From the course: Advanced NLP with Python for Machine Learning
Unlock the full course today
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Key takeaways for advanced NLP modeling techniques - Python Tutorial
From the course: Advanced NLP with Python for Machine Learning
Key takeaways for advanced NLP modeling techniques
- [Present] Let's walk through each of the four techniques we explored and summarize some of the key takeaways. Starting with TF-IDF, this is a fairly simple method that creates document level representations that capture how important a word is to a document within a corpus. It does this without any consideration of context in which a word is used and will return very sparse, very large vectors. And remember, these are stored as sparse matrices. Moving on to word2vec, word2vec is a slightly more sophisticated method that creates word vectors using a shallow two layer neural network. Then we average those word vectors to create a document or text message level representation. This method creates much smaller dense factors. I mentioned TF-IDF creates very sparse vectors with lots of zeros, this is the opposite where it's very dense, meaning very few or no zeros. Word2vec also considers the context in which a word is used…
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.
Contents
-
-
-
-
-
-
-
(Locked)
Prep the data for modeling2m 52s
-
(Locked)
Build a model on TF-IDF vectors6m 34s
-
(Locked)
Build a model on word2vec embeddings6m 41s
-
(Locked)
Build a model on doc2vec embeddings3m 59s
-
(Locked)
Build an RNN model5m 11s
-
(Locked)
Compare all methods using key performance metrics4m 16s
-
(Locked)
Key takeaways for advanced NLP modeling techniques3m 6s
-
(Locked)
-