# What Matters for Neural Cross-Lingual Named Entity Recognition: An Empirical Analysis

arXiv: https://arxiv.org/abs/1909.03598 · HTML: https://mlsanity.com/paper/1909.03598/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Sep 2019.

## Built on by (most cited first, 4 of 4)

- [Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument Extraction](https://mlsanity.com/paper/2203.08308/) (2022)
- [A cost-benefit analysis of cross-lingual transfer methods](https://mlsanity.com/paper/2105.06813/) (2021)
- [Does Synthetic Data Help Named Entity Recognition for Low-Resource Languages?](https://mlsanity.com/paper/2505.16814/) (2025)
- [What Matters When Building Universal Multilingual Named Entity Recognition Models?](https://mlsanity.com/paper/2601.06347/) (2026)

## Abstract (arXiv)

Building named entity recognition (NER) models for languages that do not have much training data is a challenging task. While recent work has shown promising results on cross-lingual transfer from high-resource languages to low-resource languages, it is unclear what knowledge is transferred. In this paper, we first propose a simple and efficient neural architecture for cross-lingual NER. Experiments show that our model achieves competitive performance with the state-of-the-art. We further analyze how transfer learning works for cross-lingual NER on two transferable factors: sequential order and multilingual embeddings, and investigate how model performance varies across entity lengths. Finally, we conduct a case-study on a non-Latin language, Bengali, which suggests that leveraging knowledge from Wikipedia will be a promising direction to further improve the model performances. Our results can shed light on future research for improving cross-lingual NER.