Natural language processing

Trend 7: Derive content intelligence from forms extraction, document attributes and paragraphs

Enterprises have information embedded in various types of documents and in the form of digital or handwritten content. These include research study documents, Know Your Customer forms, payslips and invoices. Extracting key information points and systematically digitizing this information are key problems and the driving pattern across various industries.

Infosys worked with a large global pharmaceutical company and used NLP techniques to extract various product characteristics — such as the chemical composition of drugs, posology, severity and comorbidity — from clinical research documents.

Infosys partnered with a large global seed manufacturer to extract various information data points from intellectual property documents related to studies and details of various experiments that were spread across geographies in different shared locations, languages and versions.

Infosys assisted a large bank with a solution that digitized information received from various vendors in the form of invoices that were in different formats and file types.

At Infosys, several data points get captured as part of client contracts. We are extracting sensitive financial information, such as contract name, value, start date, end date and other sensitive clauses, such as liability and indemnity, from contract documents using AI-based techniques.

Subscribe

To keep yourself updated on the latest technology and industry trends subscribe to the Infosys Knowledge Institute’s publications

Infosys TechCompass