💫 Industrial-strength Natural Language Processing (NLP) in Python
Go to file
2015-04-15 06:01:18 +02:00
bin * Fix copying of tokenizer data in init_model 2015-04-12 04:45:31 +02:00
contributors * Fix nested lists 2015-03-25 14:38:59 +01:00
docs * Add note to index.rst releasing version 0.80 2015-04-13 05:45:18 +02:00
lang_data/en * Fix specials.json 2015-04-12 04:45:41 +02:00
spacy * Add (N0w, N1w) unigram pair to NER features, prompted by failure to detect 'this weekend' 2015-04-15 06:01:18 +02:00
tests * Add test for simple NER case 2015-04-13 21:33:54 +02:00
.gitignore * Upd gitignore 2015-04-08 07:48:04 +02:00
.travis.yml * Try not downloading stuff for travis.yml 2015-04-13 05:59:05 +02:00
bootstrap_python_env.sh * Add bootstrap script 2015-03-16 14:01:36 -04:00
dev_setup.py * Upd dev_setup 2015-01-03 21:02:03 +11:00
fabfile.py * Add train function to fabfile 2015-04-08 22:47:59 +02:00
LICENSE.txt * Add license file 2015-01-26 03:07:18 +11:00
MANIFEST.in * Add manifest file 2015-01-30 16:49:02 +11:00
README.md * Upd README 2015-04-13 06:23:30 +02:00
requirements.txt * Add pathlib requirement 2015-04-12 07:17:48 +02:00
setup.py * Inc version 2015-04-13 22:29:31 +02:00
wordnet_license.txt * Add WordNet license file 2015-02-01 16:11:53 +11:00

spaCy

http://honnibal.github.io/spaCy

Fast, state-of-the-art natural language processing pipeline. Commercial licenses available, or use under AGPL.

Version 0.80 released

2015-04-13

  • Preliminary named entity recognition support. Accuracy is currently substantially behind the current state-of-the-art. I'm working on improvements.

  • Better sentence boundary detection, drawn from the syntactic structure.

  • Lots of bug fixes

Supports:

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

Want to support:

  • Visual Studio

Difficult to support:

  • PyPy 2.7
  • PyPy 3.4