%0 Conference Proceedings %T What Matters for Neural Cross-Lingual Named Entity Recognition: An Empirical Analysis %A Huang, Xiaolei %A May, Jonathan %A Peng, Nanyun %Y Inui, Kentaro %Y Jiang, Jing %Y Ng, Vincent %Y Wan, Xiaojun %S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) %D 2019 %8 November %I Association for Computational Linguistics %C Hong Kong, China %F huang-etal-2019-matters %X 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, 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 explore how transfer learning works for cross-lingual NER on two transferable factors: sequential order and multilingual embedding. Our results shed light on future research for improving cross-lingual NER. %R 10.18653/v1/D19-1672 %U https://aclanthology.org/D19-1672 %U https://doi.org/10.18653/v1/D19-1672 %P 6395-6401