annotate embeddings/parameters.py @ 496:f13847478c6d

A few more ideas, in comments
author Joseph Turian <turian@gmail.com>
date Tue, 28 Oct 2008 12:09:49 -0400
parents 3daabc7f94ff
children 919125098a3b
rev   line source
458
ed6b0b3be8d2 Polished embeddings module
Joseph Turian <turian@iro.umontreal.ca>
parents:
diff changeset
1 """
ed6b0b3be8d2 Polished embeddings module
Joseph Turian <turian@iro.umontreal.ca>
parents:
diff changeset
2 Locations of the embedding data files.
ed6b0b3be8d2 Polished embeddings module
Joseph Turian <turian@iro.umontreal.ca>
parents:
diff changeset
3 """
484
3daabc7f94ff Added Yoshua's explanation
Joseph Turian <turian@gmail.com>
parents: 468
diff changeset
4 #WEIGHTSFILE = "/home/fringant2/lisa/data/word_embeddings.collobert-and-weston/lm-weights.txt"
3daabc7f94ff Added Yoshua's explanation
Joseph Turian <turian@gmail.com>
parents: 468
diff changeset
5 #VOCABFILE = "/home/fringant2/lisa/data/word_embeddings.collobert-and-weston/words.asc"
3daabc7f94ff Added Yoshua's explanation
Joseph Turian <turian@gmail.com>
parents: 468
diff changeset
6 WEIGHTSFILE = "/home/joseph/data/word_embeddings.collobert-and-weston/lm-weights.txt"
3daabc7f94ff Added Yoshua's explanation
Joseph Turian <turian@gmail.com>
parents: 468
diff changeset
7 VOCABFILE = "/home/joseph/data/word_embeddings.collobert-and-weston/words.asc"
458
ed6b0b3be8d2 Polished embeddings module
Joseph Turian <turian@iro.umontreal.ca>
parents:
diff changeset
8 NUMBER_OF_WORDS = 30000
ed6b0b3be8d2 Polished embeddings module
Joseph Turian <turian@iro.umontreal.ca>
parents:
diff changeset
9 DIMENSIONS = 50
459
f400f62e7f9e Fixed embedding preprocessing
Joseph Turian <turian@iro.umontreal.ca>
parents: 458
diff changeset
10 UNKNOWN = "UNKNOWN"