Word2Vec: Build Semantic Recommender System with TensorFlow
3.6 (9 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.
120 students enrolled

Word2Vec: Build Semantic Recommender System with TensorFlow

Word2Vec Tutorial: Names Semantic Recommendation System by Building and Training a Word2vec Python Model with TensorFlow
3.6 (9 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.
120 students enrolled
Last updated 12/2018
English
English
Current price: $34.99 Original price: $49.99 Discount: 30% off
5 hours left at this price!
30-Day Money-Back Guarantee
This course includes
  • 2 hours on-demand video
  • 3 articles
  • 3 downloadable resources
  • Full lifetime access
  • Access on mobile and TV
  • Assignments
  • 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
  • Building and Training a Word2vec Model with Python TensorFlow
  • Semantic Recommender System - Practical Project to Semantically Suggest Names
  • Source Code *.py Files of All Lectures
  • English Captions for All Lectures
  • Q&A board to send your questions and get them answered quickly
Course content
Expand all 14 lectures 01:55:57
+ Course Overview
2 lectures 03:35

By the end of this course you will be able to structure your Word2Vec model, train it, and also use it in a real-world situation with confidence.


Word2Vec is one of the most common techniques in Natural Language Processing (NLP). It is necessary for anyone who wants to continue his career in this path. Here our main tool will be TensorFlow.


TensorFlow is a powerful Python library, developed by Google, that has a great community and is one of the best, if not the very best tool in this field.


In this course, we are going to learn all the steps in training and Word2Vec model, starting from pre-processing a text corpus, which is an inevitable part of any realistic NLP task, until of course training it using TensorFlow.


At the end of the course, you have a project. We are going to use our trained model semantically suggest names, based on one or even two given words or names, and of course, with real world considerations. By real world I mean being highly escapable.


An ideal for students in this course would be a data scientist who wants to progress into the NLP field, or a person with a minimal Python programming background that has just started their path to be a data scientist.


If you got any questions during this course, do not hesitate to ask the at the Q&A section of the course.

Preview 02:09
Course Tips
01:26
+ Model Building and Training
7 lectures 01:04:51

Requirements and how to setup your environment.

Preview 05:31

How to transform words to the machine-readable data.

Preview 10:51

Batching is a process to speed up training.

Batching
12:08

Defining the layers, vectors, loss functions and also an interesting hobby.

Structuring Your Model
16:29

Training our model with the prepared functions.

Training
11:34

In this video we plot a map of our words to see the semantic representation of words in our model.

Showing Map of Words
08:10
Do you want to learn a specific Word2Vec, TensorFlow or NLP topic?
00:08
+ Real World Considerations
2 lectures 32:10

Tensorflow offers a variety of options in saving and restoring models; here we are reviewing them.


Saving and Restoring
21:16

Making our database more standard and computer readable.

Text Pre-processing
10:54
+ Project
3 lectures 15:19

In this practical project, you will learn how to use your trained model.


Search for Names Only
13:31
Project Solution
01:44
Appendix: Good Extra Readings
00:04
+ Practical Exercise
0 lectures 00:00
Analogy game
Coding Exercise
1 question
Requirements
  • Python Level: Intermediate. This Word2Vec tutorial assumes that you already know the basics of writing simple Python programs and that you are generally familiar with Python's core features (data structures, file handling, functions, classes, modules, common library modules, etc.).
  • Python 2.7 or Python 3.4, 3.5, or 3.6. Tensorflow is not officially supporting Python 3.7.
  • Our trainees are positive and willing to learn. They practice lessons and send their questions to the Q&A section of the course, and we expect new trainees to have the same spirit.
Description

In this Word2Vec tutorial, you will learn how to train a Word2Vec Python model and use it to semantically suggest names based on one or even two given names.


This Word2Vec tutorial is meant to highlight the interesting, substantive parts of building a word2vec Python model with TensorFlow.


Word2vec is a group of related models that are used to produce Word Embeddings. Embedding vectors created using the Word2vec algorithm have many advantages compared to earlier algorithms such as latent semantic analysis.


Word embedding is one of the most popular representation of document vocabulary. It is capable of capturing context of a word in a document, semantic and syntactic similarity, relation with other words, etc. Word Embeddings are vector representations of a particular word.


The best way to understand an algorithm is to implement it. So, in this course you will learn Word Embeddings by implementing it in the Python library, TensorFlow.


Word2Vec is one of the most popular techniques to learn word embeddings using shallow neural network. Word2vec is a particularly computationally-efficient predictive model for learning word embeddings from raw text.


In this Word2Vec tutorial, you will learn The idea behind Word2Vec:

  1. Take a 3 layer neural network. (1 input layer + 1 hidden layer + 1 output layer)

  2. Feed it a word and train it to predict its neighbouring word.

  3. Remove the last (output layer) and keep the input and hidden layer.

  4. Now, input a word from within the vocabulary. The output given at the hidden layer is the ‘word embedding’ of the input word.


In this Word2Vec tutorial we are going to do all steps of building and training a Word2vec Python model (including pre-processing, tokenizing, batching, structuring the Word2Vec Python model and of course training it) using Python TensorFlow. Finally, we are going to use our trained Word2Vec Python model to semantically suggest names based on one or even two given names.


Let's start!






Who this course is for:
  • This Word2Vec tutorial is meant for those who are familiar with Python and want to learn how to use TensorFlow to implement Word2Vec Word Embeddings, building a real-life Semantic Recommendation System.