NLG-eval
A Python library for evaluating natural language generation models using multiple unsupervised automated metrics.
What is NLG-eval?
nlg-eval is a Python library for evaluating natural language generation models using multiple unsupervised automated metrics. It computes scores like BLEU, METEOR, ROUGE, and CIDEr by comparing generated text (hypotheses) against reference texts, helping researchers assess model performance quantitatively.
Researchers and developers working on natural language generation, machine translation, text summarization, or dialogue systems who need standardized evaluation metrics.
It consolidates multiple NLG metrics into a single, easy-to-use package with flexible APIs, reducing the need to implement each metric separately and ensuring consistent evaluation across projects.
Overview
Evaluation code for various unsupervised automated metrics for Natural Language Generation.
Use Cases
Best For
- Evaluating machine translation models with BLEU and METEOR scores
- Assessing text summarization systems using ROUGE metrics
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.