tfm.nlp.networks.SpanLabeling

Span labeling network head for BERT modeling.

tfm.nlp.networks.SpanLabeling(
    input_width,
    activation=None,
    initializer='glorot_uniform',
    output='logits',
    **kwargs
)

This network implements a simple single-span labeler based on a dense layer. Note that the network is constructed by Keras Functional API.

input_width The innermost dimension of the input tensor to this network.
activation The activation, if any, for the dense layer in this network.
initializer The initializer for the dense layer in this network. Defaults to a Glorot uniform initializer.
output The output style for this network. Can be either logits or predictions.

Methods

call

call(
    inputs, training=None, mask=None
)

Calls the model on new inputs and returns the outputs as tensors.

In this case call() just reapplies all ops in the graph to the new inputs (e.g. build a new computational graph from the provided inputs).

Args
inputs Input tensor, or dict/list/tuple of input tensors.
training Boolean or boolean scalar tensor, indicating whether to run the Network in training mode or inference mode.
mask A mask or list of masks. A mask can be either a boolean tensor or None (no mask). For more details, check the guide here.

Returns
A tensor if there is a single output, or a list of tensors if there are more than one outputs.