explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-09-21 11:29:13 +03:00
Code Issues Packages Projects Releases Wiki Activity
💫 Industrial-strength Natural Language Processing (NLP) in Python
1,977 Commits 66 Branches 174 Tags 277 MiB
Python 53.7%
MDX 31.3%
Cython 10.7%
JavaScript 2.7%
Sass 0.8%
Other 0.7%
c503654ec1
Go to file
Matthew Honnibal c503654ec1 * Update bin/parser/train for printing output.
2015-10-06 10:35:22 +11:00
bin * Update bin/parser/train for printing output. 2015-10-06 10:35:22 +11:00
contributors Merge pull request #85 from NSchrading/master 2015-09-07 09:05:19 +10:00
corpora/en * Add wordnet 2015-09-21 19:06:48 +10:00
examples * Add multi word matching code 2015-10-06 09:06:52 +11:00
lang_data * Start adding auxiliaries to morphs.json 2015-09-27 16:56:34 +10:00
spacy * Add LookupError for better error reporting in Vocab 2015-10-06 10:34:59 +11:00
tests * Add a test for Issue #118: Matcher behaves unpredictably with overlapping entities 2015-10-01 16:21:00 +10:00
website * Set details(open=true) on docs while we redesign 2015-09-30 11:48:15 +10:00
.gitignore * Add sass-cache to gitignore 2015-09-24 18:14:21 +10:00
.travis.yml proposal for doctests 2015-09-24 16:57:11 +02:00
bootstrap_python_env.sh * Add bootstrap script 2015-03-16 14:01:36 -04:00
fabfile.py * Update the publish command, so that it creates a git tag 2015-09-22 02:26:10 +02:00
LICENSE.txt * Change from AGPL to MIT 2015-09-28 07:37:12 +10:00
MANIFEST.in * Add manifest file 2015-01-30 16:49:02 +11:00
README.md * Fix typo in README 2015-09-29 23:02:08 +10:00
requirements.txt * Fix issue #112: Replace unidecode with text-unidecode, to avoid license problems. 2015-09-28 23:40:18 +10:00
setup.py * Fix license metadata in setup.py 2015-09-29 23:02:37 +10:00
wordnet_license.txt * Add WordNet license file 2015-02-01 16:11:53 +11:00

README.md

spaCy: Industrial-strength NLP

spaCy is a library for advanced natural language processing in Python and Cython.

Documentation and details: http://spacy.io/

spaCy is built on the very latest research, but it isn't researchware. It was designed from day 1 to be used in real products. It's commercial open-source software, released under the MIT license.

Features

  • 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 Peformance

  • 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.

Supports

  • CPython 2.7
  • CPython 3.4
  • OSX
  • Linux
  • Cygwin

Want to support:

  • Visual Studio

Difficult to support:

  • PyPy 2.7
  • PyPy 3.4