do_benchmark.py 文件源码

def nltk_parse_clause(sentence):
  """
  Natural Language Toolkit: code_cascaded_chunker
  http://www.nltk.org/book/ch07.html#code-cascaded-chunker
  """
  grammar = r"""
  NP: {<DT|JJ|NN.*>+}          # Chunk sequences of DT, JJ, NN
  PP: {<IN><NP>}               # Chunk prepositions followed by NP
  VP: {<VB.*><NP|PP|CLAUSE>+$} # Chunk verbs and their arguments
  CLAUSE: {<NP><VP>}           # Chunk NP, VP
  """
  cp = nltk.RegexpParser(grammar)
  #sentence = [("Mary", "NN"), ("saw", "VBD"), ("the", "DT"), ("cat", "NN"),  ("sit", "VB"), ("on", "IN"), ("the", "DT"), ("mat", "NN")]
  parsed_sentence = cp.parse(sentence)
  #print('parsed_sentence=', parsed_sentence)