The Natural Language Processing Workshop

Cover
FM
Copyright
Table of Contents
Preface
Chapter 1: Introduction to Natural Language Processing
	Introduction
	History of NLP
	Text Analytics and NLP
		Exercise 1.01: Basic Text Analytics
	Various Steps in NLP
		Tokenization
		Exercise 1.02: Tokenization of a Simple Sentence
		PoS Tagging
		Exercise 1.03: PoS Tagging
		Stop Word Removal
		Exercise 1.04: Stop Word Removal
		Text Normalization
		Exercise 1.05: Text Normalization
		Spelling Correction
		Exercise 1.06: Spelling Correction of a Word and a Sentence
		Stemming
		Exercise 1.07: Using Stemming
		Lemmatization
		Exercise 1.08: Extracting the Base Word Using Lemmatization
		Named Entity Recognition (NER)
		Exercise 1.09: Treating Named Entities
	Word Sense Disambiguation
		Exercise 1.10: Word Sense Disambiguation
	Sentence Boundary Detection
		Exercise 1.11: Sentence Boundary Detection
		Activity 1.01: Preprocessing of Raw Text
	Kick Starting an NLP Project
		Data Collection
		Data Preprocessing
		Feature Extraction
		Model Development
		Model Assessment
		Model Deployment
	Summary
Chapter 2: Feature Extraction Methods
	Introduction
	Types of Data
		Categorizing Data Based on Structure
		Categorizing Data Based on Content
	Cleaning Text Data
		Tokenization
		Exercise 2.01: Text Cleaning and Tokenization
		Exercise 2.02: Extracting n-grams
		Exercise 2.03: Tokenizing Text with Keras and TextBlob
		Types of Tokenizers
		Exercise 2.04: Tokenizing Text Using Various Tokenizers
		Stemming
		RegexpStemmer
		Exercise 2.05: Converting Words in the Present Continuous Tense into Base Words with RegexpStemmer
		The Porter Stemmer
		Exercise 2.06: Using the Porter Stemmer
		Lemmatization
		Exercise 2.07: Performing Lemmatization
		Exercise 2.08: Singularizing and Pluralizing Words
		Language Translation
		Exercise 2.09: Language Translation
		Stop-Word Removal
		Exercise 2.10: Removing Stop Words from Text
		Activity 2.01: Extracting Top Keywords from the News Article
	Feature Extraction from Texts
		Extracting General Features from Raw Text
		Exercise 2.11: Extracting General Features from Raw Text
		Exercise 2.12: Extracting General Features from Text
		Bag of Words (BoW)
		Exercise 2.13: Creating a Bag of Words
		Zipf\'s Law
		Exercise 2.14: Zipf\'s Law
		Term Frequency–Inverse Document Frequency (TFIDF)
		Exercise 2.15: TFIDF Representation
	Finding Text Similarity – Application of Feature Extraction
		Exercise 2.16: Calculating Text Similarity Using Jaccard and Cosine Similarity
		Word Sense Disambiguation Using the Lesk Algorithm
		Exercise 2.17: Implementing the Lesk Algorithm Using String Similarity and Text Vectorization
		Word Clouds
		Exercise 2.18: Generating Word Clouds
		Other Visualizations
		Exercise 2.19: Other Visualizations Dependency Parse Trees and Named Entities
		Activity 2.02: Text Visualization
	Summary
Chapter 3: Developing a Text Classifier
	Introduction
	Machine Learning
		Unsupervised Learning
		Hierarchical Clustering
		Exercise 3.01: Performing Hierarchical Clustering
		k-means Clustering
		Exercise 3.02: Implementing k-means Clustering
	Supervised Learning
		Classification
		Logistic Regression
		Exercise 3.03: Text Classification – Logistic Regression
		Naive Bayes Classifiers
		Exercise 3.04: Text Classification – Naive Bayes
		k-nearest Neighbors
		Exercise 3.05: Text Classification Using the k-nearest Neighbors Method
		Regression
		Linear Regression
		Exercise 3.06: Regression Analysis Using Textual Data
		Tree Methods
		Exercise 3.07: Tree-Based Methods – Decision Tree
		Random Forest
		Gradient Boosting Machine and Extreme Gradient Boost
		Exercise 3.08: Tree-Based Methods – Random Forest
		Exercise 3.09: Tree-Based Methods – XGBoost
		Sampling
		Exercise 3.10: Sampling (Simple Random, Stratified, and Multi-Stage)
	Developing a Text Classifier
		Feature Extraction
		Feature Engineering
		Removing Correlated Features
		Exercise 3.11: Removing Highly Correlated Features (Tokens)
		Dimensionality Reduction
		Exercise 3.12: Performing Dimensionality Reduction Using Principal Component Analysis
		Deciding on a Model Type
		Evaluating the Performance of a Model
		Exercise 3.13: Calculating the RMSE and MAPE of a Dataset
		Activity 3.01: Developing End-to-End Text Classifiers
	Building Pipelines for NLP Projects
		Exercise 3.14: Building the Pipeline for an NLP Project
	Saving and Loading Models
		Exercise 3.15: Saving and Loading Models
	Summary
Chapter 4: Collecting Text Data with Web Scraping and APIs
	Introduction
	Collecting Data by Scraping Web Pages
		Exercise 4.01: Extraction of Tag-Based Information from HTML Files
		Requesting Content from Web Pages
		Exercise 4.02: Collecting Online Text Data
		Exercise 4.03: Analyzing the Content of Jupyter Notebooks (in HTML Format)
		Activity 4.01: Extracting Information from an Online HTML Page
		Activity 4.02: Extracting and Analyzing Data Using Regular Expressions
	Dealing with Semi-Structured Data
		JSON
		Exercise 4.04: Working with JSON Files
		XML
		Exercise 4.05: Working with an XML File
		Using APIs to Retrieve Real-Time Data
		Exercise 4.06: Collecting Data Using APIs
		Extracting data from Twitter Using the OAuth API
		Activity 4.03: Extracting Data from Twitter
	Summary
Chapter 5: Topic Modeling
	Introduction
	Topic Discovery
		Exploratory Data Analysis
		Transforming Unstructured Data to Structured Data
		Bag of Words
	Topic-Modeling Algorithms
		Latent Semantic Analysis (LSA)
		LSA – How It Works
	Key Input Parameters for LSA Topic Modeling
		Exercise 5.01: Analyzing Wikipedia World Cup Articles with Latent Semantic Analysis
		Dirichlet Process and Dirichlet Distribution
		Latent Dirichlet Allocation (LDA)
		LDA – How It Works
		Measuring the Predictive Power of a Generative Topic Model
		Exercise 5.02: Finding Topics in Canadian Open Data Inventory Using the LDA Model
		Activity 5.01: Topic-Modeling Jeopardy Questions
	Hierarchical Dirichlet Process (HDP)
		Exercise 5.03: Topics in Around the World in Eighty Days
		Exercise 5.04: Topics in The Life and Adventures of Robinson Crusoe by Daniel Defoe
		Practical Challenges
		State-of-the-Art Topic Modeling
		Activity 5.02: Comparing Different Topic Models
	Summary
Chapter 6: Vector Representation
	Introduction
	What Is a Vector?
		Frequency-Based Embeddings
		Exercise 6.01: Word-Level One-Hot Encoding
		Character-Level One-Hot Encoding
		Exercise 6.02: Character One-Hot Encoding – Manual
		Exercise 6.03: Character-Level One-Hot Encoding with Keras
		Learned Word Embeddings
		Word2Vec
		Exercise 6.04: Training Word Vectors
		Using Pre-Trained Word Vectors
		Exercise 6.05: Using Pre-Trained Word Vectors
		Document Vectors
		Uses of Document Vectors
		Exercise 6.06: Converting News Headlines to Document Vectors
		Activity 6.01: Finding Similar News Article Using Document Vectors
	Summary
Chapter 7: Text Generation and Summarization
	Introduction
	Generating Text with Markov Chains
		Markov Chains
		Exercise 7.01: Text Generation Using a Random Walk over a Markov Chain
	Text Summarization
		TextRank
	Key Input Parameters for TextRank
		Exercise 7.02: Performing Summarization Using TextRank
		Exercise 7.03: Summarizing a Children\'s Fairy Tale Using TextRank
		Activity 7.01: Summarizing Complaints in the Consumer Financial Protection Bureau Dataset
	Recent Developments in Text Generation and Summarization
	Practical Challenges in Extractive Summarization
	Summary
Chapter 8: Sentiment Analysis
	Introduction
		Why Is Sentiment Analysis Required?
		The Growth of Sentiment Analysis
		The Monetization of Emotion
		Types of Sentiments
			Emotion
		Key Ideas and Terms
		Applications of Sentiment Analysis
	Tools Used for Sentiment Analysis
		NLP Services from Major Cloud Providers
		Online Marketplaces
		Python NLP Libraries
		Deep Learning Frameworks
	The textblob library
		Exercise 8.01: Basic Sentiment Analysis Using the textblob Library
		Activity 8.01: Tweet Sentiment Analysis Using the textblob library
	Understanding Data for Sentiment Analysis
		Exercise 8.02: Loading Data for Sentiment Analysis
	Training Sentiment Models
		Activity 8.02: Training a Sentiment Model Using TFIDF and Logistic Regression
	Summary
Appendix
Index