Contextualized End-to-End Neural Entity Linking
This addresses entity linking for natural language processing applications, but it is incremental as it builds on existing BERT-based approaches.
The paper tackles the problem of entity linking by proposing a model that links words directly to entities, bypassing mention span selection and enabling joint training of mention detection and entity disambiguation. It achieves state-of-the-art results on multiple standard datasets.
We propose yet another entity linking model (YELM) which links words to entities instead of spans. This overcomes any difficulties associated with the selection of good candidate mention spans and makes the joint training of mention detection (MD) and entity disambiguation (ED) easily possible. Our model is based on BERT and produces contextualized word embeddings which are trained against a joint MD and ED objective. We achieve state-of-the-art results on several standard entity linking (EL) datasets.