ADEL@OKE 2017: A Generic Method for Indexing Knowledge Bases for Entity Linking

In this paper, we report on the participation of ADEL, an adaptive entity recognition and linking framework, to the OKE 2017 challenge. In particular, we propose an hybrid approach that combines various extraction methods to improve the recognition level and an efficient knowledge base indexing process to increase the efficiency of the linking step. We detail how we deal with finegrained entity types, either generic (e.g. Activity, Competition, Animal for the task 2) or domain specific (e.g. MusicArtist, SignalGroup, MusicalWork for the task 3). We also show how ADEL can flexibly disambiguate entities from different knowledge bases (DBpedia and MusicBrainz). We obtain promising results on the OKE 2017 challenge training dataset for the first three tasks.