MantisAI/nervaluate

Full named-entity (i.e., not tag/token) evaluation metrics based on SemEval’13

62
/ 100
Established

When you're building systems that identify specific entities like people, organizations, or locations in text, it's crucial to accurately measure how well your system performs. This tool helps you evaluate your named entity recognition (NER) models by comparing your system's output against a set of known correct labels. It goes beyond simple word-by-word checks to tell you if the system got the whole entity right, partially right, or made a specific type of mistake. This is for anyone who needs to assess the quality of their text analysis systems, such as a computational linguist, data scientist, or researcher working with natural language processing.

206 stars. Available on PyPI.

Use this if you need a detailed and nuanced understanding of how accurately your named entity recognition (NER) model identifies specific entities in text, beyond just individual words.

Not ideal if you only need a basic, token-level accuracy report for your text classification tasks.

natural-language-processing text-analysis information-extraction computational-linguistics ai-model-evaluation
No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 17 / 25

How are scores calculated?

Stars

206

Forks

27

Language

Python

License

MIT

Last pushed

Mar 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/MantisAI/nervaluate"

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