spaCy/README.md

51 lines
1.3 KiB
Markdown
Raw Normal View History

2015-07-01 16:39:38 +03:00
spaCy: Industrial-strength NLP
==============================
2014-07-03 19:15:40 +04:00
2015-07-01 16:39:38 +03:00
spaCy is a library for advanced natural language processing in Python and Cython.
2015-02-01 06:47:18 +03:00
2015-07-01 16:27:37 +03:00
Documentation and details: http://spacy.io/
2015-06-24 06:05:33 +03:00
2015-07-01 16:27:37 +03:00
spaCy is built on the very latest research, but it isn't researchware. It was
2015-07-01 16:38:55 +03:00
designed from day 1 to be used in real products. You can buy a commercial license, or you can use it under the AGPL.
2015-06-24 06:05:33 +03:00
2015-07-01 16:27:37 +03:00
Features
--------
2015-02-01 06:47:18 +03:00
2015-07-01 16:27:37 +03:00
* 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.
Top Pefomance
-------------
* 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 13:55:36 +03:00
2015-05-12 04:32:53 +03:00
Supports
--------
2015-01-27 13:55:23 +03:00
* CPython 2.7
* CPython 3.4
* OSX
* Linux
2015-04-13 07:23:30 +03:00
* Cygwin
2015-01-27 13:55:23 +03:00
2015-02-01 06:47:18 +03:00
Want to support:
2015-01-27 13:55:23 +03:00
2015-04-13 07:23:30 +03:00
* Visual Studio
2015-01-27 13:55:23 +03:00
2015-02-01 06:47:18 +03:00
Difficult to support:
2015-01-27 13:55:23 +03:00
* PyPy 2.7
* PyPy 3.4