- Notifications
You must be signed in to change notification settings - Fork40
Rule-based facts extraction for Russian language
License
NotificationsYou must be signed in to change notification settings
natasha/yargy
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
Yargy uses rules and dictionaries to extract structured information from Russian texts. Yargy is similar toTomita parser.
Yargy supports Python 3.7+, PyPy 3, depends only onPymorphy2.
$ pip install yargy
fromyargyimportParser,rule,and_,not_fromyargy.interpretationimportfactfromyargy.predicatesimportgramfromyargy.relationsimportgnc_relationfromyargy.pipelinesimportmorph_pipelineName=fact('Name', ['first','last'],)Person=fact('Person', ['position','name'])LAST=and_(gram('Surn'),not_(gram('Abbr')),)FIRST=and_(gram('Name'),not_(gram('Abbr')),)POSITION=morph_pipeline(['управляющий директор','вице-мэр'])gnc=gnc_relation()NAME=rule(FIRST.interpretation(Name.first ).match(gnc),LAST.interpretation(Name.last ).match(gnc)).interpretation(Name)PERSON=rule(POSITION.interpretation(Person.position ).match(gnc),NAME.interpretation(Person.name )).interpretation(Person)parser=Parser(PERSON)match=parser.match('управляющий директор Иван Ульянов')print(match)Person(position='управляющий директор',name=Name(first='Иван',last='Ульянов' ))
All materials are in Russian:
- Chat —https://t.me/natural_language_processing
- Issues —https://github.com/natasha/yargy/issues
- Commercial support —https://lab.alexkuk.ru
Dev env
brew install graphvizpython -m venv~/.venvs/natasha-yargysource~/.venvs/natasha-yargy/bin/activatepip install -r requirements/dev.txtpip install -e.python -m ipykernel install --user --name natasha-yargy
Test + lint
maketestUpdate docs
make exec-docs# Manually check git diff docs/, commitRelease
# Update setup.py versiongit commit -am'Up version'git tag v0.16.0git pushgit push --tags# Github Action builds dist and publishes to PyPi
About
Rule-based facts extraction for Russian language
Topics
Resources
License
Stars
Watchers
Forks
Packages0
No packages published