Automated technical knowledge curation using machine learning

With the growth of the Internet, the amount of scientific data and information available to research teams has been increasing exponentially in the past two decades, which results in significant information overload. Approaches for manual knowledge extraction and curation does not scale up in practice.
The main objective of the project is to create an intelligent knowledge management and resource curation system that allows R&D teams to effectively organize, access, and augment the knowledge they need to carry out their projects. This will enable teams, especially, research groups, and other power users of machine learning, to efficiently navigate the exponentially growing amount of information available to them and help them decide the best directions and approaches to take for every project. The project will create a human-in-the-loop machine learning workflow generation system by innovatively combining various techniques from knowledge graphs, natural language processing, graph neural networks and graph-based reasoning.

Faculty Supervisor:

Daniel Varro;Sridhar Krishnan;Gunter Mussbacher;Sridhar Krishnan;Daniel Varro;Gunter Mussbacher

Student:

Partner:

Aggregate Intellect Inc.

Discipline:

Computer science

Sector:

Professional, scientific and technical services

University:

McGill University; Toronto Metropolitan University

Program: