Distribution

StructuredDistribution

class supar.structs.dist.StructuredDistribution(scores: Tensor, **kwargs)

Base class for structured distribution \(p(y)\) Eisner 2016,Goodman 1999,Li & Eisner (2009).

Parameters:

scores (torch.Tensor) – Log potentials, also for high-order cases.

property log_partition

Computes the log partition function of the distribution \(p(y)\).

property marginals

Computes marginal probabilities of the distribution \(p(y)\).

property max

Computes the max score of the distribution \(p(y)\).

property argmax

Computes \(\arg\max_y p(y)\) of the distribution \(p(y)\).

property mode

Returns the mode of the distribution.

kmax(k: int) → Tensor

Computes the k-max of the distribution \(p(y)\).

topk(k: int) → Tensor | Iterable

Computes the k-argmax of the distribution \(p(y)\).

sample()

Obtains a structured sample from the distribution \(y \sim p(y)\). TODO: multi-sampling.

property entropy

Computes entropy \(H[p]\) of the distribution \(p(y)\).

cross_entropy(other: StructuredDistribution) → Tensor

Computes cross-entropy \(H[p,q]\) of self and another distribution.

Parameters:

other (StructuredDistribution) – Comparison distribution.

kl(other: StructuredDistribution) → Tensor

Computes KL-divergence \(KL[p \parallel q]=H[p,q]-H[p]\) of self and another distribution.

Parameters:

other (StructuredDistribution) – Comparison distribution.

log_prob(value: LongTensor, *args, **kwargs) → Tensor

Computes log probability over values \(p(y)\).