U&P AI - Natural Language Processing (NLP) with Python
4.7 (1,206 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
13,521 students enrolled

U&P AI - Natural Language Processing (NLP) with Python

Become an NLP Engineer by creating real projects using Python, semantic search, text mining and search engines!
Highest Rated
4.7 (1,206 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
13,521 students enrolled
Created by Abdulhadi Darwish
Last updated 5/2020
English
English [Auto]
Current price: $11.99 Original price: $19.99 Discount: 40% off
3 days left at this price!
30-Day Money-Back Guarantee
This course includes
  • 6 hours on-demand video
  • 3 articles
  • 4 downloadable resources
  • Full lifetime access
  • Access on mobile and TV
  • Certificate of Completion
Training 5 or more people?

Get your team access to 4,000+ top Udemy courses anytime, anywhere.

Try Udemy for Business
What you'll learn
  • Understand every detail and build real stuff in NLP
  • (NEW)Learn how some plugins use semantic search to generate source code
  • (NEW)Building your vocabulary for any NLP model
  • (NEW)Reducing Dimensions of your Vocabulary for Machine Learning Models
  • (NEW)Feature Engineering and convert text to numerical values for machine learning models
  • (NEW) Keyword search VS Semantic search
  • (NEW)Similarity between documents
  • (NEW)Dealing with WordNet
  • (NEW)Search engines under the hood
  • Tokenizing text data
  • Converting words to their base forms using stemming
  • Converting words to their base forms using lemmatization
  • Dividing text data into chunks
  • Dealing with corpuses
  • Extracting document term matrix using the Bag of Words model
  • Building a category predictor
  • Constructing a gender identifier
  • Building a sentiment analyzer
  • Topic modeling using Latent Dirichlet Allocation
Course content
Expand all 71 lectures 05:49:29
+ Getting an Idea of NLP and its Applications
24 lectures 01:17:14
Note!
00:05

By the end of this section, not the course, the course is updated!

By The End Of This Section
01:18
Installation
03:30
Tips
00:30
U - Tokenization
01:15
P - Tokenization
02:21
U - Stemming
01:56
P - Stemming
04:50
U - Lemmatization
01:47
P - Lemmatization
03:06
U - Chunks
01:45
P - Chunks
05:04
U - Bag Of Words
04:15
P - Bag Of Words
04:20
P - Category Predictor
05:49
U - Gender Identifier
01:07
P - Gender Identifier
07:38
P - Sentiment Analyzer
06:58
U - Topic Modeling
02:45
P - Topic Modeling
05:54
Summary
01:12
+ Feature Engineering
8 lectures 27:19
Using Google Colab
00:05
Introduction
01:36
One Hot Encoding
02:26
Count Vectorizer
03:30
N-grams
03:56
Hash Vectorizing
01:35
Word Embedding
10:40
FastText
03:31
+ Dealing with corpus and WordNet
8 lectures 47:27
Introduction
01:06
In-built corpora
05:45
External Corpora
07:30
Corpuses & Frequency Distribution
07:19
Frequency Distribution
05:57
WordNet
05:44
Wordnet with Hyponyms and Hypernyms
07:22
The Average according to WordNet
06:44
+ Create your Vocabulary for any NLP Model
20 lectures 01:43:09
Putting the previous knowledge together
00:04
Introduction and Challenges
08:11
1 - Building your Vocabulary
02:26
2 - Building your Vocabulary
03:02
3 - Building your Vocabulary
07:11
4 - Building your Vocabulary
11:40
5 - Building your Vocabulary
06:13
Dot Product
03:12
Similarity using Dot Product
02:50
Reducing Dimensions of your Vocabulary using token improvement
02:03
Reducing Dimensions of your Vocabulary using n-grams
09:30
Reducing Dimensions of your Vocabulary using normalizing
09:36
Reducing Dimensions of your Vocabulary using case normalization
05:10
When to use stemming and lemmatization?
03:36
Sentiment Analysis Overview
05:00
Two approaches for sentiment analysis
02:41
Sentiment Analysis using rule-based
05:13
Sentiment Analysis using machine learning - 1
10:21
Sentiment Analysis using machine learning - 2
04:22
Summary
00:48
+ Word2Vec in Detail and what is going on under the hood
8 lectures 01:08:53
Introduction
04:14
Bag of words in detail
13:59
Vectorizing
08:22
Vectorizing and Cosine Similarity
10:30
Topic modeling in Detail
16:19
Make your Vectors will more reflect the Meaning, or Topic, of the Document
10:26
Sklearn in a short way
03:03
Summary
02:00
+ Find and Represent the Meaning or Topic of Natural Language Text
3 lectures 25:27
Problems in TI-IDF leads to Semantic Search
10:00
Transform TF-IDF Vectors to Topic Vectors under the hood
11:23
Requirements
  • A little bit of python
Description


-- UPDATED -- (NEW LESSONS ARE NOT IN THE PROMO VIDEO)

Learn about everything in AI by understanding concepts and building real stuff!

This course is a part of a series of courses specialized in artificial intelligence :

  • Understand and Practice AI - (NLP)

This course is focusing on the NLP:

  • Learn key NLP concepts and intuition training to get you quickly up to speed with all things NLP.

  • I will give you the information in an optimal way, I will explain in the first video for example what is the concept, and why is it important, what is the problem that led to thinking about this concept and how can I use it (Understand the concept). In the next video, you will go to practice in a real-world project or in a simple problem using python (Practice).

  • The first thing you will see in the video is the input and the output of the practical section so you can understand everything and you can get a clear picture!

  • You will have all the resources at the end of this course, the full code, and some other useful links and articles.

In this course, we are going to learn about natural language processing. We will discuss various concepts such as tokenization, stemming, and lemmatization to process text. We will then discuss how to build a Bag of Words model and use it to classify text. We will see how to use machine learning to analyze the sentiment of a given sentence. We will then discuss topic modeling and implement a system to identify topics in a given document.we will start with simple problems in NLP such as Tokenization Text, Stemming, Lemmatization, Chunks, Bag of Words model. and we will build some real stuff such as :

  1. Learning How to Represent the Meaning of Natural Language Text

  2. Building a category predictor to predict the category of a given text document.

  3. Constructing a gender identifier based on the name.

  4. Building a sentiment analyzer used to determine whether a movie review is positive or negative.

  5. Topic modeling using Latent Dirichlet Allocation

  6. Feature Engineering

  7. Dealing with corpora and WordNet

  8. Dealing With your Vocabulary for any NLP and ML model

TIPS (for getting through the course):

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

  • 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.

You don't know anything about NLP? let's break it down!

I am always available to answer your questions and help you along your data science journey. See you in class!

NOTICE that This course will be modified and I will add new content and new concepts from one time to another, so stay informed! :)

Who this course is for:
  • Anyone who wants to understand NLP concepts and build some projects
  • Beginner python developers curios about NLP, this course is not for experienced data scientists