AIDA-light: High-Throughput Named-Entity Disambiguation

To advance the Web of Linked Data, mapping ambiguous names in structured and unstructured contents onto knowledge bases would be a vital asset. State-of-the-art methods for Named Entity Disambiguation (NED) face major tradeoffs regarding efficiency/scalability vs. accuracy. Fast methods use relatively simple context features and avoid computationally expensive algorithms for joint inference. While doing very well on prominent entities in clear input texts, these methods achieve only moderate accuracy when fed with difficult inputs. On the other hand, methods that rely on rich context features and joint inference for mapping names onto entities pay the price of being much slower. This paper presents AIDA-light which achieves high accuracy on difficult inputs while also being fast and scalable. AIDA-light uses a novel kind of two-stage mapping algorithm. It first identifies a set of “easy” mentions with low ambiguity and links them to entities in a very efficient manner. This stage also determines the thematic domain of the input text as an important and novel kind of feature. The second stage harnesses the high-confidence linkage for the “easy” mentions to establish more reliable contexts for the disambiguation of the remaining mentions. Our experiments with four different datasets demonstrates that the accuracy of AIDA-light is competitive to the very best NED systems, while its run-time is comparable to or better than the performance of the fastest systems.