Identify 50+ Entity Types in 47 Languages

The Problem:

Good NER Systems Are Hard to Find, Especially Self-Hosted Ones

Current Named Entity Recognition (NER) systems typically only work in English and support a handful of entity types. Such systems usually also aren’t focused on entities that matter for businesses, such as money amounts and mailing addresses.

Furthermore, most systems are limited to producing a single label per entity, rendering them unable to produce rich label structures.

Enter Private AI:

Realtime Entity Detection in 47 Languages

Private AI’s entity detection engine can be used for general-purpose NER. Find ZIP codes, addresses, drug mentions and more in over 30 languages. Each entity can have multiple tags, allowing for richer entity information. 

Easily and cost efficiently support billions of inferences per month, all hosted in your own environment.

Why Private AI

Unrivalled Accuracy

Private AI uses the latest advancements in machine learning to achieve remarkable accuracy out of the box. See how we stack up against our competitors in our technical whitepaper

Private AI
Major Cloud Provider 2
Open Source Software 2
Open Source Software 1
Major Cloud Provider 1
Major Cloud Provider 3
0.80 0.90 1

Try it yourself on your own data:

Private AI’s de-identification solution was extremely easy to integrate with our current pipeline, requiring only a few lines of code to ensure GDPR-compliant data handling for our users’ sensitive information. As a data anonymizer it was accurate and highly performant, allowing us to offer superior privacy protection without affecting our rates of service. Importantly, it enabled us to meet the rigorous data privacy requirements of the financial services sector without having to break the bank.

Damian Tran
CTO, Minerva AI

99.5%+ Accuracy

Number quoted is the number of PII words missed as a fraction of total number of words. Computed on a 268 thousand word internal test dataset, comprising data from over 50 different sources, including web scrapes, emails and ASR transcripts.

Please contact us for a copy of the code used to compute these metrics, try it yourself here, or download our whitepaper.


Tested on a dataset composed of messy conversational data containing sensitive health information. Download our whitepaper for further details, as well as how we perform on precision and F1-score or contact us to get a copy of the evaluation code.


Testé sur un ensemble de données composé de données conversationnelles désordonnées contenant des informations de santé sensibles. Téléchargez notre livre blanc pour plus de détails, ainsi que nos performances en termes d’exactitude et de score F1, ou contactez-nous pour obtenir une copie du code d’évaluation.