Abstract
Free legal assistance is critically under-resourced, and many of those who seek legal help have their needs unmet. A major bottleneck in the provision of free legal assistance to those most in need is the determination of the precise nature of the legal problem. This paper describes a collaboration with a major provider of free legal assistance, and the deployment of natural language processing models to assign area-of-law categories to real-world requests for legal assistance. In particular, we focus on an investigation of models to generate efficiencies in the triage process, but also the risks associated with naive use of model predictions, including fairness across different user demographics.
Highlights
In addition to the issues surrounding the inherent fuzziness of legal categories, the descriptions ofThe number of Australians with unmet legal needs is estimated to be over 4 million people per year and growing: each year approximately 8.5 million Australians will have a legal problem and only around 4.5 million will access any assistance (Coumarelos et al, 2012; The Department of Justice and Regulation, 2012) — an indication that free legal assistance services are critically under-resourced
We investigate the viability of semi-automating this step by building a model that suggests how to categorise lay descriptions of problems/incidents into legal areas
It is critical that we develop models which will perform well for users of all backgrounds, generalise well from small amounts of curated data, and potentially dynamically interact with the help-seeker to clarify the nature of the case
Summary
In addition to the issues surrounding the inherent fuzziness of legal categories, the descriptions of. It is critical that we develop models which will perform well for users of all backgrounds, generalise well from small amounts of curated data, and potentially dynamically interact with the help-seeker to clarify the nature of the case. Can overcome these biases for future iterations of the model while keeping in mind the protection and 3 Data Set Development privacy of the help-seekers who are most vulnerable
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.