Partnerships
Industrial member of the Institute for Data Valorization
IVADO is a joint initiative by academia (HEC Montréal, Polytechnique Montréal and the University of Montreal) and industry. Its goal is to develop a new economic sector evolving around massive data processing to support decision making.
Collaboration with the Montreal Institute for Learning Algorithms
The machine learning laboratory at the University of Montreal is one of the world’s leading teams in artificial intelligence and deep learning.
Department of Computer Science and Operations Research at the University of Montréal
The Department of Computer Science and Operations Research (DIRO) was one of the first university-level computer science departments in North America. At the master's and doctoral levels, the international-caliber research conducted in the DIRO is a major attraction for students looking for a cutting-edge environment in which to study and work.
Projects
LexKey: A Public Language Model Keyword Generator for Legal Documents
As a sequel to our recent post on Automatic Classification , we would like to introduce you to the science behind the show. The following article is adapted from the one presented by Benjamin Cérat, Software programmer at Lexum, as a workshop at ICAIL 2023 . The 19th International Conference on Artificial Intelligence and Law took place from...
Automatic Classification Part 2: Use Cases
In our last article on Automatic Classification, we emphasized the science behind the scene. This time, we would like to focus on what you will get from it. Here are a couple of practical use cases to experiment with. Monitoring Recent Cases in a Niche Field For instance, let’s say you are interested in cannabis licensing in Ontario. It is a relatively...
Automatic Classification on CanLII Part 1: Functionalities
Automatic Classification is a new advanced artificial intelligence feature developed by Lexum for the CanLII website. The Automatic Classification feature leverages artificial intelligence algorithms and natural language processing techniques to categorize legal documents by subject automatically. For this project, Lexum used its own language model...
Background
Our technology enables organizations of all sizes to deliver content to end users with unparalleled speed and efficiency. We are constantly looking for new ways to automate and streamline the operation of legal information databases. Over the years, this has led us to replace manual editing by complex algorithms based on heuristics whenever possible.
One such example is Lexum’s citator, Reflex, which is used to automatically insert links on legal citations included in the text body of legal documents.
Another example is Decisia’s auto-fill feature, which enables our clients to extract all sorts of metadata values directly from the body of their unstructured documents in one single click.
This expertise, coupled with the large volume of legal information available to Lexum in parsable format, puts us in a unique position to leverage the opportunities presented by recent developments in the field of artificial intelligence, machine learning and deep learning.
Innovation has been part of Lexum’s DNA since the beginning. Twenty-five years ago, we started providing access to Supreme Court of Canada decisions on a Gopher server before the Web was even invented. Eventually, static webpages gave place to dynamic websites, and more recently bespoke software code gave way to Software-as-a-Service (SaaS) products. Overall, in collaboration with the clients and partners who have trusted us, we have transformed the legal publishing industry. We intend to continue doing so.