Python自然语言处理学习笔记之信息提取步骤&分块(chunking)
摘要:一、信息提取模型 信息提取的步骤共分为五步,原始数据为未经处理的字符串,第一步:分句,用nltk.sent_tokenize(text)实现,得到一个list of strings第二步:分词,[nltk.word_tokenize(sent) for sent in sentences]实现...
阅读全文
posted @ 2015-08-24 19:37
posted @ 2015-08-24 19:37
posted @ 2015-08-24 11:53
posted @ 2015-08-24 10:20
posted @ 2015-08-23 21:18
posted @ 2015-08-16 00:46