|View source on GitHub|
Computes the unnormalized score of all tag sequences matching tag_bitmap.
tfa.types.TensorLike) -> tf.Tensor
tag_bitmap enables more than one tag to be considered correct at each time step. This is useful when an observed output at a given time step is consistent with more than one tag, and thus the log likelihood of that observation must take into account all possible consistent tags.
Using one-hot vectors in tag_bitmap gives results identical to crf_sequence_score.
||A [batch_size] vector of unnormalized sequence scores.|