# Focusing on Context is NICE: Improving Overshadowed Entity Disambiguation

arXiv: https://arxiv.org/abs/2210.06164 · HTML: https://mlsanity.com/paper/2210.06164/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 20 references that are in the map.
- First posted on arXiv 12 Oct 2022.

## Builds on (most cited first, 8 of 8)

- [Autoregressive Entity Retrieval](https://mlsanity.com/paper/2010.00904/) (2020)
- [A Survey on Recent Advances in Named Entity Recognition from Deep Learning models](https://mlsanity.com/paper/1910.11470/) (2019)
- [Scalable Zero-shot Entity Linking with Dense Entity Retrieval](https://mlsanity.com/paper/1911.03814/) (2019)
- [Deep Joint Entity Disambiguation with Local Neural Attention](https://mlsanity.com/paper/1704.04920/) (2017)
- [REL: An Entity Linker Standing on the Shoulders of Giants](https://mlsanity.com/paper/2006.01969/) (2020)
- [Improving Entity Linking by Modeling Latent Relations between Mentions](https://mlsanity.com/paper/1804.10637/) (2018)
- [Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation](https://mlsanity.com/paper/1601.01343/) (2016)
- [Robustness Evaluation of Entity Disambiguation Using Prior Probes:the Case of Entity Overshadowing](https://mlsanity.com/paper/2108.10949/) (2021)

## Abstract (arXiv)

Entity disambiguation (ED) is the task of mapping an ambiguous entity mention to the corresponding entry in a structured knowledge base. Previous research showed that entity overshadowing is a significant challenge for existing ED models: when presented with an ambiguous entity mention, the models are much more likely to rank a more frequent yet less contextually relevant entity at the top. Here, we present NICE, an iterative approach that uses entity type information to leverage context and avoid over-relying on the frequency-based prior. Our experiments show that NICE achieves the best performance results on the overshadowed entities while still performing competitively on the frequent entities.