Commit Graph

1614 Commits

Author SHA1 Message Date
Matthew Honnibal
a664aa8180 Fix beam_parser for new API 2016-07-31 19:03:10 +02:00
Matthew Honnibal
2f09b041d1 Reset is_valid and costs during beam training 2016-07-31 19:02:45 +02:00
Matthew Honnibal
3e46b491b9 Update call to beam_parser for new thinc API 2016-07-31 11:43:23 +02:00
Matthew Honnibal
86862f3586 Update parser.pyx for new thinc API 2016-07-31 11:43:04 +02:00
Matthew Honnibal
ff36cd43df Fix call to updateC 2016-07-31 11:42:44 +02:00
Matthew Honnibal
5869f05bd6 Update tagger for new thinc API 2016-07-31 11:41:48 +02:00
Matthew Honnibal
25513b8389 Remove use of ExampleC from beam parser 2016-07-29 19:58:49 +02:00
Matthew Honnibal
6b912731f8 Refactor model for beam parser, to avoid conditionals on model type 2016-07-29 19:33:01 +02:00
Matthew Honnibal
2dda2ecdbd Merge branch 'master' of ssh://github.com/spacy-io/spaCy into july16 2016-07-27 03:15:36 +02:00
Matthew Honnibal
eb8234181c Tmp 2016-07-27 02:56:50 +02:00
Matthew Honnibal
ac63274e15 Tmp 2016-07-27 02:56:36 +02:00
Matthew Honnibal
6a98a3142f More work on beam parser. 2016-07-26 19:13:39 +02:00
Matthew Honnibal
1ee6b468a9 * Adjust arc_eager oracle, so that recovering errors via non-monotonic actions gives negative cost. Need to test this with greedy parser. 2016-07-26 19:12:00 +02:00
Matthew Honnibal
0bf448461e Work on beam parser, with max violation 2016-07-24 14:26:52 +02:00
Matthew Honnibal
a1281835a8 Clean up commented out code from beam parser. 2016-07-24 11:02:39 +02:00
Matthew Honnibal
476977ef62 Start work on max violation update. About to clean up commented out code. 2016-07-24 11:01:54 +02:00
Matthew Honnibal
8b4abc24e3 Fix beam parsing. Starting to work with early update. 2016-07-24 10:45:50 +02:00
Matthew Honnibal
27176c3d2f Fix beam parser. Starting to work 2016-07-24 01:14:56 +02:00
Matthew Honnibal
e2a9a68b66 * Work on beam parser 2016-07-23 06:07:09 +02:00
Matthew Honnibal
de7c6c48d8 Working NN, but very messy. Relies on BLIS. 2016-07-20 16:28:02 +02:00
Adam Ever Hadani
f1c0762443 exit code 0 for when downloading a model that already was downloaded 2016-07-13 16:22:14 -07:00
Matthew Honnibal
7c2f1a673b * Working neural net, but features hacky. Switching to extractor. 2016-05-26 19:06:10 +02:00
Matthew Honnibal
cdc10e9a1c * Fix Issue #375: noun phrase iteration results in index error if noun phrases are merged during the loop. Fix by accumulating the spans inside the noun_chunks property, allowing the Span index tricks to work. 2016-05-20 10:14:06 +02:00
Matthew Honnibal
13fad36e49 * Cosmetic change to english noun chunks iterator -- use enumerate instead of range loop 2016-05-20 10:11:05 +02:00
Matthew Honnibal
02276cc444 Merge branch 'master' of ssh://github.com/spacy-io/spaCy 2016-05-17 16:56:22 +02:00
Matthew Honnibal
4d7f5468bb * Change Language class to use a .pipeline attribute, instead of having the pipeline hard coded 2016-05-17 16:55:42 +02:00
Daylen Yang
5405e7dd73 Fix get_lang_class parsing (take 2) 2016-05-16 16:40:31 -07:00
Matthew Honnibal
b240104f40 Revert "Fix get_lang_class parsing" 2016-05-17 08:04:26 +10:00
Daylen Yang
1692c2df3c Fix get_lang_class parsing
We want the get_lang_class to return "en" for both "en" and "en_glove_cc_300_1m_vectors". Changed the split rule to "_" so that this happens.
2016-05-16 14:38:20 -07:00
Matthew Honnibal
17137f5c0c * Fix issue #372: mistake in Lexeme rich comparison 2016-05-12 12:58:57 +02:00
Matthew Honnibal
cc8bf62208 * Fix Issue #360: Tokenizer failed when the infix regex matched the start of the string while trying to tokenize multi-infix tokens. 2016-05-09 13:23:47 +02:00
Matthew Honnibal
c61ee8f9fa * Increment version 2016-05-09 13:20:00 +02:00
Matthew Honnibal
5d86c30f0b * Fix Issue #367: Missing has_vector property on Doc and Span objects 2016-05-09 12:36:14 +02:00
Wolfgang Seeker
7b78239436 add fix for German noun chunk iterator (issue #365) 2016-05-06 01:41:26 +02:00
Matthew Honnibal
8c0888d6cb * Fix error in span.sent 2016-05-06 00:28:05 +02:00
Matthew Honnibal
bb94022975 * Fix Issue #365: Error introduced during noun phrase chunking, due to use of corrected PRON/PROPN/etc tags. 2016-05-06 00:21:05 +02:00
Matthew Honnibal
41342ca79b Merge branch 'master' of ssh://github.com/spacy-io/spaCy 2016-05-06 00:17:58 +02:00
Matthew Honnibal
26095f9722 * Add span.sent property, re Issue #366 2016-05-06 00:17:38 +02:00
Wolfgang Seeker
dbf8f5f3ec fix bug in StateC.set_break() 2016-05-05 15:15:34 +02:00
Wolfgang Seeker
3c44b5dc1a call deprojectivization after parsing 2016-05-05 15:10:36 +02:00
Matthew Honnibal
472f576b82 * Deprojectivize German parses 2016-05-05 15:01:10 +02:00
Matthew Honnibal
9bbd6cf031 * Work on Chinese support 2016-05-05 11:39:12 +02:00
Matthew Honnibal
a6a25166ba * Remove print from test 2016-05-05 11:10:59 +02:00
Matthew Honnibal
e31df66d26 * Fix Issue #361: Lexemes didn't have rich comparison. 2016-05-05 01:32:26 +02:00
Matthew Honnibal
7441ca30ee * Add tests for Issue #361: Lexeme rich comparison 2016-05-05 01:31:58 +02:00
Matthew Honnibal
72564213e3 * Add test for Issue #309 2016-05-04 16:00:28 +02:00
Matthew Honnibal
76f1d871da Merge branch 'master' of ssh://github.com/spacy-io/spaCy 2016-05-04 15:54:00 +02:00
Matthew Honnibal
519366f677 * Fix Issue #351: Indices off when leading whitespace 2016-05-04 15:53:36 +02:00
Matthew Honnibal
b4bfc6ae55 * Add test for Issue #351: Indices off when leading whitespace 2016-05-04 15:53:17 +02:00
Matthew Honnibal
76021cb853 * Fix bug in Doc.text, introduced by a862edc 2016-05-04 11:02:16 +02:00