This paper introduces a conceptually simple, scalable, and highly effective BERT-based entity linking model, along with an extensive evaluation of its accuracy-speed trade-off.
The wealth of structured (e. g. Wikidata) and unstructured data about the world available today presents an incredible opportunity for tomorrow's Artificial Intelligence.
Ranked #1 on Entity Disambiguation on TAC2010
The occurrence of a fact (edge) is modeled as a multivariate point process whose intensity function is modulated by the score for that fact computed based on the learned entity embeddings.
Hyperbolic embeddings have recently gained attention in machine learning due to their ability to represent hierarchical data more accurately and succinctly than their Euclidean analogues.
Ranked #12 on Link Prediction on WN18RR
Linked Open Data has been recognized as a valuable source for background information in many data mining and information retrieval tasks.
Ranked #1 on Node Classification on BGS
In addition to the main dataset, we open up several derived datasets including mention entity co-occurrence counts and entity embeddings, as well as mappings between Freebase ids and Wikidata item ids.
Previous cross-lingual knowledge graph (KG) alignment studies rely on entity embeddings derived only from monolingual KG structural information, which may fail at matching entities that have different facts in two KGs.