# Entity Disambiguation with Entity Definitions

arXiv: https://arxiv.org/abs/2210.05648 · HTML: https://mlsanity.com/paper/2210.05648/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 30 references that are in the map.
- First posted on arXiv 11 Oct 2022.

## Builds on (most cited first, 11 of 11)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Autoregressive Entity Retrieval](https://mlsanity.com/paper/2010.00904/) (2020)
- [Improving Entity Linking by Modeling Latent Relations between Mentions](https://mlsanity.com/paper/1804.10637/) (2018)
- [Investigating Entity Knowledge in BERT with Simple Neural End-To-End Entity Linking](https://mlsanity.com/paper/2003.05473/) (2020)
- [Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation](https://mlsanity.com/paper/1601.01343/) (2016)
- [Collective Entity Disambiguation with Structured Gradient Tree Boosting](https://mlsanity.com/paper/1802.10229/) (2018)
- [Simple Question Answering by Attentive Convolutional Neural Network](https://mlsanity.com/paper/1606.03391/) (2016)
- [Entity-aware ELMo: Learning Contextual Entity Representation for Entity Disambiguation](https://mlsanity.com/paper/1908.05762/) (2019)
- [CompactIE: Compact Facts in Open Information Extraction](https://mlsanity.com/paper/2205.02880/) (2022)

## Built on by (most cited first, 1 of 1)

- [BELHD: Improving Biomedical Entity Linking with Homonoym Disambiguation](https://mlsanity.com/paper/2401.05125/) (2024)

## Abstract (arXiv)

Local models have recently attained astounding performances in Entity Disambiguation (ED), with generative and extractive formulations being the most promising research directions. However, previous works limited their studies to using, as the textual representation of each candidate, only its Wikipedia title. Although certainly effective, this strategy presents a few critical issues, especially when titles are not sufficiently informative or distinguishable from one another. In this paper, we address this limitation and investigate to what extent more expressive textual representations can mitigate it. We thoroughly evaluate our approach against standard benchmarks in ED and find extractive formulations to be particularly well-suited to these representations: we report a new state of the art on 2 out of 6 benchmarks we consider and strongly improve the generalization capability over unseen patterns. We release our code, data and model checkpoints at https://github.com/SapienzaNLP/extend.