0 / 0

METEOR evaluation metric

Last updated: May 08, 2025
METEOR evaluation metric

The METEOR (Metric for Evaluation of Translation with Explicit ORdering) metric measures how well text that is generated with machine translations match the structure of the text from reference translations.

Metric details

METEOR is a generative AI quality evaluation metric that measures how well generative AI assets perform tasks.

Scope

The METEOR metric evaluates generative AI assets only.

  • Types of AI assets: Prompt templates
  • Generative AI tasks:
    • Text summarization
    • Content generation
  • Supported languages: English

Scores and values

The METEOR metric score indicates how closely machine translations match with references. Higher scores indicate that machine translations match more closely with references.

  • Range of values: 0.0-1.0
  • Best possible score: 1.0

Settings

  • Thresholds:
    • Lower limit: 0
    • Upper limit: 1
  • Parameters:
    • Alpha: Controls relative weights of precision and recall
    • Beta: Controls shape of penalty as a function of fragmentation
    • Gamma: The relative weight assigned to fragmentation penalty

Parent topic: Evaluation metrics