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
ea23b64cc8
Refactor training, with new spacy.train module. Defaults still a little awkward.
2016-10-09 12:24:24 +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
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
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
7195b6742d
add restrictions to L-arc and R-arc to prevent space heads
2016-03-28 10:40:52 +02:00
Matthew Honnibal
bcf8f7ba40
* Add a parse_batch method to Parser, that releases the GIL around a batch of documents.
2016-02-01 08:34:55 +01:00
Matthew Honnibal
cb78d91ec5
* Fix ArcEager.set_valid
2016-02-01 03:07:37 +01:00
Matthew Honnibal
a47f00901b
* 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
Matthew Honnibal
daaad66448
* Now fully proxied
2016-02-01 02:37:08 +01:00
Matthew Honnibal
7a0e3bb9c1
* Continue proxying. Some problem currently
2016-02-01 02:22:21 +01:00
Matthew Honnibal
10877a7791
* 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
Matthew Honnibal
c8e0011ebc
* Add iterators to the NER and parser transition systems, to get the action types
2016-01-19 19:07:43 +01:00
Matthew Honnibal
04177debd0
* Unwind limit to sentence boundary detection that prevents it from inserting boundaries on whitespace. Replace it with a check for whitespace in StateClass.fast_forward, so that whitespace is LeftArced when it's on the stack. This should prevent the previous problem of whitespace-only sentences. Should fix Issue #184 , but may cause further problems. Needs testing.
2016-01-19 02:54:15 +01:00
Matthew Honnibal
1cfa20fb17
* Fix sentence-final whitespace issue
2015-11-07 17:34:46 +11:00
Matthew Honnibal
329ae57520
* Fix whitespace attachment thing
2015-10-13 09:46:38 +02:00
Matthew Honnibal
37919eac82
* Fix whitespace attachment in simpler way. Leaves problem with setting left/right children.
2015-10-13 18:23:24 +11:00
Matthew Honnibal
c70eb776ae
* Fix whitespace attachment, so that left/right children are consistent with head.
2015-10-13 15:58:22 +11:00
Matthew Honnibal
9dd2f25c74
* Fix Issue #131 : Force whitespace characters to attach syntactically to previous token, and ensure they cannot serve as stand-alone 'sentence' units.
2015-10-10 15:53:30 +11:00
Matthew Honnibal
8b39feefbe
* Add dependency post-process rule to ensure spaces are attached to neighbouring tokens, so that they can't be sentence boundaries
2015-10-10 15:32:13 +11:00
Matthew Honnibal
2c9753eff2
* Whitespace
2015-08-10 00:09:02 +02:00
Matthew Honnibal
76a1f0481a
* Whitespace
2015-08-08 23:31:54 +02:00
Matthew Honnibal
823ef4a00b
* Remove profile declarations
2015-07-25 18:13:06 +02:00
Matthew Honnibal
317cbbc015
* Serialization round trip now working with decent API, but with rough spots in the organisation and requiring vocabulary to be fixed ahead of time.
2015-07-19 15:18:17 +02:00
Matthew Honnibal
e29daea85f
* Fix bint/int typing problem in TransitionSystem. In C++ bint* means bool*, but in C it means int*. So, type-casting to bint* is unsafe.
2015-07-17 22:37:24 +02:00
Matthew Honnibal
9a8db9743c
* Remove gil from parser.call
2015-07-14 23:47:33 +02:00
Matthew Honnibal
75aeccc064
* Rejig parser interface to use new thinc.api.Example class, in prep of theano model. Comment out beam search
2015-06-28 11:02:34 +02:00
Matthew Honnibal
7b125f5a86
* Fixes to edge features
2015-06-23 16:31:01 +02:00
Matthew Honnibal
221e2e485f
* Assign 'ROOT' as label, not 'root'
2015-06-23 15:09:54 +02:00
Matthew Honnibal
a7bf7b0626
* Rename sent_start to sent_end, to reflect its new usage in the Break transition
2015-06-23 05:39:43 +02:00
Matthew Honnibal
43ef5ddea5
* Ensure root albel is spelled ROOT, for backwards compatibility
2015-06-23 04:14:03 +02:00
Matthew Honnibal
69507bc729
* Re-enable Break transition in arc_eager.pyx
2015-06-23 00:03:30 +02:00
Matthew Honnibal
21930ede15
* Switch toggle on USE_ROOT_ARC_SEGMENT
2015-06-15 02:54:32 +02:00
Matthew Honnibal
38a6afa484
* Make possibly dubious correction to the unshift oracle
2015-06-15 02:50:00 +02:00
Matthew Honnibal
bdd07bf000
* Fix Break oracle, but disable the Break transition for now, while we finalize the gold-standard experiments
2015-06-14 17:44:03 +02:00
Matthew Honnibal
399f15fbdf
* Add flag to toggle handling of multi-root inputs without the Break transition. Clear up now unused best_valid stuff.
2015-06-14 00:28:37 +02:00
Matthew Honnibal
15e177d7a1
* Fixes to unshift/fast-forward strategy. Getting 91.55 greedy on NW dev, gold preproc
2015-06-12 01:50:23 +02:00
Matthew Honnibal
afd77a529b
* Prepare for break transition, with fast-forwarding. 86.5 on 1k nw gold preproc
2015-06-10 14:08:30 +02:00
Matthew Honnibal
b7b18c279d
* Fix Reduce oracle. Getting 86.35
2015-06-10 11:33:39 +02:00
Matthew Honnibal
aa9625f688
* Do non-monotonic Unshift. Every word can be shifted at most 1 time. When the Reduce move is used, if S0 has no head, we put the word back on the buffer. Gets 86.4 on nw 1k with gold pre-proc. Break transition not yet implemented for this.
2015-06-10 10:15:56 +02:00
Matthew Honnibal
e2f9a80713
* Remove old _state imports
2015-06-10 07:09:17 +02:00
Matthew Honnibal
e5570c9700
* Set nogil for oracle functions
2015-06-10 06:56:56 +02:00
Matthew Honnibal
04b1cd9b8c
* Greedy parsing working with new StateClass. Beam parsing broken
2015-06-10 04:20:23 +02:00
Matthew Honnibal
d68c686ec1
* Move StateClass into interface of transition functions
2015-06-10 01:35:28 +02:00
Matthew Honnibal
4b98b3e9c8
* Cost functions now take StateClass argument, instead of State*.
2015-06-10 00:40:43 +02:00
Matthew Honnibal
e0cf61f591
* Move StateClass into the interface for is_valid
2015-06-09 23:23:28 +02:00
Matthew Honnibal
0895d454fb
* Prepare to switch to using state class, instead of state struct
2015-06-09 21:20:14 +02:00
Matthew Honnibal
2b9629ed62
* Begin adding stateclass to ArcEager
2015-06-09 01:41:09 +02:00
Matthew Honnibal
c7e3dfc1dc
* Don't automatically push words when stack is empty, as it messes up beam parsing. Add hash method to beam state.
2015-06-08 14:49:04 +02:00
Matthew Honnibal
8f142c1838
* Refactor transition system oracles, to split out move and label cost. Preparing to add Unshift move. Will exclude non-monotonic.
2015-06-07 03:21:29 +02:00
Matthew Honnibal
6bf35cecc3
* Refactor transition system to use classes with staticmethods.
2015-06-05 02:27:17 +02:00
Matthew Honnibal
36a34d544b
* Refactoring arc_eager, grouping oracle functions into transitions
2015-06-04 22:43:03 +02:00
Matthew Honnibal
4433396005
* Impove efficiency of dynamic oracle, making beam training faster
2015-06-04 21:15:14 +02:00
Matthew Honnibal
a2627b6102
* Fix bug in refactored init_transition
2015-06-03 06:01:26 +02:00
Matthew Honnibal
a513ec500f
* Have oracle functions take a struct instead of a Python object
2015-06-02 20:01:06 +02:00
Matthew Honnibal
0786d9b3c7
* Refactor TransitionSystem, adding set_valid method
2015-06-02 18:38:07 +02:00
Matthew Honnibal
c7876aa8b6
* Add get_valid method
2015-06-01 23:06:00 +02:00
Matthew Honnibal
5e99ff94c8
* Edits to arc eager oracle. Couldn't figure out how the non-monotonic lines made sense. They seem covered by children_in_stack
2015-05-31 15:14:37 +02:00
Matthew Honnibal
6c5632b71c
* Roll back proposed change to Break transition while investigate effect
2015-05-31 06:49:52 +02:00
Matthew Honnibal
76300bbb1b
* Use updated JSON format, with sentences below paragraphs. Allows use of gold preprocessing flag.
2015-05-30 01:25:46 +02:00
Matthew Honnibal
8f31d3b864
* Relax constraint on Break transition for non-monotonic parsing.
2015-05-28 23:39:52 +02:00
Matthew Honnibal
fc75210941
* Move spacy.syntax.conll to spacy.gold
2015-05-24 21:35:02 +02:00
Matthew Honnibal
78487f3e66
* Update parser oracle for missing heads
2015-05-24 20:05:58 +02:00
Matthew Honnibal
20f1d868a3
* Tmp commit. Working on whole document parsing
2015-05-24 02:49:56 +02:00
Matthew Honnibal
f2ee9c4feb
* Comment out constituency parsing stuff, so that code compiles
2015-05-20 16:55:05 +02:00
Matthew Honnibal
9dfc9c039c
* Work on constituency parsing.
2015-05-20 16:02:51 +02:00
Matthew Honnibal
f1e0272b18
* Disable c-parsing transitions
2015-05-12 22:33:25 +02:00
Matthew Honnibal
03a6626545
* Tmp commit
2015-05-12 20:27:56 +02:00
Matthew Honnibal
b3fd48c97b
* Fix missing root labels bug identified in Issue #57
2015-04-28 20:45:51 +02:00
Matthew Honnibal
a3af6b7c3d
* Left-Arc from Root, to allow non-monotonic reduce to compete with left-arc when the stack is not empty.
2015-03-27 17:39:16 +01:00
Matthew Honnibal
b32f581acb
* Fix bug in ArcEager.get_labels
2015-03-27 15:21:06 +01:00
Matthew Honnibal
3b70b304b2
* Add words to gold_tuples from gold conll file
2015-03-26 16:44:47 +01:00
Matthew Honnibal
9f4ad8fdfb
* Assign root words the ROOT label via the Break transition. Something is still wrong here...
2015-03-26 16:44:46 +01:00
Matthew Honnibal
f729164c01
* Fix bug in label assignment: ensure null-label transitions receive the label 0
2015-03-26 16:44:46 +01:00
Matthew Honnibal
31fad99518
* Use StringStore to encode label names, instead of label_ids
2015-03-26 16:44:45 +01:00
Matthew Honnibal
8057a95f20
* NER seems to be working, scoring 69 F. Need to add decision-history features --- currently only use current word, 2 words context. Need refactoring.
2015-03-26 16:44:44 +01:00
Matthew Honnibal
ae235e07b9
* Refactoring working for parser, but now need to rig up features for NER, and then debug oracle etc.
2015-03-26 16:44:44 +01:00
Matthew Honnibal
b3eda03c9c
* Tmp
2015-03-26 16:44:44 +01:00
Matthew Honnibal
fdabd93bfb
* Ensure high loss for invalid moves, and fix label reading for arc-eager
2015-03-26 16:44:43 +01:00
Matthew Honnibal
10ed738df2
* Tmp commit
2015-03-26 16:44:43 +01:00
Matthew Honnibal
4f83c9b3d5
* Make costs label-sensitive
2015-03-26 16:44:43 +01:00
Matthew Honnibal
8c883cef58
* Refactored transition system code now compiling. Still need to hook up label oracle, and test
2015-03-26 16:44:43 +01:00
Matthew Honnibal
8eadb984cb
* Refactor arc_eager to use new TransitionSystem base class. Need to fix oracle
2015-03-26 16:44:42 +01:00
Matthew Honnibal
135756ac3d
* Tmp commit of NER refactoring
2015-03-26 16:44:42 +01:00
Matthew Honnibal
ea90d136e8
* Fix bug in labelled parsing, that caused an 8% drop in labelled accuracy.
2015-02-27 03:56:10 -05:00
Matthew Honnibal
d68678a93e
* Add Exception class, OracleError
2015-02-02 11:57:32 +11:00
Matthew Honnibal
0981d68022
* Set a sent_end flag during parsing, for later use
2015-01-31 13:41:46 +11:00
Matthew Honnibal
ebf7d2fab1
* Use non-joint sbd, for more simplicity and fewer classes
2015-01-29 06:22:03 +11:00
Matthew Honnibal
d05c5bf141
* Remove comment
2015-01-29 05:19:27 +11:00
Matthew Honnibal
320b045daa
* Oracle now consistent over gold standard derivation
2015-01-29 03:41:58 +11:00
Matthew Honnibal
f590382134
* Work on sbd
2015-01-29 03:18:29 +11:00
Matthew Honnibal
1884a7a0be
* Attach comment with paper
2015-01-28 03:18:43 +11:00
Matthew Honnibal
a2d6b195db
* Add messy Break transitions, carefully following the scheme of Dd Zhang et al (2013)
2015-01-28 03:09:45 +11:00
Matthew Honnibal
d819101571
* Improve error message on oracle failure
2015-01-28 00:58:03 +11:00
