项目作者: Esukhia
项目描述 :
Tibetan canon segmented and tagged for frequency analysis
高级语言: Python
项目地址: git://github.com/Esukhia/canon-freq.git
canon-freq
canon-freq is a working repository for frequency analysis of the Tibetan canon.
Segmentation and POS-tagging are improved gradually by chuncks of 1000 most frequent words.