tf.contrib.crf.viterbi_decode(score, transition_params) Decode the highest scoring sequence of tags outside of TensorFlow.

tf.contrib.crf.crf_log_norm(inputs, sequence_lengths, transition_params) Computes the normalization for a CRF.

tf.contrib.crf.CrfForwardRnnCell.zero_state(batch_size, dtype) Return zero-filled state tensor(s). Args:

tf.contrib.crf.crf_log_likelihood(inputs, tag_indices, sequence_lengths, transition_params=None) Computes the log-likehood of

tf.contrib.crf.CrfForwardRnnCell.state_size

tf.contrib.crf.CrfForwardRnnCell.output_size

tf.contrib.crf.CrfForwardRnnCell.__call__(inputs, state, scope=None) Build the CrfForwardRnnCell. Args:

tf.contrib.crf.crf_unary_score(tag_indices, sequence_lengths, inputs) Computes the unary scores of tag sequences.

tf.contrib.crf.crf_sequence_score(inputs, tag_indices, sequence_lengths, transition_params) Computes the unnormalized score for

class tf.contrib.crf.CrfForwardRnnCell Computes the alpha values in a linear-chain CRF. See