OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Evaluation & Observability

Files2Rouge

Files2Rouge is a command-line wrapper that calculates average ROUGE scores between reference and generated-summary files arranged with matching line counts. It reports scores by sequence and documents configurable ROUGE arguments, sentence delimiters, stemming behavior and saving results to a file. The repository also demonstrates calling the tool from Python.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Files2Rouge — OpenViST project profile in AI Evaluation & Observability.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when reference and generated summaries are available as two line-aligned files and you need ROUGE scores for their corresponding sequences.

Who it is for

  • Researchers and developers evaluating generated text summaries against reference summaries.
  • Developers adding file-based ROUGE scoring to a summarization evaluation script or command-line workflow.

Documented uses

  • Calculate ROUGE-1, ROUGE-2 and ROUGE-L scores for paired reference and summary sequences.
  • Save score output to a file or adjust ROUGE arguments and sentence boundaries.
  • Call the scoring wrapper from a Python script.
Before you choose

Requirements & limits

The public repository declares an MIT license.

  • Reference and summary files must have the same number of lines.
  • For multi-sentence sequences, choose the correct --eos delimiter; the README warns that a wrong delimiter may produce an incorrect ROUGE-L score.
  • The documented setup installs pyrouge from Git because the README says its PyPI package is out of date.
  • The README identifies a possible ROUGE-1.5.5.pl XML::Parser dependency error.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up Files2Rouge and score paired text files

Install the documented prerequisites and calculate ROUGE scores for line-matched reference and summary files.

Before you start

  • Python and pip, for the documented pyrouge installation and setup commands.
  • Reference and summary text files with the same number of lines.

Steps

  1. Install pyrouge from its Git repository with the command below.

    Documented command
    pip install -U git+https://github.com/pltrdy/pyrouge

  2. Clone https://github.com/pltrdy/files2rouge.git and change into the files2rouge directory.

  3. Run the command below, then the command below.

    Documented command
    python setup_rouge.py
    Documented command
    python setup.py install

  4. Run files2rouge references.txt summaries.txt, replacing the filenames with the input paths.

Expected outcome

The tool reports average ROUGE scores for the paired sequences; the documented output includes ROUGE-1, ROUGE-2 and ROUGE-L precision, recall and F-measure.

Guide limitations

  • The input files must have the same number of lines.
  • For sequences containing multiple sentences, set --eos to the sentence-ending delimiter; an incorrect delimiter may affect ROUGE-L.
  • The README notes a possible ROUGE-1.5.5.pl XML::Parser dependency error.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
pltrdy/files2rouge · Official homepage title · retained in its source language
How we review sourcesSuggest a correction