Natural Language Processing Projects: Build Next-Generation NLP Applications Using AI Techniques

Table of Contents
About the Authors
About the Technical Reviewer
Acknowledgments
Chapter 1: Natural Language Processing and Artificial Intelligence Overview
	Machine Learning
		Supervised Learning
		Unsupervised Learning
		Reinforcement Learning
		Supervised Learning
			Regression
			Classification
				Linear Regression
				Logistic Regression
					Classification
				Random Forest
				Support-Vector Machines
					Nonlinear Data: The Kernel Trick
				Neural Networks
				Deep Neural Networks
				Convolutional Neural Networks
				RNN
		Unsupervised Learning
			Clustering
				k-means Clustering
				Hierarchical Clustering
			Dimensionality Reduction
		Reinforcement Learning
	NLP Concepts
		Unstructured Data
			Natural Language Processing
				Text Preprocessing
				Text to Features
					One-Hot Encoding (OHE)
					Count Vectorizer
					Term Frequency–Inverse Document Frequency (TF-IDF)
					Word Embeddings
			Applications
				Text Classification
				Text Summarization
				Text Generation
	The AI Life Cycle
		Understanding and Defining the Business Problem
		Translating the Business Problem into an ML Problem and Creating a Solution Approach/Architecture Design
		Data Collection and Understanding
		Data Cleaning and Preprocessing
		Exploratory Data Analysis
		Feature Engineering and Selection
		Model Building, Tuning, and Selection
		Model Testing and Validation
		Prediction and Insights
		Deployment or Productionization and Model Maintenance
	Business Context
Chapter 2: Product360: Sentiment and Emotion Detector
	Problem Statement
	Approach Formulation
		Steps to Solve This Problem
	Building an Emotion Classifier Model
		Data for Emotion Classifiers
		Data Cleaning and Preprocessing
		Label Encoding
		Train-Test Split
		Feature Engineering
		Model Building Phase
			Multinomial Naive Bayes
			Linear Classifier/Logistic Regression
			Support-Vector Machine
			Random Forest
			Model Evaluation and Comparison Summary
		Confusion Matrix for the Selected Model
	Real-time Data Extraction
		Twitter API
		Predicting the Emotion
		Predicting the Sentiment
		Visualization and Insights
		Emotion Analysis
		Emotion and Sentiment Analysis
		Automated Reporting
	Summary
Chapter 3: TED Talks Segmentation and Topics Extraction Using Machine Learning
	Problem Statement
	Approach Formulation
	Data Collection
	Understanding the Data
	Data Cleaning and Preprocessing
	Feature Engineering
		Count Vectors
		TF-IDF Vectors
		Word Embeddings
	Model Building Phase
		K-means Clustering
			Elbow Method
			Silhouette Coefficient
			Count Vectors as Features
				Elbow Method
				Silhouette
			TF-IDF as Features
				Elbow Method
				Silhouette
			Word Embeddings as Features
				Elbow Method
				Silhouette
	Building Clustering Model
		Cluster Visualization
	Topic Modeling
		Topic Modeling for Cluster 1
		Topic Modeling for Cluster 0
	Conclusion
Chapter 4: Enhancing E-commerce Using an Advanced Search Engine and Recommendation System
	Problem Statement
	Approach
		Content-Based Filtering
		Environment Setup
	Understanding the Data
	Exploratory Data Analysis
	Data Preprocessing
	Text Preprocessing
	Model Building
		Content-based Recommendation System
		Product Search Engine
			Implementation
	Advanced Search Engine Using PyTerrier and Sentence-BERT
		Data Preprocessing
		Building the Search Engine
	Multilingual Search Engine Using Deep Text Search
	Summary
Chapter 5: Creating a Résumé Parsing, Screening and Shortlisting System
	Context
	Methodology and Approach
	Implementation
	Installing and Importing Required Libraries
		Reading Résumés and Job Descriptions
		Text Processing
		Text to Features
		Feature Reduction
		Model Building
		Extracting Entities
		Ranking
		Visualization
	Conclusion
Chapter 6: Creating an E-commerce Product Categorization Model Using Deep Learning
	Problem Statement
	Methodology and Approach
		Environment Setup
		Understanding the Data
		Exploratory Data Analysis
		Data Preprocessing
			Text Preprocessing
		Feature Engineering
		Train-Test Split
		Model Building
		ANN
		Long Short-Term Memory: Recurrent Neural Networks
		Convolutional Neural Networks
		Evaluating the Model
			Hyperparameter Tuning
			Results
		Summary
Chapter 7: Predicting Duplicate Questions in Quora
	Problem Statement
	Approach
		Unsupervised Learning
		Supervised Learning
	Data set
	Implementation: Unsupervised Learning
		Data Preparation
		A. Building Vectors Using doc2vec
		B. Sentence Transformers Using the BERT Model
		C. GPT
		Finding Similar questions
	Implementation: Supervised Learning
		Understanding the Data
		Preprocessing the Data
		Text to Feature
		Model Building
		Evaluation
		Predictions on New Sentence Pairs
	Conclusion
Chapter 8: Named-Entity Recognition Using CRF and BERT
	Problem Statement
	Methodology and Approach
	Implementation
		Data
		Train Data Preparation
		Test Data Preparation
		Model Building
			Conditional Random Fields (CRF)
				Simple Feature Mapping
				Feature Mapping by Adding More Features
			BERT Transformer
	Next Steps
	Summary
Chapter 9: Building a Chatbot Using Transfer Learning
	Approach
		Rule-based Chatbots
		Generative or Smart Chatbots
	Chatbot 1: QA System Using Similarity Scores
	Chatbot 2: Context-based Chatbot Using a Pretrained Model
		Hugging Face Transformers
	Chatbot 3: Pretrained Chatbot Using RNN
	Future Scope
		RASA
		Microsoft Bot Framework
	Conclusion
Chapter 10: News Headline Summarization
	Approach
		Extractive Summarization
		Abstractive Summarization
	Environment Setup
	Understanding the Data
	Text Preprocessing
	Model Building
		BART: Simple-Transformer Pretrained Model
	T5 Pretrained Model
	Evaluation Metrics for Summarization
	Future Scope
	Conclusion
Chapter 11: Text Generation: Next Word Prediction
	Problem Statement
	Approach: Understanding Language Modeling
	Implementation
		Model 1: Word-to-Word Text Generation
		Model 2: Sentence by Sentence
		Model 3: Sequence of Input Words and Output Word
		GPT-2 (Advanced Pretrained Model)
		Autocomplete/Suggestion
			Fast Autocomplete
	Conclusion
Chapter 12: Conclusion and Future Trends
	AutoNLP
	Multilingual NLP
	Conversational AI
	Industry-Specific Pretrained Models
	Image Captioning
Index