KyTea Tokenizer for nltk

September 7, 2011 · View on GitHub

2011/09/09 chezou

JPKyteaTokenizer is Japanese tokenizer with KyTea for nltk.

It's depends on KyTea and Mykytea-python.

KyTea is developed by KyTea Development Team

Detailed information of KyTea can be found at http://www.phontron.com/kytea

Install Dependencies

You need install KyTea and Mykytea-python before build.

See 'test_kyteatokenizer.py' as a sample program.

MIT License