- 1、安装
pip install pattern
- 2、功能特点
爬虫+自然语言处理+图谱(如果没理解错的话)
- 3、自然语言处理
包括六种语言en | es | de | fr | it | nl
具体关注英语
(1)Parser
TAG CHUNK(组块分析) ROLE(角色标注) POS(词性标注)
(2)文本分类
(polarity, subjectivity)
fact opinion
positive negative
(3)wordnet
词的定义,近义词。。。词的相似度
(4)常用词表
ACADEMIC | English academic words | 500 | criterion, proportionally, research |
BASIC | English basic words | 1,000 | chicken, pain, road |
PROFANITY | English swear words | 350 | |
TIME | English time & date words | 100 | Christmas, past, saturday |