2016-03-12 13:31:39 +00:00
|
|
|
.. image:: https://travis-ci.org/spacy-io/spaCy.svg?branch=master
|
|
|
|
|
:target: https://travis-ci.org/spacy-io/spaCy
|
|
|
|
|
|
2016-03-12 13:30:24 +00:00
|
|
|
==============================
|
2015-07-01 13:39:38 +00:00
|
|
|
spaCy: Industrial-strength NLP
|
|
|
|
|
==============================
|
2014-07-03 15:15:40 +00:00
|
|
|
|
2015-07-01 13:39:38 +00:00
|
|
|
spaCy is a library for advanced natural language processing in Python and Cython.
|
2015-02-01 03:47:18 +00:00
|
|
|
|
2016-02-08 17:48:16 +00:00
|
|
|
Documentation and details: https://spacy.io/
|
2015-06-24 03:05:33 +00:00
|
|
|
|
2015-07-01 13:27:37 +00:00
|
|
|
spaCy is built on the very latest research, but it isn't researchware. It was
|
2015-09-27 21:38:12 +00:00
|
|
|
designed from day 1 to be used in real products. It's commercial open-source
|
|
|
|
|
software, released under the MIT license.
|
2015-06-24 03:05:33 +00:00
|
|
|
|
|
|
|
|
|
2015-07-01 13:27:37 +00:00
|
|
|
Features
|
|
|
|
|
--------
|
2015-02-01 03:47:18 +00:00
|
|
|
|
2015-07-01 13:27:37 +00:00
|
|
|
* Labelled dependency parsing (91.8% accuracy on OntoNotes 5)
|
|
|
|
|
* Named entity recognition (82.6% accuracy on OntoNotes 5)
|
|
|
|
|
* Part-of-speech tagging (97.1% accuracy on OntoNotes 5)
|
|
|
|
|
* Easy to use word vectors
|
|
|
|
|
* All strings mapped to integer IDs
|
|
|
|
|
* Export to numpy data arrays
|
|
|
|
|
* Alignment maintained to original string, ensuring easy mark up calculation
|
|
|
|
|
* Range of easy-to-use orthographic features.
|
|
|
|
|
* No pre-processing required. spaCy takes raw text as input, warts and newlines and all.
|
|
|
|
|
|
2015-09-29 13:02:08 +00:00
|
|
|
Top Peformance
|
2016-03-13 17:12:32 +00:00
|
|
|
--------------
|
2015-07-01 13:27:37 +00:00
|
|
|
|
|
|
|
|
* Fastest in the world: <50ms per document. No faster system has ever been
|
|
|
|
|
announced.
|
|
|
|
|
* Accuracy within 1% of the current state of the art on all tasks performed
|
|
|
|
|
(parsing, named entity recognition, part-of-speech tagging). The only more
|
|
|
|
|
accurate systems are an order of magnitude slower or more.
|
2015-01-27 10:55:36 +00:00
|
|
|
|
2015-05-12 01:32:53 +00:00
|
|
|
Supports
|
|
|
|
|
--------
|
2015-01-27 10:55:23 +00:00
|
|
|
|
2016-02-19 18:36:47 +00:00
|
|
|
* CPython 2.6, 2.7, 3.3, 3.4, 3.5 (only 64 bit)
|
2015-01-27 10:55:23 +00:00
|
|
|
* OSX
|
2016-02-08 17:47:37 +00:00
|
|
|
* Linux
|
|
|
|
|
* Windows (Cygwin, MinGW, Visual Studio)
|
2015-01-27 10:55:23 +00:00
|
|
|
|
2015-02-01 03:47:18 +00:00
|
|
|
Difficult to support:
|
2015-01-27 10:55:23 +00:00
|
|
|
|
2016-02-19 18:36:47 +00:00
|
|
|
* PyPy
|
