NLTK项目地址:
https://github.com/nltk/nltk_data/tree/gh-pages/packages
NLTK基础分词用例:
https://www.cnblogs.com/ketmales/archive/2013/05/31/3111046.html
使用NLTK nltk.tokenize.mwe()方法进行分词:(可以自定义某些特殊词不分割)
https://vimsky.com/examples/usage/python-nltk-nltk-tokenize-mwe.html
NLTK中各种分词器的介绍:
https://zhuanlan.zhihu.com/p/108695887
https://www.cnblogs.com/expttt/articles/9357710.html
NLTK停用词使用教程:
https://blog.csdn.net/qq_38463737/article/details/111387831