The project aims at defining embeddings to represent classes, instances and properties. Such a model tries to quantify semantic similarity as a measure of distance in the vector space of the embeddings. I believe this can be done by implementing Random Vector Accumulators with additional features in order to better encode the semantic information held by the Wikipedia corpus and DBpedia graphs.

Organization

Student

Akshay Jagatap

Mentors

  • SANDRO ATHAIDE COELHO
  • Xu Peng
  • Tommaso Soru
close

2017