explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-15 06:09:01 +03:00
Code Issues Packages Projects Releases Wiki Activity
1,390 Commits 68 Branches 175 Tags 279 MiB
2fbcdd0ea8
Commit Graph

1390 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Matthew Honnibal
2fbcdd0ea8 * Refactor sense tagger to get rid of intermediary layers 2015-07-03 13:31:11 +02:00
Matthew Honnibal
6735439abf * Fix the way supersenses are loaded from the json file 2015-07-03 13:29:22 +02:00
Matthew Honnibal
ff1f9fe246 * Fix init_model to read supersenses from wordnet, not pre-computed supersenses file 2015-07-03 13:28:39 +02:00
Matthew Honnibal
b977d60bf4 * Hack in WSD scoring 2015-07-03 09:25:52 +02:00
Matthew Honnibal
68f174b235 * Remove adjectives from supersense list. This seems to be associated with current memory errors 2015-07-03 09:24:45 +02:00
Matthew Honnibal
12dd4f745a * Add validation for argmaxing in _ml.pyx 2015-07-03 09:18:33 +02:00
Matthew Honnibal
5d933eec8e * Use the gold sense labels for training 2015-07-03 05:45:42 +02:00
Matthew Honnibal
4a60b68a24 * Add encode_sense_strs function 2015-07-03 05:45:16 +02:00
Matthew Honnibal
1be5ab200f * Add some of the sensetagger changes 2015-07-03 05:18:15 +02:00
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