nltk.py 文件源码

def pyrata2conll (dictList, **kwargs):
  """ 
  See 3.1   Reading IOB Format and the CoNLL 2000 Corpus http://www.nltk.org/book/ch07.html

  can be used wi
  nltk.chunk.conllstr2tree(text, chunk_types=['NP']).draw()
  """

  if 'raw' in kwargs.keys(): 
    rawFeatureName = kwargs['raw']
  if 'pos' in kwargs.keys(): 
    posFeatureName = kwargs['pos']   
  if 'chunk' in kwargs.keys(): 
    chunkFeatureName = kwargs['chunk']

  text = ''
  for e in dictList:
    text.append(' '.join([e[rawFeatureName], e[posFeatureName], e[chunkFeatureName], '\n']))

  return text


# extend a given dictList 

# merge dictList

# """"""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""
# Run all the tests
# """"""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""