An AI-powered scientific document recommender system for academic and technical resources

The attribution of textual sources remains a challenge in recommendation systems. The problem receives attention in academic circles. As part of this project, we will be developing an AI-powered recommender system to help users find out what to read next when it comes to technical documents like theses, manuscripts, and technical reports based on resources they have already read. Finding a good resource recommendation system can mitigate the time-consuming task of finding a valid reference for written paragraphs in a technical document. Additionally, the UofG grad students and research staff will be able to produce their scientific documents in a timely manner using the developed system.

Intern: 
Hamed Haddadpajouh
Faculty Supervisor: 
Ali Dehghantanha
Province: 
Ontario
Partner: 
Partner University: 
Discipline: