Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Recognizing cited facts and principles in legal judgements

Recognizing cited facts and principles in legal judgements In common law jurisdictions, legal professionals cite facts and legal principles from precedent cases to support their arguments before the court for their intended outcome in a current case. This practice stems from the doctrine of stare decisis, where cases that have similar facts should receive similar decisions with respect to the principles. It is essential for legal professionals to identify such facts and principles in precedent cases, though this is a highly time intensive task. In this paper, we present studies that demonstrate that human annotators can achieve reasonable agreement on which sentences in legal judgements contain cited facts and principles (respectively, $$\kappa =0.65$$ κ = 0.65 and $$\kappa =0.95$$ κ = 0.95 for inter- and intra-annotator agreement). We further demonstrate that it is feasible to automatically annotate sentences containing such legal facts and principles in a supervised machine learning framework based on linguistic features, reporting per category precision and recall figures of between 0.79 and 0.89 for classifying sentences in legal judgements as cited facts, principles or neither using a Bayesian classifier, with an overall $$\kappa$$ κ of 0.72 with the human-annotated gold standard. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Artificial Intelligence and Law Springer Journals

Recognizing cited facts and principles in legal judgements

Loading next page...
 
/lp/springer-journals/recognizing-cited-facts-and-principles-in-legal-judgements-4A5G9vtw1d
Publisher
Springer Journals
Copyright
Copyright © 2017 by The Author(s)
Subject
Computer Science; Artificial Intelligence (incl. Robotics); International IT and Media Law, Intellectual Property Law; Philosophy of Law; Legal Aspects of Computing; Information Storage and Retrieval
ISSN
0924-8463
eISSN
1572-8382
DOI
10.1007/s10506-017-9197-6
Publisher site
See Article on Publisher Site

Abstract

In common law jurisdictions, legal professionals cite facts and legal principles from precedent cases to support their arguments before the court for their intended outcome in a current case. This practice stems from the doctrine of stare decisis, where cases that have similar facts should receive similar decisions with respect to the principles. It is essential for legal professionals to identify such facts and principles in precedent cases, though this is a highly time intensive task. In this paper, we present studies that demonstrate that human annotators can achieve reasonable agreement on which sentences in legal judgements contain cited facts and principles (respectively, $$\kappa =0.65$$ κ = 0.65 and $$\kappa =0.95$$ κ = 0.95 for inter- and intra-annotator agreement). We further demonstrate that it is feasible to automatically annotate sentences containing such legal facts and principles in a supervised machine learning framework based on linguistic features, reporting per category precision and recall figures of between 0.79 and 0.89 for classifying sentences in legal judgements as cited facts, principles or neither using a Bayesian classifier, with an overall $$\kappa$$ κ of 0.72 with the human-annotated gold standard.

Journal

Artificial Intelligence and LawSpringer Journals

Published: Mar 11, 2017

References