---
id: rouge
version: "1.0.1"
license: LICENCE.txt
license_treatment: unclear
maintenance: dormant
---

# rouge — Full Python ROUGE Score Implementation (not a wrapper)

License: unclear · Maintenance: dormant · Downloads: 898.4K/mo

## What it is and what it does

Rouge is a pure Python implementation of the ROUGE metric, a standard evaluation framework for text summarization. It computes precision, recall, and F1 scores across ROUGE-1 (unigram), ROUGE-2 (bigram), and ROUGE-L (longest common subsequence) variants to quantify how well a generated summary matches reference text. The package works both as a command-line tool and as a library, accepting single sentences, multiple sentence pairs, or entire files for batch scoring.

The implementation is independent from the official ROUGE-155 script, so results may differ slightly. It depends only on six and installs with low friction. The codebase is dormant (last release July 2021), so it receives no active maintenance, though the repository remains unarchived and the code is stable for existing use cases.

Use it for:

- Evaluate abstractive text summarization models by comparing generated summaries to human-written references
- Batch-score multiple hypothesis-reference pairs from files to assess summarization system performance
- Integrate ROUGE scoring into NLP evaluation pipelines for research or production summarization systems
- Command-line scoring of individual text pairs without writing Python code

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Computes ROUGE scores (Recall-Oriented Understudy for Gisting Evaluation) to measure text summarization quality by comparing generated text against reference text.

Yes, if you need ROUGE scoring for summarization evaluation and can accept dormant maintenance. The package is lightweight, has no known vulnerabilities, and works reliably for its stated purpose. However, verify that slight differences from official ROUGE-155 are acceptable for your use case, and be aware that no updates are forthcoming—use it as a stable tool, not one under active development.

## Install

pip install rouge
uv add rouge
poetry add rouge

## Installing rouge

Before you install: Low friction: pure Python wheel with a single dependency (six). Maintenance is dormant—last release was 2021-07-20 and no commits since 2024-11-19—so expect no active bug fixes or feature updates.

License in practice: License treatment is unclear: the package references LICENCE.txt but provides no SPDX identifier. Review the repository's license file before adopting in proprietary or license-sensitive contexts.

Quickstart:

pip install rouge

from rouge import Rouge

rouge = Rouge()
scores = rouge.get_scores(
    "generated summary text",
    "reference summary text"
)
print(scores)

Verify before relying:

- How closely results match the official ROUGE-155 implementation beyond the acknowledged slight differences mentioned in the repository
- Whether the package is actively maintained or if dormancy poses risks for new Python versions or dependencies

## Package facts

- License: LICENCE.txt (unclear)
- Python support: unspecified
- Install friction: low
- Maintenance: dormant
- Downloads: 898.4K/month (top 5,000 on PyPI)
- Known vulnerabilities: none known

## Tags

ROUGE score calculation, text summarization evaluation, summary quality metrics, NLG evaluation metric, text comparison scoring, nlp-evaluation, summarization-metrics

[View on SkillFed](https://skillfed.io/packages/rouge) · [View on PyPI](https://pypi.org/project/rouge/)