Thomson Reuters today (1 June) launched HighQ Contract Analysis, a contract review and analysis tool in HighQ that uses machine learning to help legal professionals to extract key data and begin to triage contracts based on their risk profile. It also pulls in data from Practical Law Company that enables lawyers to quickly work out how the contract they are looking at deviates from the norm.
Contract Analysis was already in development before the acquisition of HighQ but now lives in and leverages iSheets.
Speaking to Legal IT Insider, Rawia Ashraf, vice president of Legal Practice and Productivity at Thomson Reuters said: “We did a POC in 2019 and once we had validated that we have a novel approach we started building in late 2019 and we have co-designed it with law firms in the UK and US. Some are doing data testing, some are in pilot and some are experimenting with the tool.”
Users can upload their contracts and in iSheets easily pull out key data such commencement data via a drop down menu on the left of the page.
Much of what you see is the result of work by the PLC team, and Ashraf said: “Practical Law sat down at the beginning of the process and worked out what, for example, you would be thinking about when reviewing a lease agreement.”
The model has been trained by subject matter experts working with its innovation team Thomson Reuters Labs and its data science team, which have been annotating contracts.
Within the key facts and drop down menu on the left you can find out ‘who is the landlord’ or ‘what is the rental amount’.
Ashraf says: “I can give it a risk rating and immediately share high risk documents with comments.”
A semantic search for repair and maintenance details will return all related clauses whether those words are mentioned or not. The system is inevitably still not perfect and Ashraf demonstrates that where it misses something, it can be easily highlighted and added to the pool of answers.
The idea is that Contract Analysis gets contracts ready for human review in the due diligence process, which Ashraf and the team, in the many interviews they have conducted, have been told is like ‘mining for gold.’
There is huge potential to build entire workflows around the contract review process, leveraging Contract Express to automate responses – and this contract lifecycle management capability was the vision TR had when it acquired HighQ.
“AI-powered applications require three key ingredients – data, subject matter expertise and technology – and HighQ Contract Analysis builds upon Thomson Reuters decades-long leadership in AI-driven products for legal professionals,” Andy Martens, head of Research Products at Thomson Reuters said in a statement. “HighQ Contract Analysis begins with the deep knowledge of Practical Law editors who use their expertise to develop proprietary contract review templates specific to legal domains, and then leverages the work of AI experts at Thomson Reuters Labs to train and validate its machine-learning models. The result is a highly tailored, guided review that saves our customers’ time and costs, and improves the accuracy and insights of the contract review process.”
HighQ Contract Analysis is built around legal domains, beginning with real estate leases and sales and services agreements and soon extending to other areas, including intellectual property agreements and employment agreements.