Work with natural language tools and techniques to solve real-world problems. This book focuses on how natural language processing (NLP) is used in various industries. Each chapter describes the problem and solution strategy, then provides an intuitive explanation of how different algorithms work and a deeper dive on code and output in Python. __Practical Natural Language Processing with Python__ follows a case study-based approach. Each chapter is devoted to an industry or a use case, where you address the real business problems in that industry and the various ways to solve them. You start with various types of text data before focusing on the customer service industry, the type of data available in that domain, and the common NLP problems encountered. Here you cover the bag-of-words model supervised learning technique as you try to solve the case studies. Similar depth is given to other use cases such as online reviews, bots, finance, and so on. As you cover the problems in these industries you’ll also cover sentiment analysis, named entity recognition, word2vec, word similarities, topic modeling, deep learning, and sequence to sequence modelling. By the end of the book, you will be able to handle all types of NLP problems independently. You will also be able to think in different ways to solve language problems. Code and techniques for all the problems are provided in the book. **What You Will Learn** * Build an understanding of NLP problems in industry * Gain the know-how to solve a typical NLP problem using language-based models and machine learning * Discover the best methods to solve a business problem using NLP - the tried and tested ones * Understand the business problems that are tough to solve Who This Book Is For Analytics and data science professionals who want to kick start NLP, and NLP professionals who want to get new ideas to solve the problems at hand. Table of Contents 5 About the Author 9 About the Technical Reviewer 10 Acknowledgments 11 Introduction 12 Chapter 1: Types of Data 13 Search 14 Reviews 14 Social Media Posts/Blogs 16 Chat Data 18 Personal Chats 18 Business Chats and Voice Call Data 19 SMS Data 20 Content Data 22 IVR Utterance Data 22 Useful Information from Data 24 Chapter 2: NLP in Customer Service 25 Voice Calls 25 Chats 26 Tickets Data 28 Email data 28 Voice of Customer 31 Intent Mining 31 Top Words to Understand Intents 32 Word Cloud 34 Rules to Classify Topics 37 Supervised Learning Using Machine Learning 41 Getting Manually Labelled Data 41 Word Tokenization 43 Term-Document Matrix 44 Data Normalization 50 Replacing Certain Patterns 50 Identifying Issue Lines 55 Top Customer Queries 56 Top CSAT Drivers 59 Top NPS Drivers 61 Insights into Sales Chats 68 Top Products for Sales Chats 68 Reasons for Non-Purchase 69 Survey Comments Analysis 70 Mining Voice Transcripts 70 Acoustic Model 72 Language Model 72 Chapter 3: NLP in Online Reviews 76 Sentiment Analysis 76 Emotion Mining 77 Approach 1: Lexicon-Based Approach 78 Approach 2: Rules-Based Approach 83 Observation 1 84 Observation 2 84 Observation 3 85 Observation 4 85 Overall Score 86 Implementing the Observations 88 Preprocessing 88 Booster and Negation Words (Observation 2 and Observation 3) 88 Exclamation Marks (Observation 4) 90 Evaluation of full_txt and Summary (Observation 1) 91 Optimizing the Code 97 Sentiment Analysis Libraries 105 Approach 3: Machine-Learning Based Approach (Neural Network) 106 Corpus Features 107 Building the Neural Network 112 Things to Improve 114 Attribute Extraction 114 Step 1: Using Regex to Normalize 117 Step 2: Extracting Noun Forms 118 Step 3: Creating a Mapping File 119 Step 4: Mapping Each Review to an Attribute 122 Step 5: Analyzing Brands 123 Chapter 4: NLP in Banking, Financial Services, and Insurance (BFSI) 131 NLP in Fraud 131 Method 1: Using Existing Libraries 132 Method 2: Extracting Noun Phrases 135 Method 3: Training Your Own Model 138 Word Embeddings 140 Word2Vec 143 CBOW 144 Other word2vec Libraries 150 Applying Word Embeddings to Supervised Learning 153 Method 3 – Approach 1 153 Method 3 – Approach 2 153 Applying the Model 169 Other Use Cases of NLP in Banking, Financial Services, and Insurance 187 SMS Data 187 Natural Language Generation in Banks 187 Chapter 5: NLP in Virtual Assistants 194 Types of Bots 194 The Classic Approach 196 Quick Overview of LSTM 201 Forget Gate 203 Input Gate 204 Output Gate 205 Applying LSTM 205 Time-Distributed Layer 208 Approach 2 - The Generating Responses Approach 212 Encoder-Decoder Architecture 212 Dataset 214 Implementing the Architecture 215 Encoder-Decoder Training 224 Encoder Output 228 Decoder Input 228 Preprocessing 231 Bidirectional LSTM 236 Encoder 237 Decoder 237 BERT 239 Language Models and Fine-Tuning 239 Overview of BERT 240 Fine-Tuning BERT for a Classifier 245 Further Nuances in Building Conversational Bots 249 Single-Turn vs. Multi-Turn Conversations 249 Multi-Lingual Bots 251 Index 257
