Implement NLP use-cases using BERT: Explore the Implementation of NLP Tasks Using the Deep Learning Framework and Python
- Length: 164 pages
- Edition: 1
- Language: English
- Publisher: BPB Publications
- Publication Date: 2021-04-17
- ISBN-10: 9390684625
- ISBN-13: 9789390684625
- Sales Rank: #3397795 (See Top 100 Books)
State-of-the-art BERT implementation for text classification
Key Features
- Provides a detailed explanation of the real world and industry wide NLP use-cases.
- Provides a solid foundation of the state of the art language model BERT.
- Provides methodologies to transform and fine tune the BERT model for a domain specific data.
Description
This book provides a solid foundation for ‘Natural Language Processing’ with pragmatic explanation and implementation of a wide variety of industry wide scenarios. After reading this book, one can simply jump to solve real world problems and join the league of NLP developers.
It starts with the introduction of Natural Language Processing and provides a good explanation of different practical situations which are currently implemented across the globe. Thereafter, it takes a deep dive into the text classification with different types of algorithms to implement the same. Then, it further introduces the second important NLP use case called Named Entity Recognition with its popular algorithm choices. Thereafter, it provides an introduction to a state of the art language model called BERT and its application.
After reading this book, you would be prepared to start picking any NLP applications, have a healthy discussion about the pros and cons of different approaches with other team members, and definitely implement a good NLP model.
Finally, at the end of this book you will connect with all the theoretical discussions with code snippets (Python) which would be really helpful to implement into your domain-specific applications.
What you will learn
- Learn to implement transfer learning on pre-trained BERT models.
- Learn to demonstrate a production ready Text Classification for domain specific data and networking using Python 3.x.
- Learn about the domain specific pre trained models with a library called `aiops` which has been specially designed for this book.
- Explore and work with popular and industry targeted NLP algorithms.
Who this book is for
This book is meant for Data Scientists and Machine Learning Engineers who are new to Natural Language Processing and want to quickly implement different NLP use-cases. Readers should have a basic knowledge of Python before reading the book.
Table of Contents
1. Introduction to NLP and Different Use-Cases
2. Deep Dive into Text Classification and Different Types of Algorithms in Industry
3. Named Entity Recognition
4. BERT and its Application
5. BERT: Text Classification
6. BERT: Text Classification Code
About the Authors
Amandeep has been working as a technical lead in the field of software development at the time of publishing this book. He has worked for almost eight years in a few of the top MNCs. His interests include coding in Java and Python with an inclination in deep learning. He has worked in numerous data science fields, especially Natural Language Processing. He received his master’s degree with a specialization in Data Analytics from the Birla Institute of Technology and Science, Pilani, and has reviewed a few research papers under ‘IEEE Transactions on Neural Networks and Learning Systems’. He has earned certifications from multiple MOOCs on data science, machine learning, deep learning, image processing, natural language processing, artificial intelligence, algorithms, statistics, mathematics, and related courses.
Cover Page Title Page Copyright Page Dedication Page About the Author About the Reviewers Acknowledgement Preface Errata Table of Contents 1. Introduction to NLP and Different Use-Cases Introduction Structure Objective 1.1 What is Natural Language Processing or NLP? 1.2 NLP use-cases 1.3 Quick sneak on NLP use-cases Text/Document/Sentence classification Emotion classification or sentiment analysis Subjectivity analysis Sarcasm detection Intent classification Hate speech detection Information extraction Named Entity Recognition (NER) QA (Questions and Answers) Chatbot Relation extraction Entity linking Text summarization Morphological analysis Semantic textual similarity Word sense disambiguation Spelling correction Grammatical error correction Language Modelling Slot filling Topic modelling Paraphrase generation Conclusion 2. Text Classification Introduction Structure Objective 2.1 Definition of text classification? 2.2 Text classification use-cases in the industry 2.2.1 Emotion classification or sentiment analysis 2.2.2 Subjectivity analysis: 2.2.3 Sarcasm detection 2.2.4 Intent classification 2.3 Popular text classification models 2.4 Steps to approach a text classification use-case 2.5 Conclusion 2.6 Questions 3. Named Entity Recognition Introduction Structure Objective 3.1 Definition of Named Entity Recognition? 3.2 Named-Entity Recognition use-cases 3.2.1 Unstructured to structured data conversion: 3.2.2 Chat-bots 3.3 Popular Named-Entity Extraction models 3.4 Steps to approach a named entity use-case 3.5 Conclusion 3.6 Questions 4. BERT and Its Application Introduction Structure Objective 4.1 What is BERT? 4.2. In-depth view of BERT 4.3. How does it work in the industry? 4.4. Different deep learning frameworkswith BERT 4.5. Appendix Conclusion Questions 5. BERT for Text Classification Introduction Structure Objective 5.1 Text classification recap 5.2 Text classification in BERT 5.2.1 Architecture changes in BERT 5.2.2 Data pre-processing before passing to BERT 5.3 Conclusion 5.4 Questions 6. BERT Code for Text Classification Introduction Structure Objective 6.1 Code sample to use the model after training 6.2. Code sample to fine-tune BERT 6.3. Conclusion 6.4 Questions Index
Donate to keep this site alive
1. Disable the AdBlock plugin. Otherwise, you may not get any links.
2. Solve the CAPTCHA.
3. Click download link.
4. Lead to download server to download.