# Improving Candidate Generation for Low-resource Cross-lingual Entity Linking

arXiv: https://arxiv.org/abs/2003.01343 · HTML: https://mlsanity.com/paper/2003.01343/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Mar 2020.

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

- [MMGraphRAG: Bridging Vision and Language with Interpretable Multimodal Knowledge Graphs](https://mlsanity.com/paper/2507.20804/) (2025)
- [Prix-LM: Pretraining for Multilingual Knowledge Base Construction](https://mlsanity.com/paper/2110.08443/) (2021)
- [The Zeno's Paradox of `Low-Resource' Languages](https://mlsanity.com/paper/2410.20817/) (2024)
- [Multilingual End to End Entity Linking](https://mlsanity.com/paper/2306.08896/) (2023)
- [When Word Embeddings Become Endangered](https://mlsanity.com/paper/2103.13275/) (2021)
- [Survey on English Entity Linking on Wikidata](https://mlsanity.com/paper/2112.01989/) (2021)
- [MERLIN: A Testbed for Multilingual Multimodal Entity Recognition and Linking](https://mlsanity.com/paper/2510.14307/) (2025)
- [An Unsupervised Language-Independent Entity Disambiguation Method and its Evaluation on the English and Persian Languages](https://mlsanity.com/paper/2102.00395/) (2021)
- [Efficient Entity Candidate Generation for Low-Resource Languages](https://mlsanity.com/paper/2206.15163/) (2022)
- [Knowledge-injected Prompt Learning for Chinese Biomedical Entity Normalization](https://mlsanity.com/paper/2308.12025/) (2023)

## Abstract (arXiv)

Cross-lingual entity linking (XEL) is the task of finding referents in a target-language knowledge base (KB) for mentions extracted from source-language texts. The first step of (X)EL is candidate generation, which retrieves a list of plausible candidate entities from the target-language KB for each mention. Approaches based on resources from Wikipedia have proven successful in the realm of relatively high-resource languages (HRL), but these do not extend well to low-resource languages (LRL) with few, if any, Wikipedia pages. Recently, transfer learning methods have been shown to reduce the demand for resources in the LRL by utilizing resources in closely-related languages, but the performance still lags far behind their high-resource counterparts. In this paper, we first assess the problems faced by current entity candidate generation methods for low-resource XEL, then propose three improvements that (1) reduce the disconnect between entity mentions and KB entries, and (2) improve the robustness of the model to low-resource scenarios. The methods are simple, but effective: we experiment with our approach on seven XEL datasets and find that they yield an average gain of 16.9% in Top-30 gold candidate recall, compared to state-of-the-art baselines. Our improved model also yields an average gain of 7.9% in in-KB accuracy of end-to-end XEL.