> ## Documentation Index
> Fetch the complete documentation index at: https://docs.galtea.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# METEOR

> Evaluates translation, summarization, and paraphrasing by aligning words using exact matches, stems, or synonyms, computing precision and recall.

> [!WARNING]
>
> You are reading the docs of Galtea 5.11. [Read this page in the latest version](https://docs.galtea.ai/concepts/metric/meteor.md).

The METEOR (Metric for Evaluation of Translation with Explicit ORdering) metric is one of the [Deterministic Metric](https://docs.galtea.ai/v5.11/concepts/metric.md) Galtea exposes for evaluating machine translation, summarization, and paraphrasing tasks. It aims to correlate more closely with human judgments compared to [BLEU](https://docs.galtea.ai/v5.11/concepts/metric/bleu.md).

## Evaluation Parameters

To compute the `meteor` metric, the following parameters are required:

* **`actual_output`**: The model’s generated text.
* **`expected_output`**: The reference (or gold) text to compare against.

## How Is It Calculated?

METEOR improves upon [BLEU](https://docs.galtea.ai/v5.11/concepts/metric/bleu.md) by considering **semantic and morphological matches**:

1. **Alignment**\
   Tokens are matched between candidate and reference using:
   * **Exact matches**
   * **Stems** (e.g., "run" vs. "running")
   * **Synonyms** (e.g., "big" vs. "large")

2. **Precision & Recall**\
   Both are calculated from the aligned tokens.

3. **Fragmentation Penalty**\
   A penalty is applied if matches are scattered (fragmented alignment).

4. **Final Score**\
   The score is computed as:
   $$
   METEOR = F_{mean} \times (1 - Penalty)
   $$
   where F\_mean is the harmonic mean of precision and recall.

METEOR returns a score between **0 and 1**:

* **≥ 0.6** – High-quality translation/summary with semantic fidelity.
* **0.3 – 0.6** – Moderate quality; some paraphrasing or structural divergence.
* **\< 0.3** – Low-quality or semantically incorrect output.

## Suggested Test Case Types

Use METEOR when evaluating:

* **Machine Translation** with varied phrasings.
* **Abstractive Summarization** where synonyms are common.
* **Paraphrase Detection** with semantic variation.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.