Enhanced Meta-Learning for Cross-Lingual Named Entity Recognition with Minimal Resources


  • Qianhui Wu Tsinghua University
  • Zijia Lin Microsoft Research
  • Guoxin Wang Microsoft Research
  • Hui Chen Tsinghua University
  • Börje F. Karlsson Microsoft Research
  • Biqing Huang Tsinghua University
  • Chin-Yew Lin Microsoft Research




For languages with no annotated resources, transferring knowledge from rich-resource languages is an effective solution for named entity recognition (NER). While all existing methods directly transfer from source-learned model to a target language, in this paper, we propose to fine-tune the learned model with a few similar examples given a test case, which could benefit the prediction by leveraging the structural and semantic information conveyed in such similar examples. To this end, we present a meta-learning algorithm to find a good model parameter initialization that could fast adapt to the given test case and propose to construct multiple pseudo-NER tasks for meta-training by computing sentence similarities. To further improve the model's generalization ability across different languages, we introduce a masking scheme and augment the loss function with an additional maximum term during meta-training. We conduct extensive experiments on cross-lingual named entity recognition with minimal resources over five target languages. The results show that our approach significantly outperforms existing state-of-the-art methods across the board.




How to Cite

Wu, Q., Lin, Z., Wang, G., Chen, H., Karlsson, B. F., Huang, B., & Lin, C.-Y. (2020). Enhanced Meta-Learning for Cross-Lingual Named Entity Recognition with Minimal Resources. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05), 9274-9281. https://doi.org/10.1609/aaai.v34i05.6466



AAAI Technical Track: Natural Language Processing