Word Embeddings (Word2Vec, GloVe)

Summary

Representing words as dense numeric vectors that capture semantic meaning — words with similar meanings end up close together in vector space, a major step up from Bag of Words' sparse counts.

• 1Load pretrained word embeddings and explore nearest-neighbor words for a few examples.
• 2Try the classic 'king - man + woman ≈ queen' vector arithmetic example.
• 3Learn why embeddings capture semantic relationships that raw word counts can't.