Use the power of machine learning to improve your metadata and enrich your content with the Scholarcy APIs. We can provision private API instances in the cloud or deploy on premises, giving you:

  • reference extraction and structuring as XML

  • metadata extraction

  • key phrase extraction

  • automated extraction of key highlights, findings, contributions, methods, results

  • extraction of tables from PDF to Excel or CSV

  • extraction of high-resolution images from PDF

You can try out some of this functionality for free at:

Reference Extraction API

Summarisation and highlights API

Scholarcy Labs

We also offer bespoke services such as training machine learning models on your own data, and development of automated conversion pipelines for your legacy content from PDF to XML.