Hi,I use the default jieba tokenizer tool and gensim/jieba keywords extractor tool to preprocess the corppus,but my result is not as good as you ,for example:
mine:['杨清', '孩子', '网友', '母亲', '小孩', '失望透顶', '父母', '发消息']
your:[ "王乐乐", "杨清柠", "奶粉", "外孙", "分手", "孩子"]
could you explain the tokenizer and keywords extractor tool that you use for more detail?
yahiko-l
commented
2 years ago
Hi,I use the default jieba tokenizer tool and gensim/jieba keywords extractor tool to preprocess the corppus,but my result is not as good as you ,for example: mine:['杨清', '孩子', '网友', '母亲', '小孩', '失望透顶', '父母', '发消息'] your:[ "王乐乐", "杨清柠", "奶粉", "外孙", "分手", "孩子"]
could you explain the tokenizer and keywords extractor tool that you use for more detail?