement these methods in larger infrastructures to replace existing code or create new algorithms.
Applied Natural Language Processing with Pythonstarts with reviewing the necessary machine learning concepts before moving onto discussing various NLP problems. After reading this book, you will have the skills to apply these concepts in your own professional environment.

What You Will Learn
Utilize various machine learning and natural language processing libraries such as TensorFlow, Keras, NLTK, and Gensim


Manipulate and preprocess raw text data in formats such as .txt and .pdf


Strengthen your skills in data science by learning both the theory and the application of various algorithms

Who This Book Is For
You should be at least a beginner in ML to get the most out of this text, but you needn't feel that you need be an expert to understand the content.

✦ Table of Contents

Table of Contents......Page 5
About the Author......Page 8
About the Technical Reviewer......Page 9
Acknowledgments......Page 10
Introduction......Page 11
Chapter 1: What Is Natural Language Processing?......Page 12
The History of Natural Language Processing......Page 13
TensorFlow......Page 15
Keras......Page 18
Theano......Page 19
Word Embeddings......Page 21
Language Modeling Tasks Involving RNNs......Page 22
Summary......Page 23
Multilayer Perceptrons and Recurrent Neural Networks......Page 24
Toy Example 1: Modeling Stock Returns with the MLP Model......Page 26
Learning Rate......Page 31
Vanishing Gradients and Why ReLU Helps to Prevent Them......Page 38
Loss Functions and Backpropagation......Page 40
Recurrent Neural Networks and Long Short-Term Memory......Page 41
Toy Example 2: Modeling Stock Returns with the RNN Model......Page 43
Toy Example 3: Modeling Stock Returns with the LSTM Model......Page 51
Summary......Page 52
Chapter 3: Working with  Raw Text......Page 54
Tokenization and Stop Words......Page 55
The Bag-of-Words Model (BoW)......Page 61
CountVectorizer......Page 62
Example Problem 1: Spam Detection......Page 64
Term Frequency Inverse Document Frequency......Page 68
Example Problem 2: Classifying Movie Reviews......Page 73
Summary......Page 85
Topic Model and Latent Dirichlet Allocation (LDA)......Page 87
Topic Modeling with LDA on Movie Review Data......Page 91
Non-Negative Matrix Factorization (NMF)......Page 96
Word2Vec......Page 100
Example Problem 4.2: Training a Word Embedding (Skip-Gram)......Page 104
Continuous Bag-of-Words (CBoW)......Page 113
Example Problem 4.2: Training a Word Embedding (CBoW)......Page 115
Global Vectors for Word Representation (GloVe)......Page 116
Example Problem 4.4: Using Trained Word Embeddings with LSTMs......Page 121
Paragraph2Vec: Distributed Memory of Paragraph Vectors (PV-DM)......Page 125
Example Problem 4.5: Paragraph2Vec Example with Movie Review Data......Page 126
Summary......Page 128
Chapter 5: Text Generation, Machine Translation, and Other Recurrent Language Modeling Tasks......Page 130
Text Generation with LSTMs......Page 131
Bidirectional RNNs (BRNN)......Page 135
Creating a Name Entity Recognition Tagger......Page 137
Sequence-to-Sequence Models (Seq2Seq)......Page 142
Question and Answer with Neural Network Models......Page 143
Summary......Page 150
Conclusion and Final Statements......Page 151
Index......Page 153