jackmyers.info
This example calls server-side scripts hosted by RareTechnologies.
See their published word2vec tutorial.

Similar words


One of these words is not like the others


Analogies — I:J :: X:Y

as


Cosine similarity is a measure of similarity between two vectors of an inner product space that measures the cosine of the angle between them. The cosine of 0° is 1, and it is less than 1 for any other angle. It is thus a judgment of orientation and not magnitude: two vectors with the same orientation have a cosine similarity of 1, two vectors at 90° have a similarity of 0, and two vectors diametrically opposed have a similarity of -1, independent of their magnitude.

The resulting similarity ranges from -1 meaning exactly opposite, to 1 meaning exactly the same, with 0 indicating orthogonality (decorrelation), and in-between values indicating intermediate similarity or dissimilarity. from Wikipedia

This web application, coded by Dr. Radim Řehůřek uses the word2vec model trained by Google on the Google News dataset, on about 100 billion words. "The model contains 3,000,000 unique phrases built with a layer size of 300. Note that the similarities were trained on a news dataset, and that Google did very little preprocessing there. So the phrases are case sensitive: watch out! Especially with proper nouns."

Examples

  • Most similar word -- try:
    • Cher
    • boring
    • cowboy
    • PERL
    • Java
  • Most dissimilar word -- try:
    • variable loop tractor switch method
    • elm oak flag willow pear
    • Beatles Rolling_Stones Led_Zeppelin Madonna Pink_Floyd
    • run jump kick sleep walk climb swim
    • sleep rest jump dream nap relax
    • sleep rest climb dream nap relax
  • Analogies are tricky, -- try:
    • niece is to nephew as sister is to
    • niece is to nephew as madam is to
    • Led_Zeppelin is to rock as Garth_Brooks is to
    • Berlin is to Germany as Paris is to
    • Berlin is to Germany as Trenton is to
    • Berlin is to Hamburg as Trenton is to
    • Rowan is to Glassboro as Rugers is to
    • touchdown is to football as homer is to
    • winter is to snow as summer is to
    • singer is to song as writer is to
    • writer is to book as singer is to
    • writer is to novel as singer is to
    • Toronto is to Toronto_Maple_Leafs as Philadelphia is to
    • Monet is to painter as Ice_Cube is to
    • Aristotle is to philosopher as Tom_Cruise is to
    • Aristotle is to philosopher as Tom_Hanks is to
    • Gates is to Microsoft as Jobs is to
    • Gates is to Microsoft as jobs is to
    • Italy is to pasta as Mexico is to
    • Hobbit is to Tolkein as Sherlock_Holmes is to
    • Frodo is to Tolkein as Sherlock_Holmes is to
    • small is to larger as red is to
    • small is to larger as old is to