Commit Graph

216 Commits

Author SHA1 Message Date
ines
4eabaafd66 Update docstring and example 2017-10-27 01:50:44 +02:00
ines
ed69bd69f4 Update parallel tagging example 2017-10-27 01:48:52 +02:00
ines
096a80170d Remove old example files 2017-10-27 01:48:39 +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
b7b285971f Update examples README 2017-10-26 18:47:11 +02:00
ines
cc2917c9e8 Update fastText example and add to examples in docs 2017-10-26 18:47:02 +02:00
ines
db843735d3 Remove outdated examples 2017-10-26 18:46:25 +02:00
ines
daed7ff8fe Update information extraction examples 2017-10-26 18:46:11 +02:00
ines
bca5372fb1 Clean up examples 2017-10-26 17:32:59 +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
ines
f4ae6763b9 Fix consistency of imports from spacy.tokens in examples 2017-10-11 02:30:40 +02:00
Matthew Honnibal
e0a9b02b67 Merge Span._ and Span.as_doc methods 2017-10-09 22:00:15 -05:00
ines
6679117000 Add pipeline component examples 2017-10-10 04:26:06 +02:00
Matthew Honnibal
e79fc41ff8 Merge pull request #1391 from explosion/feature/multilabel-textcat
💫 Fix multi-label support for text classification
2017-10-09 04:22:31 +02:00
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
056b08c0df Delete obsolete nn_text_class example 2017-10-05 18:27:10 +02:00
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
Matthew Honnibal
cbb1fbef80 Update train_ner_standalone example 2017-10-03 18:49:38 +02:00
Matthew Honnibal
38286b6f07 Add example loadig Fast Text vectors 2017-10-01 23:40:02 +02:00
Matthew Honnibal
f92ab03dc8 Rename phrase matcher example 2017-09-20 22:51:58 +02:00
Matthew Honnibal
01858e9b59 Fix PhraseMatcher example 2017-09-20 22:51:41 +02:00
Matthew Honnibal
027a5d8b75 Update train_ner_standalone example 2017-09-15 10:36:46 +02:00
Matthew Honnibal
683d81bb49 Update example for adding entity type 2017-09-14 16:15:59 +02:00
Matthew Honnibal
c16ef0a85c Clarify train textcat example 2017-07-29 21:59:27 +02:00
Matthew Honnibal
54a539a113 Finish text classifier example 2017-07-23 00:34:12 +02:00
Matthew Honnibal
2bc7d87c70 Add example for training text classifier 2017-07-22 20:15:32 +02:00
ines
992559bf9a Fix formatting and remove unused imports 2017-06-01 12:47:18 +02:00
Matthew Honnibal
5c30466c95 Update NER training example 2017-05-31 13:42:12 +02:00
akYoung
c158cdb1da Corretions for model test example
The sentences of test data in sentence entailment example should be generated with integers limited to vocab_size.
2017-05-03 22:41:23 +08:00
Matthew Honnibal
2da16adcc2 Add dropout optin for parser and NER
Dropout can now be specified in the `Parser.update()` method via
the `drop` keyword argument, e.g.

    nlp.entity.update(doc, gold, drop=0.4)

This will randomly drop 40% of features, and multiply the value of the
others by 1. / 0.4. This may be useful for generalising from small data
sets.

This commit also patches the examples/training/train_new_entity_type.py
example, to use dropout and fix the output (previously it did not output
the learned entity).
2017-04-27 13:18:39 +02:00
Matthew Honnibal
0605b95f2e Merge branch 'master' of https://github.com/explosion/spaCy 2017-04-18 13:48:00 +02:00
Matthew Honnibal
2f84626417 Fix train_new_entity_type example 2017-04-18 13:47:36 +02:00
Ines Montani
e7ae3b7cc2 Fix formatting and typo (closes #967) 2017-04-16 23:56:12 +02:00
Ines Montani
734b0a4e4a Update train_new_entity_type.py 2017-04-16 23:42:16 +02:00
ines
264af6cd17 Add documentation 2017-04-16 20:37:46 +02:00
ines
c7adca58a9 Tidy up example and only save/test if output_directory is not None 2017-04-16 16:55:01 +02:00
Matthew Honnibal
40e3024241 Move standalone NER training script into examples directory 2017-04-15 16:13:42 +02:00
Matthew Honnibal
b9c26aae11 Remove neptune refs from new train example 2017-04-15 16:13:17 +02:00
Matthew Honnibal
c729d72fc6 Add new example for training new entity types 2017-04-15 16:11:06 +02:00
Matthew Honnibal
a7626bd7fd Tmp commit to example 2017-04-15 15:43:14 +02:00
Matthew Honnibal
97b83c74dc WIP on training example 2017-04-14 23:54:27 +02:00
Kumaran Rajendhiran
3f55d6afae Update README 2017-04-05 16:59:52 +05:30
Kumaran Rajendhiran
47d7137c83 Set max_length to 100 for demo and evaluate 2017-04-05 16:48:35 +05:30
Kumaran Rajendhiran
10e8dcdfdb Remove not needed parameters from function 2017-04-05 16:20:47 +05:30
Matthew Honnibal
07726cf0a6 Add example of standalone NER training 2017-03-19 15:01:38 +01:00
Matthew Honnibal
f028f8ad28 Remove unfinished examples 2017-02-18 11:04:41 +01:00
Matthew Honnibal
c031c677cc Remove unused model_dir option
As noted in #845, the `model_dir` argument was not being used. I've removed it for now, although it would be good to have this option restored and working.
2017-02-18 10:38:22 +01:00
Matthew Honnibal
16ce7409e4 Merge branch 'master' of https://github.com/explosion/spaCy 2017-01-31 13:27:34 -06:00
Matthew Honnibal
80aa4e114b Fix x keras deep learning example 2017-01-31 13:27:13 -06:00
Matthew Honnibal
ab70f6e18d Update NER training example 2017-01-27 12:27:10 +01:00
Ines Montani
853130bcf8 Update installation instructions (see #727) 2017-01-14 22:12:42 +01:00
Matthew Honnibal
5a319060b9 Merge branch 'master' of https://github.com/explosion/spaCy 2016-12-20 16:26:57 -06:00
Matthew Honnibal
7793e2ad82 Fix use of dropout in sentiment analysis LSTM example 2016-12-20 16:26:38 -06:00
Christos Savvopoulos
c19b83f6ae use model_dir inside of load_model 2016-12-12 20:23:24 +00:00
Christos Savvopoulos
93cf4af701 actually commit load_ner.py 2016-12-12 20:13:33 +00:00
Christos Savvopoulos
ad54a929f8 train_ner should save vocab; add load_ner example 2016-12-12 20:09:49 +00:00
Matthew Honnibal
d0c999e0ad Add config.py for paddle example 2016-11-20 23:24:51 +01:00
Matthew Honnibal
d75fe7c19a Update paddle example 2016-11-20 21:45:08 +01:00
Matthew Honnibal
1ef541ddff Add train.sh for paddle 2016-11-20 21:44:33 +01:00
Matthew Honnibal
001abe2b9d Update config.py 2016-11-20 03:45:51 +01:00
Matthew Honnibal
409a18bd42 Add paddle sentiment example 2016-11-20 03:35:23 +01:00
Matthew Honnibal
e7eac08819 Work on paddle example 2016-11-20 03:29:36 +01:00
Matthew Honnibal
1ed40682a3 Set vectors in chainer example 2016-11-19 18:42:58 -06:00
Matthew Honnibal
b701a08249 Fix embedding in chainer sentiment example 2016-11-19 19:05:37 +01:00
Matthew Honnibal
8a2de46fcb Fix GPU usage in chainer example 2016-11-19 10:58:00 -06:00
Matthew Honnibal
4c84aae571 Merge branch 'master' of https://github.com/explosion/spaCy 2016-11-19 02:41:17 -06:00
Matthew Honnibal
3195c52741 Add WIP Chainer sentiment analysis code. 2016-11-19 09:27:59 +01:00
Matthew Honnibal
ff5ab75f5e Add partial embedding updates to Parikh model, fix dropout, other corrections. 2016-11-18 06:32:12 -06:00
Matthew Honnibal
718e66a7b9 Minibatch the forward pass. THe output argmax is incorrect... 2016-11-16 06:15:28 -06:00
Matthew Honnibal
8f053fd943 Add flag to toggle GPU to DyNet code 2016-11-16 05:51:00 -06:00
Matthew Honnibal
3a31c3a961 Merge branch 'master' of https://github.com/explosion/spaCy 2016-11-16 05:49:42 -06:00
Kyle P. Johnson
d105771a07 Add setup directions for data dir
This script's data needs are not intuitive. I have added a note explaining that (a) it expects pos/neg polarity data, (b) the structure of the data dir (train/test), and (c) a standard resource for such polarity data.
2016-11-13 10:08:16 -08:00
Kyle P. Johnson
c8d3694e2d Ch lex.repvec to lex.vector
For preventing the AttributeError: `File "spacy/lexeme.pyx", line 159, in spacy.lexeme.Lexeme.repvec.__get__ (spacy/lexeme.cpp:5016)
AttributeError: lex.repvec has been renamed to lex.vector`
2016-11-13 09:54:42 -08:00
Matthew Honnibal
389e8b700e Fix conflict 2016-11-13 08:52:20 -06:00
Matthew Honnibal
12a7b05360 Merge branch 'master' of https://github.com/explosion/spaCy 2016-11-13 08:49:07 -06:00
Matthew Honnibal
ef76c28d70 Update dynet example to use minibatching 2016-11-13 08:48:43 -06:00
Matthew Honnibal
fb8acc1dfb Merge pull request #628 from chenb67/master
Remove theano dependency from parikh model + small bug fix
2016-11-14 01:28:22 +11:00