Text summarization

Text summarization is the process of generating a summary of documents which could be considered as too long.

Extractive summarization extracts the most relevant sentences from the document. Abstractive summarization generates a summary that is not extracted from the original document, but fully generated.

Offline Text Summarization

The native text summarization capability of Dataiku provides language-agnostic extractive summarization using open-source models. It is an offline capability, meaning that it does not leverage a 3rd party API.

Note

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

This plugin is Not supported

Please see our Text summarization plugin page for detailed documentation.

Crowlingo

The Crowlingo integration provides summarization detection in 102 languags.

Please see NLP with Crowlingo API for more details

MeaningCloud

The MeaningCloud integration provides language-agnostic summarization

Please see NLP with MeaningCloud API for more details