Industry recognized certification enables you to add this credential to your resume upon completion of all courses

Need Custom Training for Your Team?
Get Quote
Call Us

Toll Free (844) 397-3739

Inquire About This Course
Burak Yoldemir, Instructor - Natural Language Processing

Burak Yoldemir

Instructor holds a Ph.D. in Electrical and Computer Engineering, with a focus on machine learning and data analysis.

Instructor: Burak Yoldemir

A hands-on and practical course on making machines understand the way we speak. Instructor holds a Ph.D. in Electrical and Computer Engineering, with a focus on machine learning and data analysis.

This course helps students understand how machines understand human language.

Course Description

This is an introductory course and assumes no background in natural language processing. Exposure to math is kept to a minimum and used only when it is needed to reinforce learning. The course is loaded with Python code snippets and exercises throughout and ends with an exciting final project on natural language generation. Instructor holds a Ph.D. in Electrical and Computer Engineering, with a focus on machine learning and data analysis.

What am I going to get from this course?

  • Preprocess and clean up text data
  • Extract features from text data to be used in downstream tasks
  • Perform some of the most common NLP tasks, such as text classification and topic modeling
  • Make a machine generate text that sounds like your favourite celebrity or book

Prerequisites and Target Audience

What will students need to know or do before starting this course?

  • Familiarity with the Python programming language is required
  • Students will benefit from prior exposure to machine learning and probability

Who should take this course? Who should not?

Industry professionals and college students who are interested in a broad overview of how machines understand human language.


Module 1: Introduction

Lecture 1 Introduction

Definition of NLP, sample NLP applications, and associated challenges

Module 2: Hello NLP

Lecture 2 Hello NLP I

Setting up your development environment and introduction to NLTK

Lecture 3 Hello NLP II

Introduction to Project Gutenberg, which provides a repository of copyright-free books that we will use throughout the course.

Lecture 4 Hello NLP III

Preliminary analyses, such as counting occurrences of words in a document, generating frequency distributions of words, and creating word clouds

Quiz 1 Finding the most common word in Hamlet

Module 3: Data Preprocessing

Lecture 5 Preprocessing I

Case normalization, removing punctuation, and tokenization

Lecture 6 Preprocessing II

Lexicon normalization and stop word removal

Quiz 2 Finding the most common word in Moby Dick, ignoring stop words and punctuation

Module 4: Feature Engineering

Lecture 7 Feature Engineering I

Part of speech tagging and named entity recognition

Lecture 8 Feature Engineering II

N-grams and TF-IDF

Lecture 9 Feature Engineering III

Word embeddings

Quiz 3 Determining POS tags
Quiz 4 Number of bigrams
Quiz 5 Word arithmetic with embeddings

Module 5: Topic Modeling

Lecture 10 Topic Modeling I

Latent semantic analysis (LSA)

Lecture 11 Topic Modeling II

Latent Dirichlet allocation

Quiz 6 Latent Dirichlet allocation
Quiz 7 Number of topics extracted

Module 6: Text Classification

Lecture 12 Text Classification I

Preparing a dataset for text classification

Lecture 13 Text Classification II

Feature extraction for text classification

Lecture 14 Text Classification III

Training a machine learning model for text classification

Quiz 8 Sentiment analysis on tweets
Quiz 9 Word embeddings vs word count vectors vs TF-IDF vectors
Quiz 10 Train and test sets

Module 7: Language Modeling

Lecture 15 Language Modeling

Markov models for language modeling and final project description