get_sampling_probability

opennmt.decoders.get_sampling_probability(step, read_probability=None, schedule_type=None, k=None)

Returns the sampling probability as described in https://arxiv.org/abs/1506.03099.

Parameters

• step – The training step.

• read_probability – The probability to read from the inputs.

• schedule_type – The type of schedule: “constant”, “linear”, “exponential”, or “inverse_sigmoid”.

• k – The convergence constant.

Returns

The probability to sample from the output ids as a 0D tf.Tensor or None if scheduled sampling is not configured.

Raises

• ValueError – if schedule_type is set but not k or if schedule_type is linear but an initial read_probability is not set.

• TypeError – if schedule_type is invalid.