s2458588 / wsm-tokenizer

Bachelor Thesis Repository. Wsm-tokenizer (word shape mapping) uses vocabulary comparisons to find probable morphemes in lexemic tokens.

Repository from Github https://github.coms2458588/wsm-tokenizerRepository from Github https://github.coms2458588/wsm-tokenizer

This repository is not active

About

Bachelor Thesis Repository. Wsm-tokenizer (word shape mapping) uses vocabulary comparisons to find probable morphemes in lexemic tokens.


Languages

Language:Jupyter Notebook 94.4%Language:Python 5.6%