RegExp and classfier used in part-of-speech(POS) tagging

来源:互联网 发布:淘宝上的银泰是正品吗 编辑:程序博客网 时间:2024/06/11 20:42
1. regular expression in pos
     judge the characteristic of a certain word by suffix pattern matching

点击(此处)折叠或打开

  1. >>> import nltk
  2. >>> from nltk.corpus import brown
  3. >>> brown_tagged_sents= brown.tagged_sents(categories='news')
  4. >>> brown_sents= brown.sents(categories='news')
  5. >>> patterns= [
  6. ...(r'.*ing$','VBG'),
  7. ...(r'.*ed$','VBD'),
  8. ...(r'.*es$','VBZ'),
  9. ...(r'.*ould$','MD'),
  10. ...(r'.*\'s$', 'NN$'),
  11. ... (r'.*s$', 'NNS'),
  12. ... (r'^-?[0-9]+(.[0-9]+)?$', 'CD'),
  13. ... (r'.*', 'NN')
  14. ... ]
  15. >>> regexp_tagger = nltk.RegexpTagger(patterns)
  16. >>> regexp_tagger.tag(brown_sents[3])[:10]
  17. [(u'``', 'NN'), (u'Only', 'NN'), (u'a', 'NN'), (u'relative', 'NN'), (u'handful', 'NN'), (u'of', 'NN'), (u'such', 'NN'), (u'reports', 'NNS'), (u'was', 'NNS'), (u'received', 'VBD

2. classfier in pos
    judge the characteristic of a certain word by suffix classfier
0 0