rouge and pythonrouge
The tools are ecosystem siblings: PythonRoug](B) is a Python wrapper that likely interfaces with an underlying ROUGE implementation, while `rouge` (A) is an independent JavaScript implementation of the ROUGE metric itself.
About rouge
kenlimmj/rouge
A Javascript implementation of the Recall-Oriented Understudy for Gisting Evaluation (ROUGE) evaluation metric for summaries.
This tool helps developers working on natural language processing projects to automatically evaluate the quality of text summaries. You provide a summary generated by your system and one or more reference summaries written by humans, and it outputs a score indicating how well your summary matches the references. This is designed for software engineers building and testing text summarization algorithms.
About pythonrouge
tagucci/pythonrouge
Python wrapper for evaluating summarization quality by ROUGE package
This tool helps researchers and developers working on text summarization evaluate how good their automatically generated summaries are. You provide your system's summaries and a set of human-written reference summaries, and it calculates various ROUGE scores like ROUGE-1, ROUGE-2, and ROUGE-SU4. This is for anyone building or comparing automated summarization models.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work