tfa.text.crf_constrained_decode

Decode the highest scoring sequence of tags under constraints.

tfa.text.crf_constrained_decode(
    potentials: tfa.types.TensorLike,
    tag_bitmap: tfa.types.TensorLike,
    transition_params: tfa.types.TensorLike,
    sequence_length: tfa.types.TensorLike
) -> tf.Tensor

This is a function for tensor.

potentials A [batch_size, max_seq_len, num_tags] tensor of unary potentials.
tag_bitmap A [batch_size, max_seq_len, num_tags] boolean tensor representing all active tags at each index for which to calculate the unnormalized score.
transition_params A [num_tags, num_tags] matrix of binary potentials.
sequence_length A [batch_size] vector of true sequence lengths.

decode_tags A [batch_size, max_seq_len] matrix, with dtype tf.int32. Contains the highest scoring tag indices.
best_score A [batch_size] vector, containing the score of decode_tags.