Methods for retrieving alternative contract language using a prototype

Abstract

This paper addresses the problem of searching for alternative contract language that is similar to, yet different from, a given provision (the prototype). While this is a core task in transactional legal work, generic search solutions do not offer an effective solution. We draw upon modern information retrieval research to propose and validate novel methods for retrieving alternative language using a prototype. Our solution accepts an entire provision as a prototype and retrieves variants on the language from a database of precedent contracts. In designing this solution, we propose two ordered proximity measures and demonstrate their effectiveness relative to existing techniques. Further, we examine the challenge posed by varying definitions of redundant search results and propose to resolve it with a user-tunable, dynamic approach to result clustering.