Nowadays, search engines like Google and e-commerce businesses like Amazon greatly impact our lifestyles. Users search for a phrase or a description, and they will be presented with options in a fraction of a second. The question is, how do these tools grasp our natural language? Natural Language Processing (NLP) is a collection of tools from computer science, artificial intelligence, and linguistics that fills the void between humans and machines by making our natural language comprehensible to machines. NLP allows computers to understand written and spoken words in much the same way human beings can. The purpose of NLP problems is not just to understand words individually but to understand the whole meaning of the words. Today NLP serves the backbone of a large number of applications that have affected our lives, such as translation engines, chatbots, recommender systems, text classification, etc.
TechClass Natural Language Processing with Python online course gives you the necessary resources to gain the career-building NLP skills you need to succeed as an NLP specialist. By the end of this course, you will be familiar with how to preprocess and analyze texts as your first steps on the journey to NLP. You will get a complete understanding of how to use Python's scientific computing libraries to vectorize and embed words and documents and classify texts using machine learning models such as SVM and Naïve Bayes gradually. Moreover, you will learn how to implement LSTM as the widely used NLP deep learning model.
Learning outcomes
- Learn the basic concepts of NLP and its applications
- Learn various text preprocessing techniques like stemming, lemmatization, tokenizing
- Learn how to analyze a text
- Learn how to embed words
- Get familiar with text vectorization techniques
- Learn how to find the most used words in a text using wordcloud maps
- Learn how to create a simple recommender system
- Learn how to create a simple chatbot
- Gain hands-on experience performing sentiment analysis
- Learn how to classify texts
- Get familiar with machine learning models useful for NLP
- Gain hands-on experience training LSTM models
- Get familiar with deep learning and Keras
- Get acquainted with NLP libraries such as Gensim, NLTK, TextBlob, SpaCy
- Learn how to perform sentiment analysis with LSTM
Table of contents
Chapter 1: Intro to Course
- 1.1. Welcome!
- 1.2. About TechClass Data Science Department
- 1.3. Learning Outcome
- 1.4. Your Expectations, Goals, and Knowledge
- 1.5. Abbreviations
- 1.6.Copyright Notice
Chapter 2: Introduction
- 2.1. What is NLP?
- 2.2. Why Should We Learn NLP?
- 2.3. Applications of Natural Language Processing
- 2.4. Python Libraries for NLP Problems
- 2.5. A General Overview of This Course
- 2.6. Quiz
Chapter 3: Text Preprocessing Techniques
- 3.1. Introduction
- 3.2. Lower Case
- 3.3. Tokenizing
- 3.4. Remove Unnecessary Elements
- 3.5. Stemming and Lemmatization
- 3.6. Numtowords
- 3.7. Pos tagging
- 3.8. Quiz
Chapter 4: Text Analysis
- 4.1. Introduction
- 4.2. Preprocessing
- 4.3. Length Analysis
- 4.4. Word Cloud
- 4.5. Pointwise Mutual Information
- 4.6. Sentiment Analysis
- 4.7. Quiz
Chapter 5: Language Models
- 5.1. Introduction
- 5.2. What is Language Model?
- 5.3. Text and Sentences Probability
- 5.4. N-Garm and LMS
- 5.5. N-Garm and LMS: Implementation
- 5.6. Neural Language Models
- 5.7. Named Entity Recognition
- 5.8. Quiz
Chapter 6: Text Vectorization Techniques
- 6.1. Introduction
- 6.2. One-Hot
- 6.3. Bag of Words
- 6.4. TF-IDF
- 6.5. Similarity Measures
- 6.6. Build Movie Recommender System: EDA
- 6.7. Build Movie Recommender System
- 6.8. Quiz
- 6.9. Project 1: QA Service
Chapter 7: Word Embedding
- 7.1. Introduction
- 7.2. What is Word Embedding?
- 7.3. CBOW and Skip-gram
- 7.4. Implementing Word2Vec: Pre-trained Model
- 7.5. Trian Your Own Word2Vec Model
- 7.6. GloVe
- 7.7. Document Embedding
- 7.8. Implementing Doc2Vec
- 7.9. News Classification with Doc2Vec
- 7.10. Quiz
Chapter 8: Classical Models for Text Classification
- 8.1. Introduction
- 8.2. Best Classical Models for Text Classification
- 8.3. Classification Evaluation Metrics: Review
- 8.4. Logistic Regression
- 8.5. Naïve Bayes
- 8.6. SVM
- 8.7. Quiz
- 8.8. Project 2: Vox News Classification
Chapter 9: Deep Learning Overview
- 9.1. Introduction
- 9.2. What is Deep learning?
- 9.3. Deep Learning Architectures
- 9.4. What is Keras?
- 9.5. Overfitting
- 9.6. Regularization
- 9.7. Quiz
Chapter 10: LSTM for Text Classification
- 10.1. Introduction
- 10.2. Recurrent Neural Networks
- 10.3. How Does LSTM Work? Part I
- 10.4. How Does LSTM Work? Part II
- 10.5. Why LSTM?
- 10.6. Sentiment Analysis Using LSTM: Part I
- 10.7. Sentiment Analysis using LSTM: Part II
- 10.8. Build a Simple Text Generator
- 10.9. Sequence to Sequence Model
- 10.10. Quiz
- 10.11. Project 3: Machine Translation System
Chapter 11: Final Task
Chapter 12: Finishing the Course
- 12.1. What We Have Learned
- 12.2. Where to Go Next?
- 12.3. Your Opinion Matters
- 12.4. Congrats! You did it!
Brochure
