Represents a parameter dictionary with a history, and contains other functionality around parameter passing and validation for AllenNLP.

The exception raised by any AllenNLP object when it's misconfigured (e.g. missing properties, invalid properties, unknown properties).

This class is for use when constructing objects using `FromParams`, when an argument to a constructor has a _sequential dependency_ with anot

A simple Shuffle-n language task.

Given an input shaped like `(batch_size, time_steps, [rest])` and a `Module` that takes inputs like `(batch_size, [rest])`, `TimeDistributed`

Prism color scale Args: palette: The color palette name

Prism fill scale Args: palette: The fill palette name

Pytorch has a number of built-in activation functions. We group those here under a common type, just to make it easier to configure and inst

This is the base class for all data instance processors that support a unified scratchpad. Unified scratchpad format looks like this: <sc

Add this class as a mixin base class to make sure your class's det_hash is derived exclusively from the parameters passed to __init__().

Add this class as a mixing base class to make sure your class's det_hash can be modified by altering a static `VERSION` member of your class.

This `Module` is a feed-forward neural network, just a sequence of `Linear` layers with activation functions in between. # Parameters

Mixin to give a from_params method to classes. We create a distinct base class for this because sometimes we want non-Registrable classes to

Any class that inherits from `Registrable` gains access to a named registry for its subclasses. To register them, just decorate them with the

Computes span representations by generating an unnormalized attention score for each word in the document. Spans representations are computed