compound-word-splitter

Splits compound words, like German "Effektivitätsberechnung


Keywords
natural-language-processing, python
License
MIT
Install
pip install compound-word-splitter==0.4

Documentation

compound-word-splitter

https://travis-ci.org/TimKam/compound-word-splitter.svg?branch=master

Splits words that are not recognized by pyenchant (spell checker) into largest possible compounds.

Installation

pip install compound-word-splitter

Usage

import splitter

splitter.split('artfactory')

returns

['art', 'factory']

If the word cannot be split into compounds pyenchant recognizes as words, the splitter returns an empty string.