Investigating Strategies for Clause Recommendation

Clause recommendation is the problem of recommending a clause to legal contract, given context contract in question and type which should belong. With not much prior work being done toward generation contracts, this was proposed as first step bigger generation. As an open-ended text problem, distinguishing characteristics lie nature language sublanguage considerable similarity textual content within clauses specific type. This aspect drives us investigate importance similar contracts’ representation for clauses. In our work, we experiment with generating 15 commonly occurring types contracts expanding upon previous on analyzing recommendations varying settings using information derived from contracts.