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

✍ Scribed by Akshay Kulkarni, Adarsha Shivananda, Anoosh Kulkarni

• Publisher: Apress
• Year: 2021
• Tongue: English
• Leaves: 327
• Edition: 1
• Category: Library

✦ Synopsis

Leverage machine learning and deep learning techniques to build fully-fledged natural language processing (NLP) projects. Projects throughout this book grow in complexity and showcase methodologies, optimizing tips, and tricks to solve various business problems. You will use modern Python libraries and algorithms to build end-to-end NLP projects. 

The book starts with an overview of natural language processing (NLP) and artificial intelligence to provide a quick refresher on algorithms. Next, it covers end-to-end NLP projects beginning with traditional algorithms and projects such as customer review sentiment and emotion detection, topic modeling, and document clustering. From there, it delves into e-commerce related projects such as product categorization using the description of the product, a search engine to retrieve the relevant content, and a content-based recommendation system to enhance user experience. Moving forward, it explains how to build systems to find similar sentences using contextual embedding, summarizing huge documents using recurrent neural networks (RNN), automatic word suggestion using long short-term memory networks (LSTM), and how to build a chatbot using transfer learning. It concludes with an exploration of next-generation AI and algorithms in the research space. 

By the end of this book, you will have the knowledge needed to solve various business problems using NLP techniques.

What You Will Learn

• Implement full-fledged intelligent NLP applications with Python
• Translate real-world business problem on text data with NLP techniques
• Leverage machine learning and deep learning techniques to perform smart language processing
• Gain hands-on experience implementing end-to-end search engine information retrieval, text summarization, chatbots, text generation, document clustering and product classification, and more

Who This Book Is For

Data scientists, machine learning engineers, and deep learning professionals looking to build natural language applications using Python

✦ Table of Contents

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