Natural Language Processing Recipes: Unlocking Text Data with Machine Learning and Deep Learning Using Python

ISBN-13: 9781484273500 / Angielski / Miękka / 2021 / 260 str.

Akshay Kulkarni; Adarsha Shivananda

Opis

Intermediate user level

Spis treści

Chapter 1: Extracting the Data

Chapter Goal: Understanding the potential data sources to build NLP applications for business benefits and ways to extract the text data with examples

No of pages: 23

Sub - Topics:  

1. Data extraction through API

2. Reading HTML page, HTML parsing

3. Reading pdf file in python

4. Reading word document

5. Regular expressions using python

6. Handling strings using python

7. Web scraping

Chapter 2: Exploring and Processing the Text Data

Chapter Goal: Data is never clean. This chapter will give in depth knowledge about how to clean and process the text data. It covers topics like cleaning, tokenizing and normalizing text data.

No of pages: 22

Sub - Topics

1 Text preprocessing methods 

2 Data cleaning – punctuation removal, stopwords removal, spelling correction

3 Lexicon normalization – stemming and lemmatization

4 Tokenization 

5 Dealing with emoticons and emojis

6 Exploratory data analysis

7 End to end text processing pipeline implementation

Chapter 3: Text to Features

Chapter Goal: One of the important task with text data is to transform text data into machines or algorithms understandable form, by using different feature engineering methods (basic to advanced).

No of pages: 40

Sub - Topics

1 One hot encoding

2 Count vectorizer

3 N grams

4 Co-occurrence matrix

5 Hashing vectorizer

6 TF-IDF

7 Word Embedding  - Word2vec, fasttext

8 Glove embeddings 

9 ELMo

10 Universal Sentence Encoder

11 Understanding Transformers like BERT, GPT

12 Open AIs

Chapter 4: Implementing Advanced NLP

Chapter Goal: Understanding and building advanced NLP techniques to solve the business problems starting from text similarity to speech recognition and language translation.

No of pages: 25

Sub - Topics: 

1. Noun phrase extraction

2. Text similarity

3. Parts of speech tagging

4. Information extraction – NER – entity recognition 

5. Topic modeling

6. Machine learning for NLP – 

a. Text classification

7. Sentiment analysis

8. Word sense disambiguation

9. Speech recognition and speech to text

10. Text to speech

11. Language detection and translation

Chapter 5: Deep Learning for NLP

Chapter Goal: Unlocking the power of deep learning on text data. Solving few real-time applications of deep learning in NLP.

No of pages: 55

Sub - Topics: 

1. Fundamentals of deep learning

2. Information retrieval using word embedding’s 

 3.  Text classification using deep learning approaches (CNN, RNN, LSTM, Bi-directional LSTM)

 4.  Natural language generation – prediction next word/ sequence of words using LSTM.

 5.  Text summarization using LSTM encoder and decoder.

 6.   Sentence comparison using SentenceBERT 

 7.  Understanding GPT

 8. Comparison between BERT, RoBERTa, DistilBERT, XLNet

Chapter 6: Industrial Application with End to End Implementation 

Chapter Goal: Solving real time NLP applications with end to end implementation using python. Right from framing and understanding the business problem to deploying the model.

No of pages: 90

Sub - Topics: 

 1.  Consumer complaint classification

 2.  Customer reviews sentiment prediction

 3.  Data stitching using text similarity and record linkage

 4.  Text summarization for subject notes

 5.  Document clustering 

 6. Product360 - Sentiment, emotion & trend capturing system

 7. TED Talks segmentation & topics extraction using machine learning

 8. Fake news detection system using deep neural networks

 9. E-commerce search engine & recommendation systems using deep learning

10. Movie genre tagging using multi-label classification 

11. E-commerce product categorization using deep learning

12. Sarcasm detection model using CNN

13. Building chatbot using transfer learning

14. Summarization system using RNN and reinforcement learning

Chapter 7: Conclusion - Next Gen NLP & AI

Chapter Goal: So far, we learnt how NLP when coupled with machine learning and deep learning helps us solve some of the complex business problems across industries and domains. In this chapter let us uncover how some of the next generation algorithms that would potentially play important roles in the future NLP era.

O autorze

Akshay Kulkarni is an AI and machine learning evangelist and thought leader. He has consulted with Fortune 500 and global enterprises to drive AI and data science-led strategic transformations. He has a rich experience of building and scaling AI and machine learning businesses and creating significant client impact. Akshay is currently Manager-Data Science & AI at Publicis Sapient where he is part of strategy and transformation interventions through AI. He manages high-priority growth initiatives around data science, works on AI engagements, and applies state-of-the-art techniques. Akshay is a Google Developers Expert-Machine Learning, and is a published author of books on NLP and deep learning. He is a regular speaker at major AI and data science conferences, including Strata, O'Reilly AI Conf, and GIDS. In 2019, he was featured as one of the Top "40 under 40 Data Scientists" in India. In his spare time, he enjoys reading, writing, coding, and helping aspiring data scientists. He lives in Bangalore with his family.

Adarsha Shivananda is Lead Data Scientist at Indegene's Product and Technology team where he leads a group of analysts who enable predictive analytics and AI features for all of their healthcare software products. They handle multi-channel activities for pharma products and solve real-time problems encountered by pharma sales reps. Adarsha aims to build a pool of exceptional data scientists within the organization and to solve greater health care problems through training programs and staying ahead of the curve. His core expertise involves machine learning, deep learning, recommendation systems, and statistics. Adarsha has worked on data science projects across multiple domains using different technologies and methodologies. Previously, he was part of Tredence Analytics and IQVIA. He lives in Bangalore and loves to read and teach data science.

Blurb

Focus on implementing end-to-end projects using Python and leverage state-of-the-art algorithms. This book teaches you to efficiently use a wide range of natural language processing (NLP) packages to: implement text classification, identify parts of speech, utilize topic modeling, text summarization, sentiment analysis, information retrieval, and many more applications of NLP. 

The book begins with text data collection, web scraping, and the different types of data sources. It explains how to clean and pre-process text data, and offers ways to analyze data with advanced algorithms. You then explore semantic and syntactic analysis of the text. Complex NLP solutions that involve text normalization are covered along with advanced pre-processing methods, POS tagging, parsing, text summarization, sentiment analysis, word2vec, seq2seq, and much more. The book presents the fundamentals necessary for applications of machine learning and deep learning in NLP. This second edition goes over advanced techniques to convert text to features such as Glove, Elmo, Bert, etc. It also includes an understanding of how transformers work, taking sentence BERT and GPT as examples. The final chapters explain advanced industrial applications of NLP with solution implementation and leveraging the power of deep learning techniques for NLP problems. It also employs state-of-the-art advanced RNNs, such as long short-term memory, to solve complex text generation tasks. 

After reading this book, you will have a clear understanding of the challenges faced by different industries and you will have worked on multiple examples of implementing NLP in the real world.

You will:

• Know the core concepts of implementing NLP and various approaches to natural language processing (NLP), including NLP using Python libraries such as NLTK, textblob, SpaCy, Standford CoreNLP, and more
  
• Implement text pre-processing and feature engineering in NLP, including advanced methods of feature engineering
• Understand and implement the concepts of information retrieval, text summarization, sentiment analysis, text classification, and other advanced NLP techniques leveraging machine learning and deep learning