Development of a recommender system based on Knowledge Graph (KG) and Graph Neural Networks (GNNs)
keywords ARTIFICIAL INTELLIGENCE, ARTIFICIAL NEURAL NETWORK, MACHINE LEARNING, NATURAL LANGUAGE PROCESSING, RECOMMENDER SYSTEMS, SEMANTIC TECHNOLOGIES, SEMANTIC WEB, SOFTWARE DEVELOPMENT, WEB APPLICATIONS
Reference persons ANTONIO VETRO'
External reference persons Ing. Giovanni Garifo ( firstname.lastname@example.org , https://nexa.polito.it/people/ggarifo )
Research Groups DAUIN - GR-22 - Nexa Center for Internet & Society - NEXA
Thesis type SOFTWARE DEVELOPMENT, SOFTWARE SPERIMENTALE, WEB DEVELOPMENT
Description Knowledge Graphs (KGs) have emerged as a core technology for incorporating human knowledge because of their capability to capture the relational dimension of information and of its semantic properties. The nature of KGs meets one of the vocational pursuits of academic institutions, which are sharing their intellectual output, especially publications.
In this thesis we propose to continue the development of Geranium (https://www.mdpi.com/2078-2489/12/9/366), a Knowledge Graph (KG) and Graph Neural Networks (GNNs) based search, discovery and recommendation engine for academic publications built by the Nexa Center for Internet and Society.
The thesis will involve the development of new features for the platform, the expansion of the knowledge base and the application of Geranium to new domains, other than the one already explored (i.e. academic publications).
https://nexa.polito.it/geranium (project web page)
https://nexacenter.org/lunch-72 (video-recorded seminar on Geranium)
See also https://nexa.polito.it/geranium
Required skills The thesis requires very good development skills and knowledge of fundamental NLP and ML techniques.
Grade point average equal to or higher than 26 will play a relevant role in the selection.
Notes When sending your application, we kindly ask you to attach the following information:
- list of exams taken in you master degree, with grades and grade point average
- a résumé or equivalent (e.g., linkedin profile), if you already have one
- by when you aim to graduate and an estimate of the time you can devote to the thesis in a typical week
Deadline 30/11/2023 PROPONI LA TUA CANDIDATURA