Matthew Honnibal
cd5ecedf6a
Try drop_layer in parser
2017-08-12 08:56:33 -05:00
Matthew Honnibal
8870d491f1
Remove redundant pickling during training
2017-08-12 08:55:53 -05:00
Matthew Honnibal
680043ebca
Improve efficiency of tagger.set_annotations for GPU
2017-08-12 08:54:21 -05:00
Matthew Honnibal
ebe0f7f641
Pass embed size correctly in tagger, and cache embeddings for efficiency
2017-08-12 05:45:20 -05:00
Matthew Honnibal
1a59db1c86
Fix dropout and learn rate in parser
2017-08-12 05:44:39 -05:00
Ines Montani
b40bc20b12
Merge pull request #1252 from nkruglikov/patch-1
...
Fix small typo in documentation
2017-08-10 12:11:31 +02:00
Nikolai Kruglikov
d42a03b8de
Fix small typo in documentation
2017-08-10 14:38:30 +05:00
Matthew Honnibal
d01dc3704a
Adjust parser model
2017-08-09 20:06:33 -05:00
Matthew Honnibal
f37528ef58
Pass embed size for parser fine-tune. Use SELU
2017-08-09 17:52:53 -05:00
Matthew Honnibal
f93f2bed58
Revert use of layer normalization in Tok2Vec
2017-08-09 17:47:03 -05:00
Matthew Honnibal
20944dd8aa
Fix conflict in parser fine-tuning
2017-08-09 16:43:05 -05:00
Matthew Honnibal
ac2de6dced
Switch to ReLu layers in Tok2Vec
2017-08-09 16:41:25 -05:00
Matthew Honnibal
bbace204be
Gate parser fine-tuning behind feature flag
2017-08-09 16:40:42 -05:00
Matthew Honnibal
a59a1deac4
Merge branch 'develop' of https://github.com/explosion/spaCy into develop
2017-08-09 16:23:19 -05:00
Matthew Honnibal
bcce6f7de0
Fix parser fine tuning
2017-08-09 16:23:12 -05:00
ines
495e042429
Add entry point-style auto alias for "spacy"
...
Simplest way to run commands as spacy xxx instead of python -m spacy
xxx, while avoiding environment conflicts
2017-08-09 12:17:30 +02:00
ines
764540a6dd
Don't ignore /bin directory
2017-08-09 12:16:30 +02:00
ines
28e2fec23b
Fix autolinking failure on fresh model install ( resolves #1138 )
...
On fresh install via subprocess, pip.get_installed_distributions()
won't show new model, so is_package check in link command fails.
Solution for now is to get model package path explicitly and pass it to
link command.
2017-08-09 11:52:38 +02:00
Jim Geovedi
c62b49b7cc
Merge remote-tracking branch 'upstream/develop' into indonesian
2017-08-09 09:17:46 +07:00
Matthew Honnibal
dbdd8afc4b
Fix parser fine-tune training
2017-08-08 15:46:07 -05:00
Matthew Honnibal
88bf1cf87c
Update parser for fine tuning
2017-08-08 15:34:17 -05:00
Matthew Honnibal
5d837c3776
Add mix weights on fine_tune
2017-08-07 06:32:59 -05:00
Matthew Honnibal
42bd26f6f3
Give parser its own tok2vec weights
2017-08-06 18:33:46 +02:00
Matthew Honnibal
3ed203de25
Use LayerNorm and SELU in Tok2Vec
2017-08-06 18:33:18 +02:00
Matthew Honnibal
78498a072d
Return Transition for missing actions in lookup_action
2017-08-06 14:16:36 +02:00
Matthew Honnibal
4a5cc89138
Fix tagger 'fine_tune', to keep private CNN weights
2017-08-06 14:15:48 +02:00
Matthew Honnibal
3cb8f06881
Fix NeuralLabeller
2017-08-06 14:15:14 +02:00
Matthew Honnibal
0acce0521b
Fix Language.update for pipeline
2017-08-06 14:13:03 +02:00
Matthew Honnibal
bfffdeabb2
Fix parser batch-size bug introduced during cleanup
2017-08-06 14:10:48 +02:00
Matthew Honnibal
0eec7c9e9b
Fix Language.evaluate
2017-08-06 02:18:31 +02:00
Matthew Honnibal
0a566dc320
Add update_tensors flag to Language.update. Experimental, re #1182
2017-08-06 02:18:12 +02:00
Matthew Honnibal
cc19ea0e7c
Add update_tensors flag to Language.update. Experimental, re #1182
2017-08-06 02:17:10 +02:00
Matthew Honnibal
4cfb7a54e7
Fix tagger
2017-08-06 01:53:31 +02:00
Matthew Honnibal
e9ab800e15
Fix tagging model
2017-08-06 01:50:08 +02:00
Matthew Honnibal
468c138ab3
WIP: Add fine-tuning logic to tagger model, re #1182
2017-08-06 01:13:23 +02:00
Matthew Honnibal
7f876a7a82
Clean up some unused code in parser
2017-08-06 00:00:21 +02:00
Matthew Honnibal
ae1ad81069
Increment version
2017-08-05 18:09:32 +02:00
Jim Geovedi
cc4772cac2
reworks
2017-08-03 13:08:38 +07:00
Jim Geovedi
37f19f5ed2
added more currencies based on corpus data
2017-08-03 13:03:25 +07:00
Jim Geovedi
30fd068d42
hashtag prefix should be handled somewhere else
2017-08-03 13:03:02 +07:00
Jim Geovedi
4705ae19ba
Merge remote-tracking branch 'upstream/develop' into indonesian
2017-08-03 12:40:19 +07:00
Jim Geovedi
ba07e23c87
added USD in currency rules
2017-08-02 22:42:47 +07:00
Matthew Honnibal
5c323daa1a
Merge branch 'develop' of https://github.com/explosion/spaCy into develop
2017-08-01 22:10:37 +02:00
Matthew Honnibal
2e00361522
Fix update when 0 docs
2017-08-01 22:10:17 +02:00
Matthew Honnibal
8fce187de4
Fix ArcEager for missing values
2017-08-01 22:10:05 +02:00
ines
78e262140f
Add workaround for displaCy server on Python 2/3 ( resolves #1227 )
...
Make sure status and headers are bytes on Python 2 and strings on
Python 3
2017-08-01 01:11:35 +02:00
Jim Geovedi
2572a9ddf0
Merge remote-tracking branch 'upstream/develop' into indonesian
2017-07-30 21:24:16 +07:00
Jim Geovedi
bb08d696f9
added hashtag rule and fixed currency rules
2017-07-30 21:23:28 +07:00
Jim Geovedi
e9af79a803
added u-\d+ rules (sports team)
2017-07-30 21:23:01 +07:00
Matthew Honnibal
c16ef0a85c
Clarify train textcat example
2017-07-29 21:59:27 +02:00