Word2Vec

Intro

“Just as Van Gogh’s painting of sunflowers is a two-dimensional mixture of oil on canvas that represents vegetable matter in a three-dimensional space in Paris in the late 1880s, so 500 numbers arranged in a vector can represent a word or group of words.” –DL4J

Word2Vec can guess a word’s association with other words, or cluster documents and define them by topic. It makes qualities into quantities, and similar things and ideas are shown to be “close” in its 500-dimension vectorspace.

Word2Vec is not classified as “deep learning” because it is only a 2-layer neural net.

Input → text corpus Output → set of vectors, or neural word embeddings

Examples

Rome - Italy = Beijing - China, so Rome - Italy + China = Beijing
king : queen :: man : woman
house : roof :: castle : [dome, bell_tower, spire, crenellations, turrets]
China : Taiwan :: Russia : [Ukraine, Moscow, Moldova, Armenia]

Notation

Algebraic notation

knee - leg = elbow - arm

English logic

knee is to leg as elbow is to arm

Logical analogy notation

knee : leg :: elbow : arm

Models

Continuous bag of words (CBOW) model

  • Uses a context to predict a target word. Faster.
  • Several times faster to train than the skip-gram, slightly better accuracy for frequent words.

Skip-gram model

  • Uses a word to predict a target context.
  • Works well with small amount of the training data, represents well even rare words or phrases.
  • Produces more accurate results on large datasets.

Implementation

Word2Vec can be implemented in DL4J, TensorFlow

To research

  • Implementation
  • Cosine similarity, dot product equation usage
mind/word2vec.txt · Last modified: 2016/09/25 22:49 by bayb2
Back to top
CC Attribution-Share Alike 4.0 International
chimeric.de = chi`s home Valid CSS Driven by DokuWiki do yourself a favour and use a real browser - get firefox!! Recent changes RSS feed Valid XHTML 1.0