50 papers with code • 10 benchmarks • 9 datasets
Entity Disambiguation is the task of linking mentions of ambiguous entities to their referent entities in a knowledge base such as Wikipedia.
We propose a novel deep learning model for joint document-level entity disambiguation, which leverages learned neural representations.
Despite of the recent success of collective entity linking (EL) methods, these "global" inference methods may yield sub-optimal results when the "all-mention coherence" assumption breaks, and often suffer from high computational cost at the inference stage, due to the complex search space.
The model is capable of generalising to large-scale knowledge bases such as Wikidata (which has 15 times more entities than Wikipedia) and of zero-shot entity linking.
Recent work in entity disambiguation (ED) has typically neglected structured knowledge base (KB) facts, and instead relied on a limited subset of KB information, such as entity descriptions or types.
We demonstrate the accuracy of our approach on a wide range of benchmark datasets, showing that it matches, and in many cases outperforms, existing state-of-the-art methods.