JAVA:如何将 Gazettes 与 Stanford NLP 结合使用？

Question

我读了这个faq但我不明白。我尝试使用这段代码:

   Properties pp=new Properties();  
   pp.put("annotators", "tokenize, ssplit, pos, lemma, ner, parse");
   pp.put("ner.useSUTime","false");

   pp.put("useGazettes","true");
   pp.put("gazette","C:\\gaz.txt");

   StanfordCoreNLP s=new StanfordCoreNLP(pp);

This is String: "Dan 于 2008 年成为 Music Friends Association 的成员"

公报文件是:

  CLASS Music friends association 

但是“乐友会”不被NER认可。

我哪里错了？

Answer 1

那里给出了答案:

If a gazette is used, this does not guarantee that words in the gazette are always used as a member of the intended class, and it does not guarantee that words outside the gazette will not be chosen. It simply provides another feature for the CRF to train against. If the CRF has higher weights for other features, the gazette features may be overwhelmed.

因此不能保证您的短语会以任何方式被标记。替代方案是

either the regexner or the tokensregex tools included in Stanford CoreNLP