View source on GitHub
|
Additional text-processing ops.
Modules
crf module
Classes
class CRFModelWrapper: A model grouping layers into an object with training/inference features.
class CrfDecodeForwardRnnCell: Computes the forward decoding in a linear-chain CRF.
Functions
crf_binary_score(...): Computes the binary scores of tag sequences.
crf_constrained_decode(...): Decode the highest scoring sequence of tags under constraints.
crf_decode(...): Decode the highest scoring sequence of tags.
crf_decode_backward(...): Computes backward decoding in a linear-chain CRF.
crf_decode_forward(...): Computes forward decoding in a linear-chain CRF.
crf_filtered_inputs(...): Constrains the inputs to filter out certain tags at each time step.
crf_forward(...): Computes the alpha values in a linear-chain CRF.
crf_log_likelihood(...): Computes the log-likelihood of tag sequences in a CRF.
crf_log_norm(...): Computes the normalization for a CRF.
crf_multitag_sequence_score(...): Computes the unnormalized score of all tag sequences matching tag_bitmap.
crf_sequence_score(...): Computes the unnormalized score for a tag sequence.
crf_unary_score(...): Computes the unary scores of tag sequences.
parse_time(...): Parse an input string according to the provided format string into a Unix time.
skip_gram_sample(...): Generates skip-gram token and label paired Tensors from the input tensor.
skip_gram_sample_with_text_vocab(...): Skip-gram sampling with a text vocabulary file.
viterbi_decode(...): Decode the highest scoring sequence of tags outside of TensorFlow.