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

Xiaolei Huang, Jonathan May, Nanyun Peng


Abstract
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.
Anthology ID:
D19-1672
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
6395–6401
Language:
URL:
https://aclanthology.org/D19-1672
DOI:
10.18653/v1/D19-1672
Bibkey:
Cite (ACL):
Xiaolei Huang, Jonathan May, and Nanyun Peng. 2019. What Matters for Neural Cross-Lingual Named Entity Recognition: An Empirical Analysis. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 6395–6401, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
What Matters for Neural Cross-Lingual Named Entity Recognition: An Empirical Analysis (Huang et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/D19-1672.pdf