Computes the log-likelihood of tag sequences in a CRF.
crf_log_likelihood(
inputs,
tag_indices,
sequence_lengths,
transition_params = NULL
)
A [batch_size, max_seq_len, num_tags] tensor of unary potentials to use as input to the CRF layer.
A [batch_size, max_seq_len] matrix of tag indices for which we compute the log-likelihood.
A [batch_size] vector of true sequence lengths.
A [num_tags, num_tags] transition matrix, if available.
log_likelihood: A [batch_size] Tensor containing the log-likelihood of each example, given the sequence of tag indices. transition_params: A [num_tags, num_tags] transition matrix. This is either provided by the caller or created in this function.