Retrieving Court Decisions Using Text Mining Techniques and Tools

Abstract

In this paper, we present a solution for finding similar legal decisions to establish a solid basis for the development of a case-based reasoning system. A court decision corpus was scraped from the web. Features that represent court decisions were carefully selected. Several machine learning methods were applied to extract selected features from court decisions in plain text format: CRF, Naive Bayes and SVM. A knowledge base of court decisions was automatically populated. Finally, the knowledge base was queried to demonstrate how to retrieve similar court decisions. By evaluating the machine learning algorithms that were used, we concluded that they can substantially speed up information extraction from court decisions without compromising quality. The selected features are suitable to represent court decision for the identified purpose.

Tasks

Reproductions