From the course: Advanced NLP with Python for Machine Learning
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
What makes doc2vec powerful? - Python Tutorial
From the course: Advanced NLP with Python for Machine Learning
What makes doc2vec powerful?
- [Instructor] Doc2Vec converts sentences or paragraphs into a single numeric vector. Now, why is that more useful than what we saw with Word2Vec before? Remember we saw these interesting mathematical properties of the individual word vectors? You can do the same thing with document vectors, but the outcome is not as clean or easily illustrated. This was an interesting property for Word2Vec and very useful in some applications, but not necessarily for ours. Where Word2Vec does fall a little bit short is when you have to average the word vectors across a sentence to prepare it to be used for machine learning. The goal is to capture the information contained within the sentence, but averaging numbers is a very naive way to capture information about a group of numbers. When you average numbers, you inherently lose information. You're taking X numbers and trying to represent them with one number. The real benefit of Doc2Vec…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.