Vocabulary (V)

Appears in 2 papers

The set of words the model knows about.

As used in Paper 05 — Efficient Estimation of Word Representations in Vector Space (Word2Vec) →

The set of words the model knows about. Typically the top 100,000 to

As used in Paper 06 — Sequence to Sequence Learning with Neural Networks →

The set of tokens (words, subwords, or characters) the model knows

Paper 05 — Efficient Estimation of Word Representations in Vector Space (Word2Vec) → Paper 06 — Sequence to Sequence Learning with Neural Networks →