Matthew Honnibal
1b5fa68996
Do pseudo-projective pre-processing for parser
2017-05-22 04:51:08 -05:00
Matthew Honnibal
1d5d9838a2
Fix action collection for parser
2017-05-22 04:51:08 -05:00
Matthew Honnibal
3b7c108246
Pass tokvecs through as a list, instead of concatenated. Also fix padding
2017-05-20 13:23:32 -05:00
Matthew Honnibal
d52b65aec2
Revert "Move to contiguous buffer for token_ids and d_vectors"
...
This reverts commit 3ff8c35a79
2017-05-20 11:26:23 -05:00
Matthew Honnibal
b272890a8c
Try to move parser to simpler PrecomputedAffine class. Currently broken -- maybe the previous change
2017-05-20 06:40:10 -05:00
Matthew Honnibal
3ff8c35a79
Move to contiguous buffer for token_ids and d_vectors
2017-05-20 04:17:30 -05:00
Matthew Honnibal
8b04b0af9f
Remove freqs from transition_system
2017-05-20 02:20:48 -05:00
Matthew Honnibal
a1ba20e2b1
Fix over-run on parse_batch
2017-05-19 18:57:30 -05:00
Matthew Honnibal
e84de028b5
Remove 'rebatch' op, and remove min-batch cap
2017-05-19 18:16:36 -05:00
Matthew Honnibal
c12ab47a56
Remove state argument in pipeline. Other changes
2017-05-19 13:26:36 -05:00
Matthew Honnibal
c2c825127a
Fix use_params and pipe methods
2017-05-18 08:30:59 -05:00
Matthew Honnibal
fc8d3a112c
Add util.env_opt support: Can set hyper params through environment variables.
2017-05-18 04:36:53 -05:00
Matthew Honnibal
d2626fdb45
Fix name error in nn parser
2017-05-18 04:31:01 -05:00
Matthew Honnibal
793430aa7a
Get spaCy train command working with neural network
...
* Integrate models into pipeline
* Add basic serialization (maybe incorrect)
* Fix pickle on vocab
2017-05-17 12:04:50 +02:00
Matthew Honnibal
8cf097ca88
Redesign training to integrate NN components
...
* Obsolete .parser, .entity etc names in favour of .pipeline
* Components no longer create models on initialization
* Models created by loading method (from_disk(), from_bytes() etc), or
.begin_training()
* Add .predict(), .set_annotations() methods in components
* Pass state through pipeline, to allow components to share information
more flexibly.
2017-05-16 16:17:30 +02:00
Matthew Honnibal
5211645af3
Get data flowing through pipeline. Needs redesign
2017-05-16 11:21:59 +02:00
Matthew Honnibal
a9edb3aa1d
Improve integration of NN parser, to support unified training API
2017-05-15 21:53:27 +02:00
Matthew Honnibal
4b9d69f428
Merge branch 'v2' into develop
...
* Move v2 parser into nn_parser.pyx
* New TokenVectorEncoder class in pipeline.pyx
* New spacy/_ml.py module
Currently the two parsers live side-by-side, until we figure out how to
organize them.
2017-05-14 01:10:23 +02:00
Matthew Honnibal
5cac951a16
Move new parser to nn_parser.pyx, and restore old parser, to make tests pass.
2017-05-14 00:55:01 +02:00
Matthew Honnibal
f8c02b4341
Remove cupy imports from parser, so it can work on CPU
2017-05-14 00:37:53 +02:00
Matthew Honnibal
e6d71e1778
Small fixes to parser
2017-05-13 17:19:04 -05:00
Matthew Honnibal
188c0f6949
Clean up unused import
2017-05-13 17:18:27 -05:00
Matthew Honnibal
f85c8464f7
Draft support of regression loss in parser
2017-05-13 17:17:27 -05:00
Matthew Honnibal
827b5af697
Update draft of parser neural network model
...
Model is good, but code is messy. Currently requires Chainer, which may cause the build to fail on machines without a GPU.
Outline of the model:
We first predict context-sensitive vectors for each word in the input:
(embed_lower | embed_prefix | embed_suffix | embed_shape)
>> Maxout(token_width)
>> convolution ** 4
This convolutional layer is shared between the tagger and the parser. This prevents the parser from needing tag features.
To boost the representation, we make a "super tag" with POS, morphology and dependency label. The tagger predicts this
by adding a softmax layer onto the convolutional layer --- so, we're teaching the convolutional layer to give us a
representation that's one affine transform from this informative lexical information. This is obviously good for the
parser (which backprops to the convolutions too).
The parser model makes a state vector by concatenating the vector representations for its context tokens. Current
results suggest few context tokens works well. Maybe this is a bug.
The current context tokens:
* S0, S1, S2: Top three words on the stack
* B0, B1: First two words of the buffer
* S0L1, S0L2: Leftmost and second leftmost children of S0
* S0R1, S0R2: Rightmost and second rightmost children of S0
* S1L1, S1L2, S1R2, S1R, B0L1, B0L2: Likewise for S1 and B0
This makes the state vector quite long: 13*T, where T is the token vector width (128 is working well). Fortunately,
there's a way to structure the computation to save some expense (and make it more GPU friendly).
The parser typically visits 2*N states for a sentence of length N (although it may visit more, if it back-tracks
with a non-monotonic transition). A naive implementation would require 2*N (B, 13*T) @ (13*T, H) matrix multiplications
for a batch of size B. We can instead perform one (B*N, T) @ (T, 13*H) multiplication, to pre-compute the hidden
weights for each positional feature wrt the words in the batch. (Note that our token vectors come from the CNN
-- so we can't play this trick over the vocabulary. That's how Stanford's NN parser works --- and why its model
is so big.)
This pre-computation strategy allows a nice compromise between GPU-friendliness and implementation simplicity.
The CNN and the wide lower layer are computed on the GPU, and then the precomputed hidden weights are moved
to the CPU, before we start the transition-based parsing process. This makes a lot of things much easier.
We don't have to worry about variable-length batch sizes, and we don't have to implement the dynamic oracle
in CUDA to train.
Currently the parser's loss function is multilabel log loss, as the dynamic oracle allows multiple states to
be 0 cost. This is defined as:
(exp(score) / Z) - (exp(score) / gZ)
Where gZ is the sum of the scores assigned to gold classes. I'm very interested in regressing on the cost directly,
but so far this isn't working well.
Machinery is in place for beam-search, which has been working well for the linear model. Beam search should benefit
greatly from the pre-computation trick.
2017-05-12 16:09:15 -05:00
Matthew Honnibal
b44f7e259c
Clean up unused parser code
2017-05-08 15:42:04 +02:00
Matthew Honnibal
17efb1c001
Change width
2017-05-08 08:40:13 -05:00
Matthew Honnibal
bef89ef23d
Mergery
2017-05-08 08:29:36 -05:00
Matthew Honnibal
50ddc9fc45
Fix infinite loop bug
2017-05-08 07:54:26 -05:00
Matthew Honnibal
a66a4a4d0f
Replace einsums
2017-05-08 14:46:50 +02:00
Matthew Honnibal
8d2eab74da
Use PretrainableMaxouts
2017-05-08 14:24:55 +02:00
Matthew Honnibal
2e2268a442
Precomputable hidden now working
2017-05-08 11:36:37 +02:00
Matthew Honnibal
10682d35ab
Get pre-computed version working
2017-05-08 00:38:35 +02:00
Matthew Honnibal
35458987e8
Checkpoint -- nearly finished reimpl
2017-05-07 23:05:01 +02:00
Matthew Honnibal
4441866f55
Checkpoint -- nearly finished reimpl
2017-05-07 22:47:06 +02:00
Matthew Honnibal
6782eedf9b
Tmp GPU code
2017-05-07 11:04:24 -05:00
Matthew Honnibal
e420e5a809
Tmp
2017-05-07 07:31:09 -05:00
Matthew Honnibal
700979fb3c
CPU/GPU compat
2017-05-07 04:01:11 +02:00
Matthew Honnibal
f99f5b75dc
working residual net
2017-05-07 03:57:26 +02:00
Matthew Honnibal
bdf2dba9fb
WIP on refactor, with hidde pre-computing
2017-05-07 02:02:43 +02:00
Matthew Honnibal
b439e04f8d
Learning smoothly
2017-05-06 20:38:12 +02:00
Matthew Honnibal
08bee76790
Learns things
2017-05-06 18:24:38 +02:00
Matthew Honnibal
bcf4cd0a5f
Learns things
2017-05-06 17:37:36 +02:00
Matthew Honnibal
8e48b58cd6
Gradients look correct
2017-05-06 16:47:15 +02:00
Matthew Honnibal
7e04260d38
Data running through, likely errors in model
2017-05-06 14:22:20 +02:00
Matthew Honnibal
ef4fa594aa
Draft of NN parser, to be tested
2017-05-05 19:20:39 +02:00
Matthew Honnibal
ccaf26206b
Pseudocode for parser
2017-05-04 12:17:59 +02:00
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
d2436dc17b
Update fix for Issue #999
2017-04-23 18:14:37 +02:00
Matthew Honnibal
60703cede5
Ensure noun chunks can't be nested. Closes #955
2017-04-23 17:56:39 +02:00
Matthew Honnibal
4eef200bab
Persist the actions within spacy.parser.cfg
2017-04-20 17:02:44 +02:00
Matthew Honnibal
137b210bcf
Restore use of FTRL training
2017-04-16 18:02:42 +02:00
Matthew Honnibal
45464d065e
Remove print statement
2017-04-15 16:11:43 +02:00
Matthew Honnibal
c76cb8af35
Fix training for new labels
2017-04-15 16:11:26 +02:00
Matthew Honnibal
4884b2c113
Refix StepwiseState
2017-04-15 16:00:28 +02:00
Matthew Honnibal
1a98e48b8e
Fix Stepwisestate'
2017-04-15 13:35:01 +02:00
ines
0739ae7b76
Tidy up and fix formatting and imports
2017-04-15 13:05:15 +02:00
Matthew Honnibal
354458484c
WIP on add_label bug during NER training
...
Currently when a new label is introduced to NER during training,
it causes the labels to be read in in an unexpected order. This
invalidates the model.
2017-04-14 23:52:17 +02:00
Matthew Honnibal
49e2de900e
Add costs property to StepwiseState, to show which moves are gold.
2017-04-10 11:37:04 +02:00
Matthew Honnibal
cc36c308f4
Fix noun_chunk rules around coordination
...
Closes #693 .
2017-04-07 17:06:40 +02:00
Matthew Honnibal
1bb7b4ca71
Add comment
2017-03-31 13:59:19 +02:00
Matthew Honnibal
47a3ef06a6
Unhack deprojetivization, moving it into pipeline
...
Previously the deprojectivize() call was attached to the transition
system, and only called for German. Instead it should be a separate
process, called after the parser. This makes it available for any
language. Closes #898 .
2017-03-31 12:31:50 +02:00
Matthew Honnibal
a9b1f23c7d
Enable regression loss for parser
2017-03-26 09:26:30 -05:00
Matthew Honnibal
b487b8735a
Decrease beam density, and fix Python 3 problem in beam
2017-03-20 12:56:05 +01:00
Matthew Honnibal
c90dc7ac29
Clean up state initiatisation in transition system
2017-03-16 11:59:11 -05:00
Matthew Honnibal
a46933a8fe
Clean up FTRL parsing stuff.
2017-03-16 11:58:20 -05:00
Matthew Honnibal
2611ac2a89
Fix scorer bug for NER, related to ambiguity between missing annotations and misaligned tokens
2017-03-16 09:38:28 -05:00
Matthew Honnibal
3d0833c3df
Fix off-by-1 in parse features fill_context
2017-03-15 19:55:35 -05:00
Matthew Honnibal
4ef68c413f
Approximate cost in Break transition, to speed things up a bit.
2017-03-15 16:40:27 -05:00
Matthew Honnibal
8543db8a5b
Use ftrl optimizer in parser
2017-03-15 11:56:37 -05:00
Matthew Honnibal
d719f8e77e
Use nogil in parser, and set L1 to 0.0 by default
2017-03-15 09:31:01 -05:00
Matthew Honnibal
c61c501406
Update beam-parser to allow parser to maintain nogil
2017-03-15 09:30:22 -05:00
Matthew Honnibal
c79b3129e3
Fix setting of empty lexeme in initial parse state
2017-03-15 09:26:53 -05:00
Matthew Honnibal
6c4108c073
Add header for beam parser
2017-03-11 12:45:12 -06:00
Matthew Honnibal
931feb3360
Allow beam parsing for NER
2017-03-11 11:12:01 -06:00
Matthew Honnibal
ca9c8c57c0
Add iteration argument to parser.update
2017-03-11 07:00:47 -06:00
Matthew Honnibal
d59c6926c1
I think this fixes the segfault
2017-03-11 06:58:34 -06:00
Matthew Honnibal
318b9e32ff
WIP on beam parser. Currently segfaults.
2017-03-11 06:19:52 -06:00
Matthew Honnibal
b0d80dc9ae
Update name of 'train' function in BeamParser
2017-03-10 14:35:43 -06:00
Matthew Honnibal
d11f1a4ddf
Record negative costs in non-monotonic arc eager oracle
2017-03-10 11:22:04 -06:00
Matthew Honnibal
ecf91a2dbb
Support beam parser
2017-03-10 11:21:21 -06:00
Matthew Honnibal
c62da02344
Use ftrl training, to learn compressed model.
2017-03-09 18:43:21 -06:00
Matthew Honnibal
40703988bc
Use FTRL training in parser
2017-03-08 01:38:51 +01:00
Roman Inflianskas
66e1109b53
Add support for Universal Dependencies v2.0
2017-03-03 13:17:34 +01:00
Matthew Honnibal
97a1286129
Revert changes to tagger and parser for thinc 6
2017-01-09 10:08:34 -06:00
Matthew Honnibal
af81ac8bb0
Use thinc 6.0
2016-12-29 11:58:42 +01:00
Matthew Honnibal
bc0a202c9c
Fix unicode problem in nonproj module
2016-11-25 17:29:17 -06:00
Matthew Honnibal
159e8c46e1
Merge old training fixes with newer state
2016-11-25 09:16:36 -06:00
Matthew Honnibal
39341598bb
Fix NER label calculation
2016-11-25 09:02:22 -06:00
Matthew Honnibal
ca773a1f53
Tweak arc_eager n_gold to deal with negative costs, and improve error message.
2016-11-25 09:01:52 -06:00
Matthew Honnibal
608d8f5421
Pass cfg through parser, and have is_valid default to 1, not 0 when resetting state
2016-11-25 09:00:21 -06:00
Matthew Honnibal
b8c4f5ea76
Allow German noun chunks to work on Span
...
Update the German noun chunks iterator, so that it also works on Span objects.
2016-11-24 23:30:15 +11:00
Pokey Rule
3e3bda142d
Add noun_chunks to Span
2016-11-24 10:47:20 +00:00
Matthew Honnibal
b86f8af0c1
Fix doc strings
2016-11-01 12:25:36 +01:00
Matthew Honnibal
708ea22208
Infer types in transition_system.pyx
2016-10-27 18:08:13 +02:00
Matthew Honnibal
301f3cc898
Fix Issue #429 . Add an initialize_state method to the named entity recogniser that adds missing entity types. This is a messy place to add this, because it's strange to have the method mutate state. A better home for this logic could be found.
2016-10-27 18:01:55 +02:00
Matthew Honnibal
03a520ec4f
Change signature of Parser.parseC, so that nr_class is read from the transition system. This allows the transition system to modify the number of actions in initialize_state.
2016-10-27 17:58:56 +02:00
Matthew Honnibal
a209b10579
Improve error message when oracle fails for non-projective trees, re Issue #571 .
2016-10-24 20:31:30 +02:00
Matthew Honnibal
3e688e6d4b
Fix issue #514 -- serializer fails when new entity type has been added. The fix here is quite ugly. It's best to add the entities ASAP after loading the NLP pipeline, to mitigate the brittleness.
2016-10-23 17:45:44 +02:00
Matthew Honnibal
59038f7efa
Restore support for prior data format -- specifically, the labels field of the config.
2016-10-17 00:53:26 +02:00
Matthew Honnibal
7887ab3b36
Fix default use of feature_templates in parser
2016-10-16 21:41:56 +02:00
Matthew Honnibal
f787cd29fe
Refactor the pipeline classes to make them more consistent, and remove the redundant blank() constructor.
2016-10-16 21:34:57 +02:00
Matthew Honnibal
274a4d4272
Fix queue Python property in StateClass
2016-10-16 17:04:41 +02:00
Matthew Honnibal
e8c8aa08ce
Make action_name optional in StepwiseState
2016-10-16 17:04:16 +02:00
Matthew Honnibal
4fc56d4a31
Rename 'labels' to 'actions' in parser options
2016-10-16 11:42:26 +02:00
Matthew Honnibal
3259a63779
Whitespace
2016-10-16 01:47:28 +02:00
Matthew Honnibal
d9ae2d68af
Load features by string-name for backwards compatibility.
2016-10-12 20:15:11 +02:00
Matthew Honnibal
3a03c668c3
Fix message in ParserStateError
2016-10-12 14:44:31 +02:00
Matthew Honnibal
6bf505e865
Fix error on ParserStateError
2016-10-12 14:35:55 +02:00
Matthew Honnibal
ea23b64cc8
Refactor training, with new spacy.train module. Defaults still a little awkward.
2016-10-09 12:24:24 +02:00
Matthew Honnibal
1d70db58aa
Revert "Changes to iterators.pyx for new StringStore scheme"
...
This reverts commit 4f794b215a
2016-09-30 20:19:53 +02:00
Matthew Honnibal
9e09b39b9f
Revert "Changes to transition systems for new StringStore scheme"
...
This reverts commit 0442e0ab1e
2016-09-30 20:11:49 +02:00
Matthew Honnibal
e3285f6f30
Revert "Fix report of ParserStateError"
...
This reverts commit 78f19baafa
2016-09-30 20:11:33 +02:00
Matthew Honnibal
78f19baafa
Fix report of ParserStateError
2016-09-30 19:59:22 +02:00
Matthew Honnibal
0442e0ab1e
Changes to transition systems for new StringStore scheme
2016-09-30 19:58:51 +02:00
Matthew Honnibal
4f794b215a
Changes to iterators.pyx for new StringStore scheme
2016-09-30 19:57:49 +02:00
Matthew Honnibal
4cbf0d3bb6
Handle errors when no valid actions are available, pointing users to the issue tracker.
2016-09-27 19:19:53 +02:00
Matthew Honnibal
430473bd98
Raise errors when no actions are available, re Issue #429
2016-09-27 19:09:37 +02:00
Matthew Honnibal
8e7df3c4ca
Expect the parser data, if parser.load() is called.
2016-09-27 14:02:12 +02:00
Matthew Honnibal
a44763af0e
Fix Issue #469 : Incorrectly cased root label in noun chunk iterator
2016-09-27 13:13:01 +02:00
Matthew Honnibal
e07b9665f7
Don't expect parser model
2016-09-26 18:09:33 +02:00
Matthew Honnibal
ee6fa106da
Fix parser features
2016-09-26 17:57:32 +02:00
Matthew Honnibal
e607e4b598
Fix parser loading
2016-09-26 17:51:11 +02:00
Matthew Honnibal
2debc4e0a2
Add .blank() method to Parser. Start housing default dep labels and entity types within the Defaults class.
2016-09-26 11:57:54 +02:00
Matthew Honnibal
fd65cf6cbb
Finish refactoring data loading
2016-09-24 20:26:17 +02:00
Matthew Honnibal
83e364188c
Mostly finished loading refactoring. Design is in place, but doesn't work yet.
2016-09-24 15:42:01 +02:00
Matthew Honnibal
60fdf4d5f1
Remove commented out debuggng code
2016-09-24 01:17:18 +02:00
Matthew Honnibal
070af4af9d
Revert "* Working neural net, but features hacky. Switching to extractor."
...
This reverts commit 7c2f1a673b
2016-09-21 12:26:14 +02:00
Matthew Honnibal
7c2f1a673b
* Working neural net, but features hacky. Switching to extractor.
2016-05-26 19:06:10 +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
Wolfgang Seeker
7b78239436
add fix for German noun chunk iterator (issue #365 )
2016-05-06 01:41:26 +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
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
Wolfgang Seeker
e4ea2bea01
fix whitespace
2016-05-04 07:40:38 +02:00
Wolfgang Seeker
5bf2fd1f78
make the code less cryptic
2016-05-03 17:19:05 +02:00
Wolfgang Seeker
a06fca9fdf
German noun chunk iterator now doesn't return tokens more than once
2016-05-03 16:58:59 +02:00
Wolfgang Seeker
7b246c13cb
reformulate noun chunk tests for English
2016-05-03 14:24:35 +02:00
Matthew Honnibal
1f1532142f
* Fix cost calculation on non-monotonic oracle
2016-05-03 00:21:08 +02:00
Matthew Honnibal
508fd1f6dc
* 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
Matthew Honnibal
77609588b6
* Fix assignment of root label to words left as root implicitly, after parsing ends.
2016-04-25 19:41:59 +00:00
Matthew Honnibal
7c2d2deaa7
* Revise transition system so that the Break transition retains sole responsibility for setting sentence boundaries. Re Issue #322
2016-04-25 19:41:59 +00:00
Wolfgang Seeker
12024b0b0a
bugfix: introducing multiple roots now updates original head's properties
...
adjust tests to rely less on statistical model
2016-04-20 16:42:41 +02:00
Wolfgang Seeker
b98cc3266d
bugfix: iterators now reset properly when called a second time
2016-04-15 17:49:16 +02:00
Wolfgang Seeker
289b10f441
remove some comments
2016-04-14 15:37:51 +02:00
Wolfgang Seeker
d99a9cbce9
different handling of space tokens
...
space tokens are now always attached to the previous non-space token
there are two exceptions:
leading space tokens are attached to the first following non-space token
in input that consists exclusively of space tokens, the last space token
is the head of all others.
2016-04-13 15:28:28 +02:00
Wolfgang Seeker
d328e0b4a8
Merge branch 'master' into space_head_bug
2016-04-11 12:11:01 +02:00
Wolfgang Seeker
80bea62842
bugfix in unit test
2016-04-08 16:46:44 +02:00
Wolfgang Seeker
1fe911cdb0
bigfix
2016-04-07 18:19:51 +02:00
Matthew Honnibal
872695759d
Merge pull request #306 from wbwseeker/german_noun_chunks
...
add German noun chunk functionality
2016-04-08 00:54:24 +10:00
