Contextualized End-to-End Neural Entity Linking

Abstract

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.

arXiv comment5 pages, 1 figure, 2 tables

References in corpus (5)

• Efficient Estimation of Word Representations in Vector Space
• XLNet: Generalized Autoregressive Pretraining for Language Understanding
• Transition-Based Dependency Parsing with Stack Long Short-Term Memory
• Investigating Entity Knowledge in BERT with Simple Neural End-To-End Entity Linking
• Neural Cross-Lingual Entity Linking

Cited by in corpus (1)

• Wikipedia2Vec: An Efficient Toolkit for Learning and Visualizing the Embeddings of Words and Entities from Wikipedia