Skip to content
Calcrivo

METEOR Score Calculator

Calculate the METEOR score to evaluate translation quality with synonym matching.

Inputs

METEOR Score

0.6989

F-mean

0.7220

Fragmentation Penalty

0.0320

Step by step

  1. Precision: matches ÷ candidate length

    20 ÷ 25

    = 0.8000

  2. Recall: matches ÷ reference length

    20 ÷ 28

    = 0.7143

  3. F-mean (α=0.9): 10PR/(9P+R)

    10×0.800×0.714/(9×0.800+0.714)

    = 0.7220

  4. Fragmentation penalty: 0.5×(chunks/matches)³

    0.5×(8/20)³

    = 0.032000

  5. METEOR = F-mean × (1 − penalty)

    0.7220 × (1 − 0.0320)

    = 0.698917

How it works

METEOR improves on BLEU by incorporating recall, synonym matching, and stemming. It computes a weighted F-measure heavily favoring recall (α=0.9), then applies a fragmentation penalty that penalizes translations where matches are scattered rather than contiguous.

Formula

METEOR

METEOR = F_mean * (1 - 0.5*(chunks/matches)^3)

F_mean
Weighted harmonic mean: 10*P*R / (9P + R)
chunks
Number of contiguous matched segments

Frequently Asked Questions

How does METEOR handle synonyms?

METEOR uses WordNet synonym databases and stemming to match words that are semantically equivalent but lexically different (e.g., 'buy' and 'purchase'), giving it better correlation with human judgment than pure n-gram overlap methods.

Why does METEOR correlate better with human judgments than BLEU?

METEOR's recall emphasis, synonym matching, stemming, and fragmentation penalty all capture aspects of translation quality that humans care about but simple n-gram precision misses.

You might also need