Named Entities Extraction

Named Entities Extraction is the process of recognizing various kinds of entities (persons, cities, diseases, …) in documents, and tagging each text with the named entities that it contains.

Dataiku provides several named entities extraction capabilities

Native entity extraction

The native entity extraction capability of Dataiku extracts information about people, dates, places, …

It is an offline capability, meaning that it does not leverage a 3rd party API.

Extraction is provided in 7 languages

Note

This capability is provided by the “Named Entities Recognition” plugin, which you need to install. Please see Installing plugins.

This plugin is Not supported

Please see our Named entity recognition plugin page for detailed documentation.

AWS Comprehend

The AWS Comprehend integration provides named entity recognition in 12 languages.

Please see NLP using AWS APIs for more details

Azure Cognitive Services

The Azure Cognitive Services integration provides named entity recognition in 23 languages.

Please see NLP using Azure APIs for more details

Google Cloud NLP

The Google Cloud NLP integration provides named entity recognition in 11 languages.

Please see NLP using Google APIs for more details