rbnet.pcfg.ExpandedPCFG

class rbnet.pcfg.ExpandedPCFG(non_terminals, terminals, non_term_variables, rules, start)

Bases: PCFG

An ExpandedPCFG…

Parameters:

• non_terminals – list or array of non-terminal symbols

• terminals – list or array of terminal symbols

• non_term_variables – list of non-terminal variables corresponding to the non-terminal symbols

• rules – iterable of rules-weight-transition tuples with rules provided either as strings of the form (“X –> Y Z”, w, t) or (“X –> Y”, w, t) for non-terminal and terminal rules, respectively (symbols have to be strings without whitespace for this), or of the form ((X, (Y, Z)), w, t) or ((X, (Y,)), w, t) for arbitrary symbols, where w is the rule weight, and t is the transition for the corresponding variables.

• start – the start symbol

Public Data Attributes:

Inherited from PCFG

dump_patches
training
call_super_init
forward(*input)	Define the computation performed at every call.

Inherited from SequentialRBN

root_location	Return the location of the root variables.
inside_chart	Return the chart with inside probabilities for all variables.
terminal_chart	Return the chart with terminal variables.
prior	Return the prior transition (typically an instance of Prior), which has to implement Prior.marginal_likelihood().
dump_patches
training
call_super_init
forward(*input)	Define the computation performed at every call.

Inherited from RBN

root_location	Return the location of the root variables.
inside_chart	Return the chart with inside probabilities for all variables.
terminal_chart	Return the chart with terminal variables.
prior	Return the prior transition (typically an instance of Prior), which has to implement Prior.marginal_likelihood().

Inherited from Module

dump_patches
call_super_init
T_destination
training

Public Methods:

__init__(non_terminals, terminals, ...)

An ExpandedPCFG...

Inherited from PCFG

__init__(cells, prior, terminal_indices, ...)
tokenise(sequence)
init_inside(sequence)	Initialise for parsing a new input.
map_inside_chart([precision])

Inherited from SequentialRBN

__init__(cells, prior, *args, **kwargs)
init_inside(sequence)	Initialise for parsing a new input.
inside_schedule(*args, **kwargs)	Iterate through (batches of) non-terminal locations for computing inside probabilities.
cells()	Return iterable over cells (corresponding to the non-terminal variables).
update_inside_chart(var_idx, locations, values)	For the specified variable, update the chart for inside probabilities with given values at given locations.

Inherited from RBN

__init__(*args, **kwargs)
inside_schedule(*args, **kwargs)	Iterate through (batches of) non-terminal locations for computing inside probabilities.
cells()	Return iterable over cells (corresponding to the non-terminal variables).
init_inside(*args, **kwargs)	Initialise for parsing a new input.
update_inside_chart(var_idx, locations, values)	For the specified variable, update the chart for inside probabilities with given values at given locations.
inside(*args, **kwargs)	Compute the inside probabilities and return the marginal data likelihood.

Inherited from Module

__init__(*args, **kwargs)	Initialize internal Module state, shared by both nn.Module and ScriptModule.
forward(*input)	Define the computation performed at every call.
register_buffer(name, tensor[, persistent])	Add a buffer to the module.
register_parameter(name, param)	Add a parameter to the module.
add_module(name, module)	Add a child module to the current module.
register_module(name, module)	Alias for add_module().
get_submodule(target)	Return the submodule given by target if it exists, otherwise throw an error.
set_submodule(target, module)	Set the submodule given by target if it exists, otherwise throw an error.
get_parameter(target)	Return the parameter given by target if it exists, otherwise throw an error.
get_buffer(target)	Return the buffer given by target if it exists, otherwise throw an error.
get_extra_state()	Return any extra state to include in the module's state_dict.
set_extra_state(state)	Set extra state contained in the loaded state_dict.
apply(fn)	Apply fn recursively to every submodule (as returned by .children()) as well as self.
cuda([device])	Move all model parameters and buffers to the GPU.
ipu([device])	Move all model parameters and buffers to the IPU.
xpu([device])	Move all model parameters and buffers to the XPU.
mtia([device])	Move all model parameters and buffers to the MTIA.
cpu()	Move all model parameters and buffers to the CPU.
type(dst_type)	Casts all parameters and buffers to dst_type.
float()	Casts all floating point parameters and buffers to float datatype.
double()	Casts all floating point parameters and buffers to double datatype.
half()	Casts all floating point parameters and buffers to half datatype.
bfloat16()	Casts all floating point parameters and buffers to bfloat16 datatype.
to_empty(*, device[, recurse])	Move the parameters and buffers to the specified device without copying storage.
to(*args, **kwargs)	Move and/or cast the parameters and buffers.
register_full_backward_pre_hook(hook[, prepend])	Register a backward pre-hook on the module.
register_backward_hook(hook)	Register a backward hook on the module.
register_full_backward_hook(hook[, prepend])	Register a backward hook on the module.
register_forward_pre_hook(hook, *[, ...])	Register a forward pre-hook on the module.
register_forward_hook(hook, *[, prepend, ...])	Register a forward hook on the module.
__call__(*args, **kwargs)	Call self as a function.
__getstate__()
__setstate__(state)
__getattr__(name)
__setattr__(name, value)	Implement setattr(self, name, value).
__delattr__(name)	Implement delattr(self, name).
register_state_dict_post_hook(hook)	Register a post-hook for the state_dict() method.
register_state_dict_pre_hook(hook)	Register a pre-hook for the state_dict() method.
state_dict(*args[, destination, prefix, ...])	Return a dictionary containing references to the whole state of the module.
register_load_state_dict_pre_hook(hook)	Register a pre-hook to be run before module's load_state_dict() is called.
register_load_state_dict_post_hook(hook)	Register a post-hook to be run after module's load_state_dict() is called.
load_state_dict(state_dict[, strict, assign])	Copy parameters and buffers from state_dict into this module and its descendants.
parameters([recurse])	Return an iterator over module parameters.
named_parameters([prefix, recurse, ...])	Return an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.
buffers([recurse])	Return an iterator over module buffers.
named_buffers([prefix, recurse, ...])	Return an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.
children()	Return an iterator over immediate children modules.
named_children()	Return an iterator over immediate children modules, yielding both the name of the module as well as the module itself.
modules()	Return an iterator over all modules in the network.
named_modules([memo, prefix, remove_duplicate])	Return an iterator over all modules in the network, yielding both the name of the module as well as the module itself.
train([mode])	Set the module in training mode.
eval()	Set the module in evaluation mode.
requires_grad_([requires_grad])	Change if autograd should record operations on parameters in this module.
zero_grad([set_to_none])	Reset gradients of all model parameters.
share_memory()	See torch.Tensor.share_memory_().
extra_repr()	Set the extra representation of the module.
__repr__()	Return repr(self).
__dir__()	Default dir() implementation.
compile(*args, **kwargs)	Compile this Module's forward using torch.compile().

Private Data Attributes:

_abc_impl

Inherited from PCFG

_abc_impl
_version	This allows better BC support for load_state_dict().
_parameters
_buffers
_non_persistent_buffers_set
_backward_pre_hooks
_backward_hooks
_is_full_backward_hook
_forward_hooks
_forward_hooks_with_kwargs
_forward_hooks_always_called
_forward_pre_hooks
_forward_pre_hooks_with_kwargs
_state_dict_hooks
_load_state_dict_pre_hooks
_state_dict_pre_hooks
_load_state_dict_post_hooks
_modules
_compiled_call_impl

Inherited from SequentialRBN

_abc_impl
_version	This allows better BC support for load_state_dict().
_parameters
_buffers
_non_persistent_buffers_set
_backward_pre_hooks
_backward_hooks
_is_full_backward_hook
_forward_hooks
_forward_hooks_with_kwargs
_forward_hooks_always_called
_forward_pre_hooks
_forward_pre_hooks_with_kwargs
_state_dict_hooks
_load_state_dict_pre_hooks
_state_dict_pre_hooks
_load_state_dict_post_hooks
_modules
_compiled_call_impl

Inherited from RBN

_abc_impl

Inherited from ABC

_abc_impl

Inherited from Module

_version	This allows better BC support for load_state_dict().
_compiled_call_impl
_parameters
_buffers
_non_persistent_buffers_set
_backward_pre_hooks
_backward_hooks
_is_full_backward_hook
_forward_hooks
_forward_hooks_with_kwargs
_forward_hooks_always_called
_forward_pre_hooks
_forward_pre_hooks_with_kwargs
_state_dict_hooks
_load_state_dict_pre_hooks
_state_dict_pre_hooks
_load_state_dict_post_hooks
_modules

Private Methods:

Inherited from Module

_apply(fn[, recurse])
_get_backward_hooks()	Return the backward hooks for use in the call function.
_get_backward_pre_hooks()
_maybe_warn_non_full_backward_hook(inputs, ...)
_slow_forward(*input, **kwargs)
_wrapped_call_impl(*args, **kwargs)
_call_impl(*args, **kwargs)
_register_state_dict_hook(hook)	Register a post-hook for the state_dict() method.
_save_to_state_dict(destination, prefix, ...)	Save module state to the destination dictionary.
_register_load_state_dict_pre_hook(hook[, ...])	See register_load_state_dict_pre_hook() for details.
_load_from_state_dict(state_dict, prefix, ...)	Copy parameters and buffers from state_dict into only this module, but not its descendants.
_named_members(get_members_fn[, prefix, ...])	Help yield various names + members of modules.
_get_name()
_replicate_for_data_parallel()

---