# Global Entity Disambiguation with BERT

arXiv: https://arxiv.org/abs/1909.00426 · HTML: https://mlsanity.com/paper/1909.00426/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Sep 2019.

## Built on by (most cited first, 10 of 10)

- [SpEL: Structured Prediction for Entity Linking](https://mlsanity.com/paper/2310.14684/) (2023)
- [Improving Toponym Resolution with Better Candidate Generation, Transformer-based Reranking, and Two-Stage Resolution](https://mlsanity.com/paper/2305.11315/) (2023)
- [LELA: an LLM-based Entity Linking Approach with Zero-Shot Domain Adaptation](https://mlsanity.com/paper/2601.05192/) (2026)
- [Newswire: A Large-Scale Structured Database of a Century of Historical News](https://mlsanity.com/paper/2406.09490/) (2024)
- [Evaluating Design Decisions for Dual Encoder-based Entity Disambiguation](https://mlsanity.com/paper/2505.11683/) (2025)
- [Deep Learning for Economists](https://mlsanity.com/paper/2407.15339/) (2024)
- [S2abEL: A Dataset for Entity Linking from Scientific Tables](https://mlsanity.com/paper/2305.00366/) (2023)
- [Coherent Entity Disambiguation via Modeling Topic and Categorical Dependency](https://mlsanity.com/paper/2311.03253/) (2023)
- [Span-Oriented Information Extraction -- A Unifying Perspective on Information Extraction](https://mlsanity.com/paper/2403.15453/) (2024)
- [CoSiNES: Contrastive Siamese Network for Entity Standardization](https://mlsanity.com/paper/2306.03316/) (2023)

## Abstract (arXiv)

We propose a global entity disambiguation (ED) model based on BERT. To capture global contextual information for ED, our model treats not only words but also entities as input tokens, and solves the task by sequentially resolving mentions to their referent entities and using resolved entities as inputs at each step. We train the model using a large entity-annotated corpus obtained from Wikipedia. We achieve new state-of-the-art results on five standard ED datasets: AIDA-CoNLL, MSNBC, AQUAINT, ACE2004, and WNED-WIKI. The source code and model checkpoint are available at https://github.com/studio-ousia/luke.