Commit Graph

1381 Commits

Author SHA1 Message Date
Matthew Honnibal
b7e9c1da85 * Begin writing score_senses method 2015-07-03 05:10:52 +02:00
Matthew Honnibal
8464378a85 * Initialize Lexeme.senses to zero 2015-07-03 05:03:16 +02:00
Matthew Honnibal
e99e15574e * Add sense and sense_ properties to Token objects 2015-07-03 04:59:20 +02:00
Matthew Honnibal
8f068dc6fe * Set scores to 0 before prediction 2015-07-03 04:55:30 +02:00
Matthew Honnibal
2be517ba6d * Read in gold wsd data, as supersenses 2015-07-03 04:47:23 +02:00
Matthew Honnibal
c60cc22390 * Ignore adjective supersenses 2015-07-03 04:46:11 +02:00
Matthew Honnibal
dbcef2b76e * Read in new WSD gold data 2015-07-03 04:43:23 +02:00
Matthew Honnibal
333e414e9f * Hack prepare_treebank script to load wordnet supersenses 2015-07-02 08:31:12 +02:00
Matthew Honnibal
05146a4578 * Add script to read wordnet data for supersense stuff 2015-07-02 08:30:43 +02:00
Matthew Honnibal
2256ba7590 * Integrate sense tagger module 2015-07-02 00:54:46 +02:00
Matthew Honnibal
9c74f82d20 * Add rough sense tagger 2015-07-02 00:54:26 +02:00
Matthew Honnibal
4e830b9d41 * Add N_SENSES in senses.pxd 2015-07-02 00:54:06 +02:00
Matthew Honnibal
041908a272 * Merge neuralnet branch into sense-tagger 2015-07-01 22:38:22 +02:00
Matthew Honnibal
3992724685 * Compile sense_tagger 2015-07-01 22:37:31 +02:00
Matthew Honnibal
52fd80c6c6 * Add experimental supersense features for parsing, based on lookup into wordnet. 2015-07-01 20:12:44 +02:00
Matthew Honnibal
e6d828a9af * Set up an array POS_SENSES that denotes the set of valid senses for each POS tag. This way, we can do bitwise & between a lexeme's senses and the ones available for its POS tag, to get the allowable senses for the token. 2015-07-01 20:12:13 +02:00
Matthew Honnibal
2b8459d9a8 * Add senses flag to Lexeme 2015-07-01 20:10:41 +02:00
Matthew Honnibal
e23d1582a2 * Add supersense data to Lexeme objects. Add simple has_sense method to check the flag. 2015-07-01 18:50:37 +02:00
Matthew Honnibal
64fafa98be * Add senses.pyx and senses.pxd 2015-07-01 18:49:44 +02:00
Matthew Honnibal
1e8dd0e2c5 * Comple senses.pyx 2015-07-01 18:49:15 +02:00
Matthew Honnibal
62cfcd76fe * Add supersense sets to lexemes, from WordNet. Look-up via lemmatization. 2015-07-01 18:48:59 +02:00
Matthew Honnibal
aa3d06857e * Upd license page 2015-07-01 16:05:57 +02:00
Matthew Honnibal
be3e935bd5 * Upd readme 2015-07-01 15:39:38 +02:00
Matthew Honnibal
a96f1c26a3 * Upd readme 2015-07-01 15:38:55 +02:00
Matthew Honnibal
2f46015c34 Merge branch 'master' of ssh://github.com/honnibal/spaCy 2015-07-01 15:37:11 +02:00
Matthew Honnibal
17792bb4e3 * Announce v0.87 in docs 2015-07-01 15:36:41 +02:00
Matthew Honnibal
d8ef2d6b61 * Upd README.md 2015-07-01 15:27:37 +02:00
Matthew Honnibal
90e2059200 * Include spacy.munge in the built library 2015-06-30 18:35:39 +02:00
Matthew Honnibal
9af86b0b0b * Fix attrs.pxd 2015-06-30 18:16:30 +02:00
Matthew Honnibal
94dab94e5f uerge branch 'master' of https://github.com/honnibal/spaCy 2015-06-30 18:16:26 +02:00
Matthew Honnibal
af9c82f7a6 Merge branch 'master' of https://github.com/honnibal/spaCy 2015-06-30 18:11:37 +02:00
Matthew Honnibal
5d595b5a8c * Inc versions 2015-06-30 18:11:06 +02:00
Matthew Honnibal
d2eeba6667 * Start wiring up color and emotion lexicons. Hopefully we get to use them. 2015-06-30 16:22:23 +02:00
Matthew Honnibal
341cd0c99f * Require thinc==3.2 2015-06-30 14:27:11 +02:00
Matthew Honnibal
31b5e58aeb * Begin reorganizing neuralnet work 2015-06-30 14:26:53 +02:00
Matthew Honnibal
e20106fdff * Begin reorganizing neuralnet work 2015-06-30 14:26:32 +02:00
Matthew Honnibal
1135cfe50a * Tidy nn_train a bit 2015-06-29 16:45:14 +02:00
Matthew Honnibal
5cd3ed42d4 * Reenable averaging 2015-06-29 16:44:42 +02:00
Matthew Honnibal
df8179ca4f * Add separate Param and AdadeltaParam classes. AdadeltaParam seems broken. 2015-06-29 16:39:16 +02:00
Matthew Honnibal
1dff04acb5 * Apply regularization to the softmax, not the bias 2015-06-29 11:45:38 +02:00
Matthew Honnibal
ca30fe1582 * Use He initialization trick 2015-06-29 10:56:02 +02:00
Matthew Honnibal
894cbef8ba * Wire eta and mu parameters up for neural net 2015-06-29 07:10:33 +02:00
Matthew Honnibal
fc34e1b6e4 * Move Theano functions into nn_train.py script 2015-06-29 07:09:16 +02:00
Matthew Honnibal
8e7ffd2cdd * Use thinc 3.1 2015-06-29 02:13:23 +02:00
Matthew Honnibal
3bb5876c5a * Inline methods in StateClass 2015-06-29 01:10:14 +02:00
Matthew Honnibal
313a7f87b3 * Inline methods in StateClass 2015-06-29 01:06:28 +02:00
Matthew Honnibal
a02fd3af5d * Check valency in L and R feature methods, to make feaure calculation faster 2015-06-29 00:27:56 +02:00
Matthew Honnibal
5d870720bc * Check valency in L and R feature methods, to make feaure calculation faster 2015-06-29 00:17:29 +02:00
Matthew Honnibal
f4986d5d3c * Use new Example class 2015-06-28 22:36:03 +02:00
Matthew Honnibal
735f1af91f * Fix neural net stuff 2015-06-28 11:44:58 +02:00