Search icon CANCEL
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
The Handbook of NLP with Gensim

You're reading from   The Handbook of NLP with Gensim Leverage topic modeling to uncover hidden patterns, themes, and valuable insights within textual data

Arrow left icon
Product type Paperback
Published in Oct 2023
Publisher Packt
ISBN-13 9781803244945
Length 310 pages
Edition 1st Edition
Arrow right icon
Author (1):
Arrow left icon
Chris Kuo Chris Kuo
Author Profile Icon Chris Kuo
Chris Kuo
Arrow right icon
View More author details
Toc

Table of Contents (24) Chapters Close

Preface 1. Part 1: NLP Basics
2. Chapter 1: Introduction to NLP FREE CHAPTER 3. Chapter 2: Text Representation 4. Chapter 3: Text Wrangling and Preprocessing 5. Part 2: Latent Semantic Analysis/Latent Semantic Indexing
6. Chapter 4: Latent Semantic Analysis with scikit-learn 7. Chapter 5: Cosine Similarity 8. Chapter 6: Latent Semantic Indexing with Gensim 9. Part 3: Word2Vec and Doc2Vec
10. Chapter 7: Using Word2Vec 11. Chapter 8: Doc2Vec with Gensim 12. Part 4: Topic Modeling with Latent Dirichlet Allocation
13. Chapter 9: Understanding Discrete Distributions 14. Chapter 10: Latent Dirichlet Allocation 15. Chapter 11: LDA Modeling 16. Chapter 12: LDA Visualization 17. Chapter 13: The Ensemble LDA for Model Stability 18. Part 5: Comparison and Applications
19. Chapter 14: LDA and BERTopic 20. Chapter 15: Real-World Use Cases 21. Assessments 22. Index 23. Other Books You May Enjoy

From LDA to Ensemble LDA

Suppose a corpus has three distinct words, and the three words belong to three topics. This idea is shown in Figure 13.1, in which the vertices of the simplex are the three words. The three topics are labeled as Topic A, Topic B, and Topic C in the left simplex. However, LDA may identify a fourth topic from the combination of the three topics. It is a “pseudo” topic, as shown in the middle of the simplex.

Figure 13.1 – Applying the ensembling method to LDA

Figure 13.1 – Applying the ensembling method to LDA

Let’s take an ensembling approach by building many LDA models on the same data. Most of the LDA models will have topics A, B, and C, and some other LDA models will produce pseudo topics in addition to topics A, B, and C. The “true” topics A, B, and C shall appear more frequently and the “pseudo” topics shall appear less frequently. This idea is demonstrated in the simplex on the right-hand side of Figure 14.1. All the blue...

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 AU $24.99/month. Cancel anytime