Automatically exported from code.google.com/p/word2vec

Clone this repo:

Branches

  1. d83ccfb bugfix in InitUnigramTable() - some words could not have been sampled as negative examples by tmikolov · 8 years ago master
  2. 330c98d Bug fix - added questions-phrases.txt by tmikolov · 8 years ago
  3. 02c556d added script for training big word vector model using public corpora by tmikolov · 8 years ago
  4. ffd46fd fixed minor bugs by tmikolov · 8 years ago
  5. 891d84c update to 0.1c version by tmikolov · 8 years ago
  6. 5815e5d and fixed the minimal cosine similarity to be -1 instead of 0 by tmikolov · 9 years ago
  7. ab5da71 updated the code so that it would run even with extremely large N (number of closest words), such as 5000 by tmikolov · 9 years ago
  8. dd2d92a fixed bug: the counter in K-means was updated too frequently by tmikolov · 9 years ago
  9. 445fc1e fixed typo back of words -> bag of words by tmikolov · 9 years ago
  10. 907cd68 bugfix - the vector computation was done before check for out-of-vocabulary words was performed, which resulted in accessing memory outside of the allocated block by tmikolov · 9 years ago
  11. 4896886 changed makefile so that the .sh scripts would become executable after 'make' by tmikolov · 9 years ago
  12. 8d17b01 distance -> cosine distance by tmikolov · 9 years ago
  13. d90649a changed index of OOV from 0 to -1 (so that first word vector is included in search) by tmikolov · 9 years ago
  14. 7082459 Added comment to makefile by tmikolov · 9 years ago
  15. ada9ca3 removed some specific information from README, as I just changed the scritps by tmikolov · 9 years ago
  16. 402ae80 aa by tmikolov · 9 years ago
  17. b354dfc aa by tmikolov · 9 years ago
  18. 45da685 aa by tmikolov · 9 years ago
  19. ced0164 aa by tmikolov · 9 years ago
  20. e7fb781 aa by tmikolov · 9 years ago