Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
mind:word2vec [2016/09/25 22:25]
bayb2 [Examples]
mind:word2vec [2016/09/25 22:49] (current)
bayb2
Line 1: Line 1:
 =Word2Vec= =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== ==Notation==
Line 14: Line 36:
  knee : leg :: elbow : arm  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.
  
-==Examples== +==Implementation== 
- +Word2Vec can be implemented in DL4JTensorFlow
- +
-Rome - Italy = Beijing - Chinaso Rome - Italy + China = Beijing +
- +
-king : queen :: man : woman+
  
-house : roof :: castle : [domebell_tower, spire, crenellations,​ turrets]+==To research== 
 +*Implementation 
 +*Cosine similaritydot product equation usage
  
-China Taiwan :: Russia : [Ukraine, Moscow, Moldova, Armenia]+==Links== 
 +*http://​deeplearning4j.org/​word2vec
  
mind/word2vec.1474842323.txt.gz · Last modified: 2016/09/25 22:25 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