Enum SmoothingMethod 

pub enum SmoothingMethod {
    None,
    AddOne,
    ExpDecay,
}

Smoothing strategy for sentence-level / sparse BLEU.

Corpus-level BLEU aggregates counts first and should generally use SmoothingMethod::None.

Variants

None

No smoothing (classic Papineni — geometric mean may go to 0).

AddOne

Add 1 to both numerator and denominator of each p_n.

This is Chen & Cherry 2014 method 2 (a.k.a. Laplace / Lidstone-1).

ExpDecay

Exponentially decaying smoothing (Chen & Cherry 2014 method 3).

When a modified precision is zero, fall back to 1 / (2^k · c) for the k-th consecutive zero, where c is candidate length.

Trait Implementations

impl Clone for SmoothingMethod

fn clone(&self) -> SmoothingMethod

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for SmoothingMethod

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for SmoothingMethod

fn default() -> SmoothingMethod

Returns the “default value” for a type.

impl PartialEq for SmoothingMethod

fn eq(&self, other: &SmoothingMethod) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Copy for SmoothingMethod

impl Eq for SmoothingMethod

impl StructuralPartialEq for SmoothingMethod