Over the course of the last year Lexum has started exploring the potential of deep learning (DL) and machine learning (ML) technologies for legal research. Although these projects are still under the umbrella of Lexum’s research and development team, or Lexum’s Lab (https://lexum.com/en/ailab/), concrete applications have recently started to become available. This paper explores two of these projects: Lexum’s Citation Predictor, and Lexum’s Learning to Rank solution.
These projects benefit from a combination of three factors. First, the millions of legal documents available in the CanLII database in parsable format along with structured metadata constitute a significant dataset to train AI algorithms. Second, Lexum has direct access to the knowledge and experience of one of the leading teams in AI and deep learning worldwide at the Montreal Institute for Learning Algorithms (MILA) of the University of Montreal. Third, the availability of computer engineers with cutting-edge expertise in the specifics of legal documents facilitates the transition from theory to practical applications.
This papers first look at why the data available on the CanLII website is particularly well suited to train ML algorithms. More specifically, the fact that its citator recognizes over 16 million citations has contributed to create a “map” of the Canadian Law.
Regarding concrete outcomes, Lexum’s Citation Predictor can predict the most relevant sources of law for any given piece of text (incorporating legal citations or not). Lexum’s approach consist in learning from the citation network to predict which sources of law are relevant to the text of a legal brief, a legal opinion or to the plain language description of a legal issue.
The Learning to Rank algorithm for its part improve the relevance of search results by learning from document structures, user behaviors and the content of the citation network. It weights-in all of these signals using a ML algorithm to better rank search results.
Related Session:
October 12th, 2018
Session VI.A. Legal Knowledge in Times of Big Data
14:45-17:30
Aula Magna of the Rectorate of the University of Florence