tfm.nlp.models.XLNetSpanLabeler

View source on GitHub

Span labeler model based on XLNet.

tfm.nlp.models.XLNetSpanLabeler(
    network: Union[tf.keras.layers.Layer, tf.keras.Model],
    start_n_top: int = 5,
    end_n_top: int = 5,
    dropout_rate: float = 0.1,
    span_labeling_activation: tf.keras.initializers.Initializer = 'tanh',
    initializer: tf.keras.initializers.Initializer = 'glorot_uniform',
    **kwargs
)

This is an implementation of the network structure surrounding a Transformer-XL encoder as described in "XLNet: Generalized Autoregressive Pretraining for Language Understanding" (https://arxiv.org/abs/1906.08237).

Args
network	A transformer network. This network should output a sequence output and a classification output. Furthermore, it should expose its embedding table via a "get_embedding_table" method.
start_n_top	Beam size for span start.
end_n_top	Beam size for span end.
dropout_rate	The dropout rate for the span labeling layer.
span_labeling_activation	The activation for the span labeling head.
initializer	The initializer (if any) to use in the span labeling network. Defaults to a Glorot uniform initializer.

Attributes
checkpoint_items

Methods

call

View source

call(
    inputs: Mapping[str, Any]
)

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.