TrainingHelper in Tensorflow seq2seq don't use start token as the initial input?

Question

In my understand, the first input of the decoder for seq2seq model is the start token. But when I read the code from TrainingHelper in tensorflow/contrib/seq2seq/python/ops/helper.py , I found it just return the first token of the target tokens as the first token:

  def initialize(self, name=None):
    with ops.name_scope(name, "TrainingHelperInitialize"):
      finished = math_ops.equal(0, self._sequence_length)
      all_finished = math_ops.reduce_all(finished)
      next_inputs = control_flow_ops.cond(
          all_finished, lambda: self._zero_inputs,
          lambda: nest.map_structure(lambda inp: inp.read(0), self._input_tas))
      return (finished, next_inputs)

Is that right?

Answer 1

Em... I have worked around nlp many times including seq2seq translation. But I have never heard about start token but only end token( EOF ).

Although my seq2seq task worked well without anything like start token, I'm not sure if it is a new technique. If it is, thank you let me know.

Answer 2

事实证明，您需要自己添加启动令牌，然后才能将其输入到TrainHelper中