Plain English Contract Summarization Task
Jump to navigation
Jump to search
A Plain English Contract Summarization Task is a contract summarization task that is a legal language simplification task (converts complex legal language into plain English legal language).
- Context:
- It can (typically) involve translating legal contracts like terms of service into plain language that laypersons can easily understand.
- It can (often) require significant abstraction, compression, and simplification of the original legal text.
- It can range from being an automated summarization process using natural language processing (NLP) techniques to a manual summarization by legal experts.
- It can help users make more informed decisions by clearly presenting the essential elements of a contract, such as rights, obligations, and provisions.
- It can involve the creation of datasets pairing legal text snippets with their plain English summaries for training and evaluation purposes.
- It can be evaluated for quality and effectiveness using both automated and human assessment methods.
- It can utilize techniques from extractive summarization and abstractive summarization to achieve the desired level of clarity.
- It can face challenges due to the inherent complexity and formal style of legal language.
- It can be applied to various types of contracts, including terms of service, employment agreements, and lease contracts.
- It can involve collaboration between legal experts and computational linguists to ensure accuracy and comprehensibility.
- ...
- Example(s):
- a summary that translates Facebook's terms of service into "Facebook can use any of your stuff for any reason they want without paying you, for advertising in particular."
- a summary that simplifies Niantic's terms of service to "If you haven’t played for a year, you mess up, or we mess up, we can delete all of your virtual goods. We don’t have to give them back."
- a dataset consisting of legal text snippets paired with their plain English summaries used for training NLP models.
- ...
- Counter-Example(s):
- Legal documents that remain in complex legal jargon without any simplification or summarization.
- Technical manuals or user guides that use industry-specific jargon not intended for legal use.
- See: Legal Language Simplification, Natural Language Processing, Extractive Summarization, Abstractive Summarization
References
2019
- (Manor & Li, 2019) ⇒ Laura Manor, and Junyi Jessy Li. (2019). “Plain English Summarization of Contracts.” arXiv preprint arXiv:1906.00424
- ABSTRACT: Unilateral legal contracts, such as terms of service, play a substantial role in modern digital life. However, few 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.