explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-11 04:08:09 +03:00
Code Issues Packages Projects Releases Wiki Activity
💫 Industrial-strength Natural Language Processing (NLP) in Python
1,987 Commits 68 Branches 175 Tags 279 MiB
Python 53.6%
MDX 31.4%
Cython 10.8%
JavaScript 2.6%
Sass 0.8%
Other 0.7%
b3a70e6375
Go to file
Matthew Honnibal b3a70e6375 * Clean up unnecessary try/except block
2015-10-08 14:34:11 +11:00
bin * Add script to train models off the UD treebanks. Note that the UD data is restricted to research purposes only, and should only be used to train models for academic experiments. 2015-10-08 12:01:08 +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 * Fix multi_word_matches script 2015-10-08 13:59:32 +11:00
lang_data * Patch italian tag map 2015-10-08 14:00:13 +11:00
spacy * Clean up unnecessary try/except block 2015-10-08 14:34:11 +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 * Avoid compiling unused files 2015-10-08 14:00:34 +11:00
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