Abstract:

New automation technologies and workflows, most notably semantic recognition, Natural Language Processing (NLP), and Optical Character Recognition (OCR), eliminate many of the difficulties typically associated with data mining of unstructured, text-based documents. By augmenting this with visual verification and quality control, Brightleaf Solutions now delivers abstracted data at Six Sigma-level accuracy.

While text-based documents can be searched using simple search algorithms, extracting the correct data from these unstructured documents has always been an arduous task. Without a clear solution, the problem remains: how do you consolidate unstructured data in a way that multiple users run access it to run database queries and reports?  The most common way to accomplish this is methodically review each unstructured document and using manual “cut and paste” to populate the values into an Excel spreadsheet.  This has proven problematic because with all the tedious, repetitive manual efforts, there is huge potential for errors and omissions.  Large abstraction projects may require a team of people doing the abstraction and thus requiring hiring, training, replacing and managing the staff. Plus, with text documents, you have additional concerns with large variances in both language and translation and OCR errors if the original documents were paper-based.

To remedy this, Samir Bhatia the President and CEO of Brightleaf Solutions, Inc., has brought a ‘technology enabled solution’ to market for legal documents that delivers 99.99% accuracy. It is accomplished through a combination of software, people, and a Six Sigma process for quality review.

“In a contract, for example, you can have expiry dates, penalty clauses, incentive functions and a myriad of other terms and conditions that often have a significant legal or financial impact on your business,” said Mr. Bhatia. “We developed our Semantic Intelligence/Natural Language Processing engine to extract any and all critical data from contracts. The engine is customized to each client’s data requirements and unique contract language by a finely tuned configuration process. After the software extracts most of the critical elements, our team of seasoned lawyers, financial, and business analysts utilize our Six Sigma process to identify and fix errors and to resolve any ambiguity in the results.  The combination of our software and a multiple step review by our team delivers data at unmatched levels of accuracy.”

The software engine was developed in conjunction with Nihilent Technologies Limited of Pune, India.  Mr. Minoo Dastur, President and COO of Nihilent Technologies adds, “We were extremely delighted to have worked with Brightleaf.  Our close alliance with Brightleaf’s legal staff enabled our companies to collaborate on every aspect of the development of an advanced semantic software platform. With the addition of machine learning algorithms, the extraction accuracy increases as more contracts are processed, thereby decreasing the manual work required by lawyers.”

Based in Brookline Massachusetts, Brightleaf serves Fortune 500 customers worldwide providing them insight into the terms, provisions, and obligations across large numbers of legal agreements.

“We have one customer, for example, who has over 250,000 different vendor contracts,” said Mr. Bhatia. “We are extracting vital legal and financial information for their operational, legal, and purchasing staff. This essential data, critical to their business was once locked away in contracts, but is now structured and available for analysis and reporting whenever it’s needed.

”Our technology opens new opportunities that extend beyond typical enterprise contract management. Because it can be used on any documents, including MS Word, HTML, PDF etc. or on any image format (TIF, JPEG, PNG, GIF etc.),this technology can be used on all types of documents, not just contracts.  We see this as a much larger opportunity and future direction for the company.” added Mr. Bhatia.

Typically, the data Brightleaf extracts is uploaded into a Contract Lifecycle Management System (CLM) from companies such as Apttus, IBM (Emptoris), Icertis, The Corridor Company, Exari, Symfact, and others.  Clients use these systems for contract centralization, time savings, better management reporting, cost reduction, greater accountability, and risk reduction. Additionally, companies are using Brightleaf to find missing or hidden revenue, for compliance with new and changing regulatory requirements such as FASB/IASB lease accounting standards, and managing all the important obligations captured in their contracts.

“Brightleaf’s partnership with CLM vendors provides meaningful benefits,” says Mr. Bhatia.  “Deploying a truly effective and complete CLM system requires uploading extracted data from legacy contracts.  Because we work very closely with the best-known CLM companies, we make that migration seamless, greatly increasing the value of both companies’ offerings.”

Brightleaf Solutions, Inc., is headquartered in Brookline Massachusetts and has offices in Gurgaon and Pune in India. For more information go to www.brightleaf.com