自然语言处理nltk分词断句（2）

from nltk.corpus import gutenberg
import nltk


# file = gutenberg.words('melville-moby_dick.txt')
# text = nltk.Text(file)
# print(file)
# print(text)
# print(text.findall('<a> (<.*>) <man>'))
# 对Text对象使用findall的特殊方式
# this is not a list


# test_string = '''Over the last 10 years, I have used and tweaked Vim. 
# This configuration is the ultimate vimrc 
# (or at least my version of it).'''
# print(nltk.word_tokenize(test_string))


# 词干提取
# porter = nltk.PorterStemmer()
# lancaster = nltk.LancasterStemmer()
# test_list = gutenberg.words('melville-moby_dick.txt')[:10]
# list_by_porter = [porter.stem(word) for word in test_list]
# list_by_lancaster = [lancaster.stem(word) for word in test_list]
# print('the oringin:',test_list)
# print('porter stem:',list_by_porter)
# print('lancaster stem:',list_by_lancaster)


# test_list = gutenberg.words('melv

最后

以上就是伶俐大叔为你收集整理的自然语言处理nltk分词断句（2）的全部内容，希望文章能够帮你解决自然语言处理nltk分词断句（2）所遇到的程序开发问题。

如果觉得靠谱客网站的内容还不错，欢迎将靠谱客网站推荐给程序员好友。