Plain English Summarization of Contracts

TL;DR

This paper introduces the task of summarizing legal contracts in plain English to improve user understanding, presents an initial dataset, and highlights the challenges of existing summarization methods for legal language.

Contribution

It provides the first dataset for plain English legal contract summarization and analyzes the limitations of current extractive methods for this task.

Findings

Unsupervised extractive methods perform poorly on legal summarization.

Summaries involve heavy abstraction, compression, and simplification.

The task requires new resources and techniques for legal language simplification.

Abstract

Unilateral contracts, such as terms of service, play a substantial role in modern digital life. However, few users read these documents before accepting the terms within, as they are too long and the language too complicated. We propose the task of summarizing such legal documents in plain English, which would enable users to have a better understanding of the terms they are accepting. We propose an initial dataset of legal text snippets paired with summaries written in plain English. We verify the quality of these summaries manually and show that they involve heavy abstraction, compression, and simplification. Initial experiments show that unsupervised extractive summarization methods do not perform well on this task due to the level of abstraction and style differences. We conclude with a call for resource and technique development for simplification and style transfer for legal language.