tfa.text.crf_forward

View source on GitHub

Computes the alpha values in a linear-chain CRF.

Aliases:

• tfa.text.crf.crf_forward

tfa.text.crf_forward(
    inputs,
    state,
    transition_params,
    sequence_lengths
)

See http://www.cs.columbia.edu/~mcollins/fb.pdf for reference.

Args:

• inputs: A [batch_size, num_tags] matrix of unary potentials.
• state: A [batch_size, num_tags] matrix containing the previous alpha values.
• transition_params: A [num_tags, num_tags] matrix of binary potentials. This matrix is expanded into a [1, num_tags, num_tags] in preparation for the broadcast summation occurring within the cell.
• sequence_lengths: A [batch_size] vector of true sequence lengths.

Returns:

• new_alphas: A [batch_size, num_tags] matrix containing the new alpha values.