GloVe, FastText, and Subword Embeddings
Word2Vec trained one embedding per word. GloVe factorized the co-occurrence matrix. FastText embedded the pieces. BPE bridged to transformers.
Visual edition planned
This lesson isn’t interactive yet.
It is part of the curriculum and will get the same treatment as Phase 1 — a visual cover, hands-on labs, derivations with numeric checks and a quiz. Until then, the original lesson is the best place to read it:
Part of Phase 05 — NLP — Foundations to Advanced. Use the previous / next cards below to keep browsing the phase.