tf.contrib.crf.crf_sequence_score

Computes the unnormalized score for a tag sequence.

tf.contrib.crf.crf_sequence_score(
    inputs, tag_indices, sequence_lengths, transition_params
)

Args
inputs	A [batch_size, max_seq_len, num_tags] tensor of unary potentials to use as input to the CRF layer.
tag_indices	A [batch_size, max_seq_len] matrix of tag indices for which we compute the unnormalized score.
sequence_lengths	A [batch_size] vector of true sequence lengths.
transition_params	A [num_tags, num_tags] transition matrix.

Returns
sequence_scores	A [batch_size] vector of unnormalized sequence scores.