Case Study: Docusign achieves scalable document understanding with John Snow Labs

Docusign scales document understanding with John Snow Labs using CV, OCR, and NLP

DocuSign, a company that pioneered e-signature technology, sought to automate the extraction of structured information from a vast variety of document images like contracts and invoices. They faced challenges due to high layout variation, unbounded field complexity, and unstructured information, which made traditional rules-based extraction engines ineffective. To overcome this, DocuSign partnered with vendor John Snow Labs to leverage its Spark NLP for AI-powered document understanding.

The solution implemented by John Snow Labs used a unified approach combining computer vision, OCR, and NLP to learn high-level representations from data. This AI-driven method from Spark NLP allowed DocuSign to scalably process documents regardless of their format, effectively addressing the challenges of object size variation, context, and density to achieve automated information extraction.

Docusign