tagger_data.py 文件源码

def tensorize(sentence, max_length):
  """ Input:
      - sentence: The sentence is a tuple of lists (s1, s2, ..., sk)
            s1 is always a sequence of word ids.
            sk is always a sequence of label ids.
            s2 ... sk-1 are sequences of feature ids,
              such as predicate or supertag features.
      - max_length: The maximum length of sequences, used for padding.
  """
  x = np.array([t for t in zip(*sentence[:-1])])
  y = np.array(sentence[-1])
  weights = (y >= 0).astype(float)
  x.resize([max_length, x.shape[1]])
  y.resize([max_length])
  weights.resize([max_length])
  return x, np.absolute(y), len(sentence[0]), weights