Matthew Honnibal 2bfe184692 Fiddle with nll loss in parser		2016-09-04 16:56:47 +02:00
..
__init__.pxd	* Work on greedy parser	2014-12-16 22:46:55 +11:00
__init__.py	* Work on greedy parser	2014-12-16 22:46:55 +11:00
_neural.pxd	Fix set_features on _neural	2016-08-29 14:26:07 +02:00
_neural.pyx	Fiddle with nll loss in parser	2016-09-04 16:56:47 +02:00
_parse_features.pxd	* Add a parse_batch method to Parser, that releases the GIL around a batch of documents.	2016-02-01 08:34:55 +01:00
_parse_features.pyx	Working NN, but very messy. Relies on BLIS.	2016-07-20 16:28:02 +02:00
_state.pxd	Working NN, but very messy. Relies on BLIS.	2016-07-20 16:28:02 +02:00
_state.pyx	* Continue proxying. Some problem currently	2016-02-01 02:22:21 +01:00
arc_eager.pxd	* Update for thinc 5.0, including changing cost from int to weight_t, and updating the tagger and parser	2016-01-30 14:31:36 +01:00
arc_eager.pyx	* 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
beam_parser.pyx	Update beam_parser	2016-08-29 14:24:14 +02:00
iterators.pxd	* Refactor noun chunk iterators, so that they're simple functions. Install the iterator when the Doc is created, but allow users to write to the noun_chunk_iterator attribute. The iterator functions accept an object and yield (int start, int end, int label) triples.	2016-05-02 14:25:10 +02:00
iterators.pyx	Working NN, but very messy. Relies on BLIS.	2016-07-20 16:28:02 +02:00
ner.pxd	* Remove import of _state module	2015-06-23 17:25:08 +02:00
ner.pyx	* Pass a StateC pointer into the transition and validation methods in the parser, so that the GIL can be released over a batch of documents	2016-02-01 02:58:14 +01:00
nonproj.pxd	integrated pseudo-projective parsing into parser	2016-03-01 10:09:08 +01:00
nonproj.pyx	* Deprojectivize German parses	2016-05-05 15:01:10 +02:00
parser.pxd	Tmp	2016-07-27 02:56:36 +02:00
parser.pyx	Fiddle with nll loss in parser	2016-09-04 16:56:47 +02:00
stateclass.pxd	* Now fully proxied	2016-02-01 02:37:08 +01:00
stateclass.pyx	different handling of space tokens	2016-04-13 15:28:28 +02:00
transition_system.pxd	* Add a parse_batch method to Parser, that releases the GIL around a batch of documents.	2016-02-01 08:34:55 +01:00
transition_system.pyx	* Refactor noun chunk iterators, so that they're simple functions. Install the iterator when the Doc is created, but allow users to write to the noun_chunk_iterator attribute. The iterator functions accept an object and yield (int start, int end, int label) triples.	2016-05-02 14:25:10 +02:00
util.py	* Add get() function in spacy/syntax/Config	2015-06-07 19:09:15 +02:00