Entity linking systems typically rely on encyclopedic knowledge bases such as DBpedia or Freebase. In this paper, we use, instead, a French lexical-semantic network named JeuxDeMots to jointly type and link entities. Our approach combines word embeddings and a path-based similarity resulting in encouraging results over a set of documents from the French Le Monde newspaper.
JeuxDeLiens: Word embeddings and path-based similarity for entity lnking using the french JeuxDeMots lexical semantic network
TALN 2018, 25th French Conference on Natural Language Processing, May 14-18, 2018, Rennes, France
PERMALINK : https://www.eurecom.fr/publication/5675