Contextualized End-to-End Neural Entity Linking

Haotian Chen1, Xi Li1, Andrej Zukov Gregoric1, Sahil Wadhwa2
1BlackRock, 2University of Illinois at Urbana-Champaign


We propose an entity linking (EL) model that jointly learns mention detection (MD) and entity disambiguation (ED). Our model applies task-specific heads on top of shared \texttt{BERT} contextualized embeddings. We achieve state-of-the-art results across a standard EL dataset using our model; we also study our model's performance under the setting when hand-crafted entity candidate sets are not available and find that the model performs well under such a setting too.