Free NLP Course

NLP Course in Python: From Beginner to Expert in 2 months

by

Looking to learn about Natural Language Processing (NLP)? Look no further than our blog! We’re excited to offer a free NLP course that covers all the important concepts in the field. Not only will you learn about the theory behind NLP, but you’ll also get hands-on experience with real-time projects in every lesson.

What sets our NLP course apart is its implementation-focused approach. You won’t just learn about the concepts, you’ll also learn how to apply them in practice. This means you’ll gain valuable skills that you can use in your own NLP projects.

And the best part? It’s all completely free! No need to spend a fortune on expensive courses or textbooks. Our NLP course is accessible to anyone who wants to learn, regardless of their background or experience level.

So what are you waiting for? Head over to our blog and start learning about NLP today. With our free course, you’ll be on your way to mastering one of the most in-demand skills in the tech industry.

For successfully completing and proper understanding of this NLP course following are the prerequisites for this course:

Prerequisites

  • Proficiency in Python: Implementation of all the NLP concepts will be demonstrated in Python. If you have a good level of programming experience in a different language (e.g. C/C++/Matlab/Java/Javascript), you can understand the course and pick up the code as well.
  • College level Calculus, Linear Algebra You should be comfortable taking (multivariable) derivatives and understanding matrix/vector notation and operations. You can refer to this PDF for the calculus course offered by MIT OCW.
  • Basic Probability and Statistics You should know the basics of probabilities, and statistics such as Gaussian distributions, mean, median, standard deviation, etc. You can refer to this free online course offered by MIT OCW.
  • Understanding of Machine Learning You should know the basic level of machine learning concepts such as cost functions, taking derivatives, and performing optimization with gradient descent. You can refer to this free online course offered by Andrew NG on Coursera.

Note: The course still is in the development stage so the links which are inactive currently are in the development stage and will be available immediately once prepared.

NLP Course Structure

Module 1: Lexical Processing

Basic Lexical Processing

  1. Introduction to Natural Language Processing
  2. Regular Expressions – Quantifiers Part 1
  3. Regular Expressions -Quantifiers Part 2
  4. Regular Expressions – Anchors & Wildcards
  5. Regular Expressions – Character Sets
  6. Regular Expression – Commonly Used Functions
  7. Regular Expression – Grouping
  8. Tokenization in Natural Language Processing
  9. What are Stopwords in NLP and Why we should remove them?
  10. Bag of Words (BoW) model with Complete implementation in Python
  11. Stemming and Lemmatization
  12. TF-IDF in NLP & How to implement it in 4 steps
  13. Project 1: Building Financial Sentiment Analyzer

Advanced Lexical Processing

  1. Canonicalization
  2. Phonetic Hashing
  3. Edit Distance
  4. Pointwise Mutual Information
  5. Project 2: Building Real-Time Spell Corrector

Module 2: Syntactic Processing

Introduction to Syntactic Processing

  1. Introduction to Syntactic Processing
  2. Parts-of-Speech (POS) Tagging
  3. Lexicon and Rule-based POS Tagging
  4. Probabilistic POS Tagging: Markov Chain and Hidden Markov Model (HMM) with Implementation in Python

Parsing

  1. Introduction to Parsing
  2. Constituency Parsing
  3. Dependency Parsing

Named Entity Recognition

  1. Introduction to Named Entity Recognition
  2. Probabilistic Models for Entity Recognition
  3. Naive Bayes Classifier for NER
  4. Decision Tree Classifiers for NER
  5. Project 3: Information Extraction System for Airline Travel Information Systems (ATIS)
  6. Project 4: Clinical NER

Conditional Random Fields (CRFs)

  1. Introduction to CRFs
  2. CRF Model Architecture -I
  3. CRF ModelArchitecture -II
  4. Training a CRF Model
  5. Python Implementation of CRF

Module 3: Semantic Processing

Introduction to Semantic Processing

  1. Concepts and Terms
  2. Entity & Entity Types
  3. Arity & Reification
  4. Schema
  5. Semantic Association
  6. WordNet & ConceptNet
  7. Word Sense Disambiguation
  8. Lesk Algorithm Implementation

Distributional Semantics

  1. Introduction to Distributional Semantics
  2. Occurrence Matrix
  3. Co-Occurrence Matrix
  4. Word Vectors
  5. Word Embeddings
  6. Latent Semantic Analysis
  7. Skip-gram Model
  8. Word2Vec in Python
  9. Glove in Python
  10. Probabilistic Latent Semantic Analysis

Topic Modelling

  1. Introduction to Topic Modelling
  2. Matrix Factorisation-based Topic Modelling
  3. Probabilistic Model
  4. Probabilistic Latent Semantic Analysis
  5. Latent Dirichlet Allocation (LDA)
  6. Parameter Estimation Using Gibbs Sampling
  7. LDA implementation in Python
  8. Project 5: Social Media Opinion Mining

Module 4: Advanced NLP Concepts

  1. Issues with Recurrent Models: RNNs and LSTMs
  2. Introduction to Transformers in NLP
  3. Architecture of Transformers
  4. Intuition for Attention Mechanism
  5. Recurrence vs Attention
  6. GPT
  7. BERT & its Extensions
  8. In-context Learning & Very Large Models – GPT-3
  9. Project 6: Building Machine Translation Application using Transformer
  10. Project 7: Medical Speciality Detection using Custom Trained BioBert Transformer

Leave a Comment