explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-09-22 20:09:18 +03:00
Code Issues Packages Projects Releases Wiki Activity
7,836 Commits 66 Branches 174 Tags 277 MiB
3696ce6a7b
Commit Graph

81 Commits

Author SHA1 Message Date
ines
726fb2d0b5 Use fewer iterations by default to avoid overfitting on blank model (resolves #1632) 2017-11-23 15:27:12 +01:00
ines
ec08996000 Add note on tags matching tokenization (see #1613) 2017-11-20 15:12:47 +01:00
ines
f36fab39b0 Don't rename component in intent parser example (resolves #1551) 
Otherwise, the default saved model won't know that it's supposed to create spaCy's 'parser'.
 2017-11-10 23:35:38 +01:00
Ines Montani
1a23a0f87e
Remove broken link (resolves #1541) 2017-11-10 12:28:39 +01:00
ines
89bd40b821 Fix print statement in textcat training example (resolves #1515) 2017-11-08 17:17:40 +01:00
ines
a09c096d3c Get docs ready for v2.0.0 2017-11-07 12:00:43 +01:00
ines
173b1551af Update examples 2017-11-07 01:22:30 +01:00
ines
1b1c9105b4 Update example compatibility statements 2017-11-07 01:11:45 +01:00
ines
8fb48b9b91 Update and document new util functions 2017-11-07 00:22:43 +01:00
Matthew Honnibal
d7016d4050 Update intent parser example 2017-11-06 23:31:11 +01:00
ines
fe498b3d5e Update training examples to use "simple style" 2017-11-06 23:14:04 +01:00
ines
2dca9e71a1 Add notes on catastrophic forgetting (see #1496) 2017-11-06 13:17:02 +01:00
Matthew Honnibal
e033162a1d Update tagger training example 2017-11-01 21:49:08 +01:00
ines
8f1d3fc3ee Update textcat example 2017-11-01 17:09:22 +01:00
Matthew Honnibal
dad8f09fba Fix print statements in text classifier example 2017-11-01 16:34:31 +01:00
ines
bfe17b7df1 Fix begin_training if get_gold_tuples is None 2017-11-01 13:14:31 +01:00
ines
4b196fdf7f Fix formatting 2017-11-01 00:43:22 +01:00
ines
33af6ac69a Use even smaller examle size 
100 was still too much, so try 20 instead
 2017-10-30 19:46:45 +01:00
ines
f02b0af821 Fix path and use smaller example size 
500 was too larger and caused laggy rendering
 2017-10-30 19:44:35 +01:00
ines
18dde7869a Update training data docs and add vocab JSONL 2017-10-30 19:40:05 +01:00
ines
b5643d8575 Update intent parser docs and add to usage docs 2017-10-27 04:49:05 +02:00
ines
9dfca0f2f8 Add example for custom intent parser 2017-10-27 03:55:11 +02:00
ines
4d272e25ee Fix examples 2017-10-27 03:55:04 +02:00
ines
a7b9074b4c Update textcat training example and docs 2017-10-27 00:48:45 +02:00
ines
b61866a2e4 Update textcat example 2017-10-27 00:32:19 +02:00
ines
f81cc0bd1c Fix usage of disable_pipes 2017-10-27 00:31:30 +02:00
ines
f57043e6fe Update docstring 2017-10-26 16:29:08 +02:00
ines
b90e958975 Update tagger and parser examples and add to docs 2017-10-26 16:27:42 +02:00
ines
f1529463a8 Update tagger training example 2017-10-26 16:19:02 +02:00
ines
e44bbb5361 Remove old example 2017-10-26 16:12:41 +02:00
ines
421c3837e8 Fix formatting 2017-10-26 16:11:25 +02:00
ines
4d896171ae Use plac annotations for arguments 2017-10-26 16:11:20 +02:00
ines
c3b681e5fb Use plac annotations for arguments and add n_iter 2017-10-26 16:11:05 +02:00
ines
bc2c92f22d Use plac annotations for arguments 2017-10-26 16:10:56 +02:00
ines
b5c74dbb34 Update parser training example 2017-10-26 15:15:37 +02:00
ines
586b9047fd Use create_pipe instead of importing the entity recognizer 2017-10-26 15:15:26 +02:00
ines
d425ede7e9 Fix example 2017-10-26 15:15:08 +02:00
ines
9d58673aaf Update train_ner example for spaCy v2.0 2017-10-26 14:24:12 +02:00
ines
e904075f35 Remove stray print statements 2017-10-26 14:24:00 +02:00
ines
c30258c3a2 Remove old example 2017-10-26 14:23:52 +02:00
ines
615c315d70 Update train_new_entity_type example to use disable_pipes 2017-10-25 14:56:53 +02:00
ines
2b8e7c45e0 Use better training data JSON example 2017-10-24 16:00:56 +02:00
ines
9bf5751064 Pretty-print JSON 2017-10-24 12:22:17 +02:00
ines
6675755005 Add training data JSON example 2017-10-24 12:05:10 +02:00
Jeroen Bobbeldijk
84c6c20d1c Fix #1444: fix pipeline logic and wrong paramater in update call 2017-10-22 15:18:36 +02:00
Jeffrey Gerard
5ba970b495 minor cleanup 2017-10-12 12:34:46 -07:00
Jeffrey Gerard
39d3cbfdba Bugfix example script train_ner_standalone.py, fails after training 2017-10-12 11:39:12 -07:00
Matthew Honnibal
563f46f026 Fix multi-label support for text classification 
The TextCategorizer class is supposed to support multi-label
text classification, and allow training data to contain missing
values.

For this to work, the gradient of the loss should be 0 when labels
are missing. Instead, there was no way to actually denote "missing"
in the GoldParse class, and so the TextCategorizer class treated
the label set within gold.cats as complete.

To fix this, we change GoldParse.cats to be a dict instead of a list.
The GoldParse.cats dict should map to floats, with 1. denoting
'present' and 0. denoting 'absent'. Gradients are zeroed for categories
absent from the gold.cats dict. A nice bonus is that you can also set
values between 0 and 1 for partial membership. You can also set numeric
values, if you're using a text classification model that uses an
appropriate loss function.

Unfortunately this is a breaking change; although the functionality
was only recently introduced and hasn't been properly documented
yet. I've updated the example script accordingly.
 2017-10-05 18:43:02 -05:00
Matthew Honnibal
f1b86dff8c Update textcat example 2017-10-04 15:12:28 +02:00
Matthew Honnibal
79a94bc166 Update textcat exampe 2017-10-04 14:55:30 +02:00