disi-unibo-nlp/nlg-metricverse

[COLING22] An End-to-End Library for Evaluating Natural Language Generation

42
/ 100
Emerging

When developing or researching Natural Language Generation (NLG) models, it's crucial to accurately assess their output. This tool takes your model's generated text and a set of human-written reference texts, then calculates various automatic evaluation scores. It's designed for NLP researchers and engineers who need to understand and compare the quality of different NLG systems, such as those used for summarization, translation, or chatbots.

No commits in the last 6 months. Available on PyPI.

Use this if you are developing or fine-tuning NLG models and need a comprehensive, consistent way to evaluate their performance using a wide array of automatic metrics.

Not ideal if you primarily rely on human evaluation or only need a single, basic metric for a well-established NLG task.

natural-language-generation model-evaluation text-summarization machine-translation chatbot-development
Stale 6m
Maintenance 0 / 25
Adoption 9 / 25
Maturity 25 / 25
Community 8 / 25

How are scores calculated?

Stars

94

Forks

5

Language

Python

License

MIT

Last pushed

Dec 18, 2023

Commits (30d)

0

Dependencies

26

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/disi-unibo-nlp/nlg-metricverse"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.