Natural language processing (NLP)

Automating legal contracts

A lot of a lawyer’s work is still manual: reading and revising contracts. The process could be made more efficient; what usually takes around one hour for an experienced lawyer, could be done automatically in a few minutes.

Different natural language processing (NLP) technologies could be used to ease the repetitive workload. The structure, and the content up to a certain point, is somewhat similar in every contract. 

Linguistically a contract contains sections, subsections, moments, paragraphs and sentences, as well as tables, pictures and bullet list. All of these are linked to each other and a change in one part of the contract may trigger a change in another part of the contract.

the GOAL

Build a model/engine that – based on the terms and conditions defined by an organisation – independently/automatically:

a) analyses, compares and revises the contract

b) adds terms and conditions if needed

c) adds specific words into paragraphs and/or rewrites paragraphs

d) sets out a draft of the final contract and

e) sends the final draft to an expert for revision.


Companies with and internal legal department

Service provides with knowledge about text mining and generation

Researchers with expertise of natural language processing

Finnish AI Accelerator

contact information

00130 Helsinki

Finnish AI Accelerator Tekoälyaika
Finnish AI Accelerator Teknologiateollisuus ry