As submitted by the proposer: The purpose of this project is to investigate and design computational approaches to statutory interpretation leading to a proof of concept expert system capable of supporting the interpretation and performing it automatically in the domain of cybercrime.
Such a system would have a far reaching impact on the speed and quality of statutory interpretation performed by judges, attorneys, prosecutors, administrative staff and other professionals.
Our working hypothesis is that a computer program can automatically recognize specific types of statements that play the most important roles in statutory interpretation. Furthermore, we hypothesize that the ability to recognize these types of statements combined with the contextual information about the uncertainties of the user as to the meaning of a specific phrase can be used to evaluate different statements in terms of their usefulness for the interpretation. Finally, we hypothesize that this ability to evaluate the statements would allow the system to outperform the state of the art solutions that are currently offered to support statutory interpretation.
Recent advances in the fields of question answering, recommendation systems, and natural language processing and machine learning in general provide a solid basis for the implementation of the proposed system. The main technological challenges are to identify the most useful techniques from those fields, modify and fine tune them, and augment them with the expert knowledge necessary for them to effectively support and perform statutory interpretation. With gradual maturing of the system it would become possible to test the first hypothesis (year one of the project), then the second hypothesis (year two), and finally the third hypothesis (year three) on the selected legal domain (cybercrime). The resulting technology could become a valuable part of the existing legal information retrieval systems, both commercial and open source. Or it can be deployed as a standalone system.
The most important results of the proposed project will include a working proof of concept system capable of performing and supporting statutory interpretation in the domain of cybercrime. The source code of the system, generated data, as well as the corpus of cybercrime resources will become freely available enabling anyone to use the system, improve on it, and extend it to other domains.
This project contains a research and/or development component, as defined in the applicable law, and complies with Part 200 Uniform Requirements 2 CFR 200.210(a) (14). nca/ncf
