spaCy/spacy
Matthew Honnibal 7c504b6ddb Try to implement more losses for pretraining
* Try to implement cosine loss
This one seems to be correct? Still unsure, but it performs okay

* Try to implement the von Mises-Fisher loss
This one's definitely not right yet.
2018-12-17 14:48:27 +00:00
..
cli Try to implement more losses for pretraining 2018-12-17 14:48:27 +00:00
data Make spacy/data a package 2017-03-18 20:04:22 +01:00
displacy 💫 New JSON helpers, training data internals & CLI rewrite (#2932) 2018-11-30 20:16:14 +01:00
lang 💫 Tidy up and auto-format .py files (#2983) 2018-11-30 17:03:03 +01:00
syntax 💫 Better support for semi-supervised learning (#3035) 2018-12-10 16:25:33 +01:00
tests Add test for issue #2871 -- vectors for reserved words 2018-12-10 16:09:10 +01:00
tokens 💫 Allow Span to take text label (#3031) 2018-12-08 13:08:41 +01:00
__init__.pxd * Seems to be working after refactor. Need to wire up more POS tag features, and wire up save/load of POS tags. 2014-10-24 02:23:42 +11:00
__init__.py Tidy up and format remaining files 2018-11-30 17:43:08 +01:00
__main__.py 💫 New JSON helpers, training data internals & CLI rewrite (#2932) 2018-11-30 20:16:14 +01:00
_align.pyx Improve alignment around quotes 2018-08-16 01:04:34 +02:00
_ml.py 💫 Better support for semi-supervised learning (#3035) 2018-12-10 16:25:33 +01:00
about.py Set version back to 2.1.0a4 2018-12-03 02:03:26 +01:00
attrs.pxd Fix LANG symbol 2018-02-17 18:10:50 +01:00
attrs.pyx Revert "Merge branch 'develop' of https://github.com/explosion/spaCy into develop" 2018-03-27 19:23:02 +02:00
compat.py 💫 Replace ujson, msgpack and dill/pickle/cloudpickle with srsly (#3003) 2018-12-03 01:28:22 +01:00
errors.py replace user-facing references to "sbd" with "sentencizer" (#2985) 2018-11-30 21:22:40 +01:00
glossary.py 💫 Tidy up and auto-format .py files (#2983) 2018-11-30 17:03:03 +01:00
gold.pxd Add support for sent_start to GoldParse 2017-08-25 20:03:14 -05:00
gold.pyx Fix JSON segmentation bug that affected French 2018-12-08 10:41:24 +01:00
language.py 💫 Better support for semi-supervised learning (#3035) 2018-12-10 16:25:33 +01:00
lemmatizer.py 💫 Tidy up and auto-format .py files (#2983) 2018-11-30 17:03:03 +01:00
lexeme.pxd WIP on stringstore change. 27 failures 2017-05-28 14:06:40 +02:00
lexeme.pyx 💫 Add .similarity warnings for no vectors and option to exclude warnings (#2197) 2018-05-21 01:22:38 +02:00
matcher.pyx 💫 Port master changes over to develop (#2979) 2018-11-29 16:30:29 +01:00
morphology.pxd Revert "Merge branch 'develop' of https://github.com/explosion/spaCy into develop" 2018-03-27 19:23:02 +02:00
morphology.pyx Fix lemmatization 2018-07-05 13:56:02 +02:00
parts_of_speech.pxd Add support for Universal Dependencies v2.0 2017-03-03 13:17:34 +01:00
parts_of_speech.pyx Tidy up rest 2017-10-27 21:07:59 +02:00
pipeline.pxd Fix names of pipeline components 2017-10-26 12:38:23 +02:00
pipeline.pyx 💫 Better support for semi-supervised learning (#3035) 2018-12-10 16:25:33 +01:00
scorer.py 💫 Tidy up and auto-format .py files (#2983) 2018-11-30 17:03:03 +01:00
strings.pxd Try to fix StringStore clean up (see #1506) 2017-11-11 03:11:27 +03:00
strings.pyx Add get_string_id helper to spacy.strings 2018-12-10 16:09:26 +01:00
structs.pxd Make NORM a token attribute (#3029) 2018-12-08 10:49:10 +01:00
symbols.pxd Revert "Merge branch 'develop' of https://github.com/explosion/spaCy into develop" 2018-03-27 19:23:02 +02:00
symbols.pyx Revert "Merge branch 'develop' of https://github.com/explosion/spaCy into develop" 2018-03-27 19:23:02 +02:00
tokenizer.pxd Disable tokenizer cache for special-cases. Fixes #1250 2017-10-24 16:08:05 +02:00
tokenizer.pyx 💫 Small efficiency fixes to tokenizer (#2587) 2018-07-24 23:35:54 +02:00
typedefs.pxd Work on changing StringStore to return hashes. 2017-05-28 12:36:27 +02:00
typedefs.pyx Tidy up rest 2017-10-27 21:07:59 +02:00
util.py Set cupy.random seed in fix_random_seed helper 2018-12-08 12:37:38 +01:00
vectors.pyx Fix KeyError in Vectors.most_similar. Fixes #2648 2018-12-10 16:19:18 +01:00
vocab.pxd 💫 Small efficiency fixes to tokenizer (#2587) 2018-07-24 23:35:54 +02:00
vocab.pyx Make NORM a token attribute (#3029) 2018-12-08 10:49:10 +01:00