On Semi-Supervised Learning of Legal Semantics

Abstract

In this conference, Professor McCarty reviews his prior work (from 1998, 2007 and 2015) and proposes a research strategy to produce a computational summary of a legal case, which can be scaled up to a realistic legal corpus. The computational challenge was introduced in a 1998 paper on « Structured Casenotes. » Two steps toward a solution were developed in (i) an ICAIL 2007 paper on « Deep Semantic Interpretations of Legal Texts, » and (ii) an ICAIL 2015 paper on « How to Ground a Language for Legal Discourse in a Prototypical Perceptual Semantics. » The current proposal is to combine the 2007 NL model with the 2015 KR model, and to add an ML model based on semi-supervised learning.

Formation d’un dispensateur reconnu aux fins de la formation continue obligatoire du Barreau du Québec pour une durée de 1 heure et 30 minutes. Une attestation de participation représentant 1 heure et 30 minutes de formation sera aussi transmise aux notaires.

Speaker

L. Thorne McCarty is a professor emeritus in Computer Science and Law at Rutgers University (New Jersey, USA)  where he teaches since 1981. Before joining Rutgers University in the Department of Computer Science, he taught Law at the State University of New York for 10 years. His research expertise is on artificial intelligence, machine learning, natural language processing and computer science.

He graduated in Mathematics and Philosophy at Yale University and in Law at Harvard Law School.

Respondant

Ejan Mackaay  is a professor emeritus in Law at the Faculty of Law at the Université de Montréal where he teaches Law and Economic analysis for 35 years. He was director of the Centre de recherche en droit public in 1999-2003 and of the Centre de droit des affaires et du commerce international in 2005-2008.

Inscription

Ce contenu a été mis à jour le 4 avril 2018 à 14 h 38 min.