Multiple academics, commentators and entrepreneurs have noted how technology can be used to automate tasks currently performed by lawyers. Instead of automating legal work, I intend to focus on augmenting legal work. Specifically, my project focuses on using advances in computational linguistics technology to help lawyers draft more precise and error-free legal documents like contracts, regulations and statutes.
It goes without saying that unwanted litigation is incredibly costly from a time, reputation and financial perspective. From research I conducted, it became evident that a tremendous amount of litigation is caused, or at least made possible, by poorly drafted legal documents. Drafting oversights, such as ambiguous languages, create loopholes that disaffected parties can subsequently use to their advantage. A well-publicized example is King v. Burwell, a case recently before the Supreme Court, which could have voided important elements of the Affordable Care Act due to poor drafting of certain provisions.
I intend to develop a diagnostic application that scans for and flags potential drafting errors. Such oversights include lexical and semantic ambiguities, inconsistent clauses, and contract terms that have not been updated to reflect changes in regulations and recent case law. My interviews with practitioners, coupled with an analysis of pertinent case law, confirm that these types of issues are not easy for lawyers to consistently catch, especially when they are under tight time constraints.
The technology underlying this project includes various natural language processing, machine learning, and data mining techniques. Any public or private sector entity that handles legal documents and is concerned about litigation risk would be a potential user of this solution.
Project leader: Gurinder Sangha
The descriptions of current and past projects of CodeX non-residential fellows are provided to illustrate the kind of work our non-residential fellows are carrying out. These projects are listed here for informational purposes only and are not endorsed by CodeX, Stanford Law School, or Stanford University.