4.54 out of 5
4.54
3179 reviews on Udemy

Natural Language Processing with Deep Learning in Python

Complete guide on deriving and implementing word2vec, GloVe, word embeddings, and sentiment analysis with recursive nets
Instructor:
Lazy Programmer Inc.
24,492 students enrolled
English [Auto-generated] More
Understand and implement word2vec
Understand the CBOW method in word2vec
Understand the skip-gram method in word2vec
Understand the negative sampling optimization in word2vec
Understand and implement GloVe using gradient descent and alternating least squares
Use recurrent neural networks for parts-of-speech tagging
Use recurrent neural networks for named entity recognition
Understand and implement recursive neural networks for sentiment analysis
Understand and implement recursive neural tensor networks for sentiment analysis

In this course we are going to look at advanced NLP.

Previously, you learned about some of the basics, like how many NLP problems are just regular machine learning and data science problems in disguise, and simple, practical methods like bag-of-words and term-document matrices.

These allowed us to do some pretty cool things, like detect spam emails, write poetry, spin articles, and group together similar words.

In this course I’m going to show you how to do even more awesome things. We’ll learn not just 1, but 4 new architectures in this course.

First up is word2vec.

In this course, I’m going to show you exactly how word2vec works, from theory to implementation, and you’ll see that it’s merely the application of skills you already know.

Word2vec is interesting because it magically maps words to a vector space where you can find analogies, like:

  • king – man = queen – woman

  • France – Paris = England – London

  • December – Novemeber = July – June

We are also going to look at the GloVe method, which also finds word vectors, but uses a technique called matrix factorization, which is a popular algorithm for recommender systems.

Amazingly, the word vectors produced by GLoVe are just as good as the ones produced by word2vec, and it’s way easier to train.

We will also look at some classical NLP problems, like parts-of-speech tagging and named entity recognition, and use recurrent neural networks to solve them. You’ll see that just about any problem can be solved using neural networks, but you’ll also learn the dangers of having too much complexity.

Lastly, you’ll learn about recursive neural networks, which finally help us solve the problem of negation in sentiment analysis. Recursive neural networks exploit the fact that sentences have a tree structure, and we can finally get away from naively using bag-of-words.

All of the materials required for this course can be downloaded and installed for FREE. We will do most of our work in Numpy, Matplotlib, and Theano. I am always available to answer your questions and help you along your data science journey.

This course focuses on “how to build and understand“, not just “how to use”. Anyone can learn to use an API in 15 minutes after reading some documentation. It’s not about “remembering facts”, it’s about “seeing for yourself” via experimentation. It will teach you how to visualize what’s happening in the model internally. If you want more than just a superficial look at machine learning models, this course is for you.

See you in class!

TIPS (for getting through the course):

  • Watch it at 2x.

  • Take handwritten notes. This will drastically increase your ability to retain the information.

  • Write down the equations. If you don’t, I guarantee it will just look like gibberish.

  • Ask lots of questions on the discussion board. The more the better!

  • Realize that most exercises will take you days or weeks to complete.

  • Write code yourself, don’t just sit there and look at my code.

HARD PREREQUISITES / KNOWLEDGE YOU ARE ASSUMED TO HAVE:

  • calculus

  • linear algebra

  • probability (conditional and joint distributions)

  • Python coding: if/else, loops, lists, dicts, sets

  • Numpy coding: matrix and vector operations, loading a CSV file

  • neural networks and backpropagation, be able to derive and code gradient descent algorithms on your own

  • Can write a feedforward neural network in Theano and TensorFlow

  • Can write a recurrent neural network / LSTM / GRU in Theano and TensorFlow from basic primitives, especially the scan function

  • Helpful to have experience with tree algorithms

WHAT ORDER SHOULD I TAKE YOUR COURSES IN?:

  • Check out the lecture “What order should I take your courses in?” (available in the Appendix of any of my courses, including the free Numpy course)

Outline, Review, and Logistical Things

1
Introduction, Outline, and Review
2
Where to get the code / data for this course
3
How to Succeed in this Course
4
Tensorflow or Theano - Your Choice!

Beginner's Corner: Working with Word Vectors

1
What are vectors?
2
What is a word analogy?
3
Trying to find and assess word vectors using TF-IDF and t-SNE
4
Pretrained word vectors from GloVe
5
Pretrained word vectors from word2vec
6
Text Classification with word vectors
7
Text Classification in Code
8
Using pretrained vectors later in the course

Review of Language Modeling and Neural Networks

1
Review Section Intro
2
Bigrams and Language Models
3
Bigrams in Code
4
Neural Bigram Model
5
Neural Bigram Model in Code
6
Neural Network Bigram Model
7
Neural Network Bigram Model in Code
8
Improving Efficiency
9
Improving Efficiency in Code
10
Review Section Summary

Word Embeddings and Word2Vec

1
Return of the Bigram
2
CBOW
3
Skip-Gram
4
Hierarchical Softmax
5
Negative Sampling
6
Negative Sampling - Important Details
7
Why do I have 2 word embedding matrices and what do I do with them?
8
Word2Vec implementation tricks
9
Word2Vec implementation outline
10
Word2Vec in Code with Numpy
11
Word2Vec Tensorflow Implementation Details
12
Word2Vec Tensorflow in Code
13
How to update only part of a Theano shared variable
14
Word2Vec in Code with Theano
15
Alternative to Wikipedia Data: Brown Corpus

Word Embeddings using GloVe

1
GloVe Section Introduction
2
Matrix Factorization for Recommender Systems - Basic Concepts
3
Matrix Factorization Training
4
Expanding the Matrix Factorization Model
5
Regularization for Matrix Factorization
6
GloVe - Global Vectors for Word Representation
7
Recap of ways to train GloVe
8
GloVe in Code - Numpy Gradient Descent
9
GloVe in Code - Alternating Least Squares
10
GloVe in Code - Theano Gradient Descent
11
GloVe in Tensorflow with Gradient Descent
12
Visualizing country analogies with t-SNE
13
Hyperparameter Challenge
14
Training GloVe with SVD (Singular Value Decomposition)

Unifying Word2Vec and GloVe

1
Pointwise Mutual Information - Word2Vec as Matrix Factorization
2
PMI in Code

Using Neural Networks to Solve NLP Problems

1
Parts-of-Speech (POS) Tagging
2
How can neural networks be used to solve POS tagging?
3
Parts-of-Speech Tagging Baseline
4
Parts-of-Speech Tagging Recurrent Neural Network in Theano
5
Parts-of-Speech Tagging Recurrent Neural Network in Tensorflow
6
How does an HMM solve POS tagging?
7
Parts-of-Speech Tagging Hidden Markov Model (HMM)
8
Named Entity Recognition (NER)
9
Comparing NER and POS tagging
10
Named Entity Recognition Baseline
11
Named Entity Recognition RNN in Theano
12
Named Entity Recognition RNN in Tensorflow
13
Hyperparameter Challenge II

Recursive Neural Networks (Tree Neural Networks)

1
Recursive Neural Networks Section Introduction
2
Sentences as Trees
3
Data Description for Recursive Neural Networks
4
What are Recursive Neural Networks / Tree Neural Networks (TNNs)?
5
Building a TNN with Recursion
6
Trees to Sequences
7
Recursive Neural Network in Theano
8
Recursive Neural Tensor Networks
9
RNTN in Tensorflow (Tips)
10
RNTN in Tensorflow (Code)
11
Recursive Neural Network in TensorFlow with Recursion

Theano and Tensorflow Basics Review

1
(Review) Theano Basics
2
(Review) Theano Neural Network in Code
3
(Review) Tensorflow Basics
4
(Review) Tensorflow Neural Network in Code

Legacy Word2vec Lectures

1
(Legacy) What is a word embedding?
2
(Legacy) Using pre-trained word embeddings
3
(Legacy) Word analogies using word embeddings
4
(Legacy) TF-IDF and t-SNE experiment
5
(Legacy) Word2Vec introduction

Appendix

1
What is the Appendix?
2
How to install wp2txt or WikiExtractor.py
3
Windows-Focused Environment Setup 2018
You can view and review the lecture materials indefinitely, like an on-demand channel.
Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don't have an internet connection, some instructors also let their students download course lectures. That's up to the instructor though, so make sure you get on their good side!
4.5
4.5 out of 5
3179 Ratings

Detailed Rating

Stars 5
1976
Stars 4
888
Stars 3
181
Stars 2
73
Stars 1
64
313ce096be22f18d754f25cb234f782d
30-Day Money-Back Guarantee

Includes

13 hours on-demand video
Full lifetime access
Access on mobile and TV
Certificate of Completion