How to Improve the Performance of Chinese Text Tokenization in Python and Jieba
Published in
4 min readJul 2, 2020
Adding custom words and modifying the dictionary dynamically in your Python application
By reading this piece, you will learn to add your own customs word to Jieba
in order to improve the performance of the tokenization. When dealing with domain-specific Natural Language Processing (NLP) tasks, it is essential to have control…