# Improving Zero-Shot Multi-Lingual Entity Linking

arXiv: https://arxiv.org/abs/2104.08082 · HTML: https://mlsanity.com/paper/2104.08082/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 15 references that are in the map.
- First posted on arXiv 16 Apr 2021.

## Builds on (most cited first, 7 of 7)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Neural Ranking Models with Weak Supervision](https://mlsanity.com/paper/1704.08803/) (2017)
- [DeepType: Multilingual Entity Linking by Neural Type System Evolution](https://mlsanity.com/paper/1802.01021/) (2018)
- [Multinomial Adversarial Networks for Multi-Domain Text Classification](https://mlsanity.com/paper/1802.05694/) (2018)
- [Zero-shot Neural Transfer for Cross-lingual Entity Linking](https://mlsanity.com/paper/1811.04154/) (2018)
- [Joint Multilingual Supervision for Cross-lingual Entity Linking](https://mlsanity.com/paper/1809.07657/) (2018)

## Abstract (arXiv)

Entity linking -- the task of identifying references in free text to relevant knowledge base representations -- often focuses on single languages. We consider multilingual entity linking, where a single model is trained to link references to same-language knowledge bases in several languages. We propose a neural ranker architecture, which leverages multilingual transformer representations of text to be easily applied to a multilingual setting. We then explore how a neural ranker trained in one language (e.g. English) transfers to an unseen language (e.g. Chinese), and find that while there is a consistent but not large drop in performance. How can this drop in performance be alleviated? We explore adding an adversarial objective to force our model to learn language-invariant representations. We find that using this approach improves recall in several datasets, often matching the in-language performance, thus alleviating some of the performance loss occurring from zero-shot transfer.