EL92: Entity Linking Combining Open Source Annotators via Weighted Voting

Pablo Ruiz (1) , Thierry Poibeau (1)

1 Lattice - Lattice - Langues, Textes, Traitements informatiques, Cognition - UMR 8094

Our participation at SemEval's Multilingual All-Words Sense Disambiguation and Entity Linking task is described. An English entity linking (EL) system is presented, which combines the annotations of four public open source EL services. The annotations are combined through a weighted voting scheme inspired on the ROVER method, which had not been previously tested on EL outputs. Results on the task's EL items were competitive.

Mots clés: Natural language processing; Entity linking; Machine learning

Domaines: Intelligence artificielle [cs.AI]; Recherche d'information [cs.IR]; Apprentissage [cs.LG]; Web; Informatique; Linguistique; Sciences de l'information et de la communication; Linguistique; Méthodes et statistiques; Traitement du texte et du document

Pablo Ruiz, Thierry Poibeau. EL92: Entity Linking Combining Open Source Annotators via Weighted Voting. 9th International Workshop on Semantic Evaluation (SemEval 2015), Association for Computational Linguistics, Jun 2015, Denver, United States. pp.355-359. ⟨hal-01173968⟩