BLEUAlgorithm class

Static helpers for computing BLEU scores.

See: Papineni et al. (2002), and the NLTK reference implementation.

Constructors

BLEUAlgorithm()

Properties

hashCode → int

The hash code for this object.

no setter, inherited

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

Methods

noSuchMethod(Invocation invocation) → dynamic

Invoked when a nonexistent method or property is accessed.

inherited

toString() → String

A string representation of this object.

inherited

Operators

operator ==(Object other) → bool

The equality operator.

inherited

Static Properties

defaultBLEUWeights → List<double>

Default weights: uniform 0.25 for 1–4 gram.

final

Static Methods

brevityPenalty(int closestRef, int hypLength) → double

Brevity penalty: penalizes hypotheses shorter than references.

closestRefLength(List<List<String>> references, int hypLength) → int

Returns the reference length closest to hypLength.

equalWeights(int n) → List<double>

Generates n equal weights summing to 1.0.

modifiedPrecision(List<List<String>> references, List<String> hypothesis, {required int n}) → RationalNumber

Modified n-gram precision (clipped against reference counts).

sentenceBLEU(List<List<String>> references, List<String> hypothesis, {List<double>? weights, List<double> smoothingFunction(List<RationalNumber>, int)?}) → double

Computes the sentence-level BLEU score.