Re:Zero − Chinese Word Segmentation Tool's buliding.
l18i: English | 简体中文
This is a repository for a Chinese Word Segmentation Tool. I built it with simple enumerate way and an improved version based on viterbi algorithm.
I left two method to finish the Enumerate way, dictionary based and input based.
You can access the dictionary file as enumerate_old file, and enumerate file for another.
You can check them out as follow:
The file located on the path of /data/ is the dataset used as dictionary, you can check it out on here.
If you have any question, take it easy to contact me on my blog comment area.