MAG

• DOI: 10.1145/3148011.3148024
• Publication Date: 2017-12-18T13:22:50Z
• Authors: Diego Moussallem; Ricardo Usbeck; Michael Röeder; Axel-Cyrille Ngon...
• Keywords: FOS: Computer and information sciences; Computer Science - Computation and Language; I.2.7; 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology; Computation and Language (cs.CL)

Entity linking has recently been the subject of a significant body research. Currently, best performing approaches rely on trained mono-lingual models. Porting these to other languages is consequently difficult endeavor as it requires corresponding training data and retraining We address this drawback by presenting novel multilingual, knowledge-based agnostic deterministic approach entity linking, dubbed MAG. MAG based combination context-based retrieval structured knowledge bases graph algorithms. evaluate 23 sets in 7 languages. Our results show that English datasets (PBOH) achieves micro F-measure up 4 times worse MAG, hand, state-of-the-art performance reaches 0.6 higher than PBOH non-English