Search icon CANCEL
Subscription
0
Cart icon
Your Cart (0 item)
Close icon
You have no products in your basket yet
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Conferences
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Natural Language Processing with TensorFlow

You're reading from   Natural Language Processing with TensorFlow Teach language to machines using Python's deep learning library

Arrow left icon
Product type Paperback
Published in May 2018
Publisher Packt
ISBN-13 9781788478311
Length 472 pages
Edition 1st Edition
Languages
Arrow right icon
Authors (2):
Arrow left icon
Thushan Ganegedara Thushan Ganegedara
Author Profile Icon Thushan Ganegedara
Thushan Ganegedara
Motaz Saad Motaz Saad
Author Profile Icon Motaz Saad
Motaz Saad
Arrow right icon
View More author details
Toc

Table of Contents (14) Chapters Close

Preface 1. Introduction to Natural Language Processing 2. Understanding TensorFlow FREE CHAPTER 3. Word2vec – Learning Word Embeddings 4. Advanced Word2vec 5. Sentence Classification with Convolutional Neural Networks 6. Recurrent Neural Networks 7. Long Short-Term Memory Networks 8. Applications of LSTM – Generating Text 9. Applications of LSTM – Image Caption Generation 10. Sequence-to-Sequence Learning – Neural Machine Translation 11. Current Trends and the Future of Natural Language Processing A. Mathematical Foundations and Advanced TensorFlow Index

The original skip-gram algorithm

The skip-gram algorithm discussed up to this point in the book is actually an improvement over the original skip-gram algorithm proposed in the original paper by Mikolov and others, published in 2013. In this paper, the algorithm did not use an intermediate hidden layer to learn the representations. In contrast, the original algorithm used two different embedding or projection layers (the input and output embeddings in Figure 4.1) and defined a cost function derived from the embeddings themselves:

The original skip-gram algorithm

Figure 4.1: The original skip-gram algorithm without hidden layers

The original negative sampled loss was defined as follows:

The original skip-gram algorithm

Here, v is the input embeddings layer, v' is the output word embeddings layer, The original skip-gram algorithm corresponds to the embedding vector for the word wi in the input embeddings layer and The original skip-gram algorithm corresponds to the word vector for the word wi in the output embeddings layer.

The original skip-gram algorithm

is the noise distribution, from which we sample noise samples (for example, it can be as...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at $19.99/month. Cancel anytime
Banner background image