Plain English Summarization of Contracts
This addresses the issue of low readability for users of digital contracts, but it is incremental as it focuses on dataset creation and highlights challenges without introducing new methods.
The paper tackles the problem of users not reading long and complex legal contracts by proposing the task of summarizing them in plain English, and presents an initial dataset with manually verified summaries that involve heavy abstraction and simplification.
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.