Track 4 · Path · 7 explainers
NLP I: Text as Numbers
Tokenization, classic text features, and word embeddings
- 1
Tokenization & BPE
How text becomes numbers — from characters to subword tokens via byte-pair encoding
- 2
Bag of Words
Turn text into numbers — count word occurrences to create the simplest document representation in NLP
- 3
TF-IDF
Score how important a word is to a document in a collection — the backbone of search engines and text retrieval
- 4
Word2Vec & Word Embeddings
Learn dense vector representations where similar words live near each other in space
- 5
CBOW (Continuous Bag of Words)
Predict the center word from its context — the averaging architecture behind Word2Vec
- 6
Skip-gram
Predict context words from a center word — the architecture that powers Word2Vec with negative sampling
- 7
Embeddings
Turning words and categories into vectors