0PricingLogin
NLP Academy · Lesson

From Sparse Counts to Dense Vectors

Why embeddings beat bag-of-words.

A Quick Recap

Bag-of-words and TF-IDF turned text into long count vectors. They work, but those sparse vectors hide a real weakness you are about to see.

Mostly Zeros

A bag-of-words vector has one slot per vocabulary word, so a short sentence is almost all zeros. We call this a sparse representation.

All lessons in this course

  1. From Sparse Counts to Dense Vectors
  2. How word2vec Learns Meaning
  3. Loading GloVe Vectors in Python
  4. Word Math: King Minus Man Plus Woman
← Back to NLP Academy