We present DualNER, a simple and effective framework to make full use of both annotated source language corpus and unlabeled target language text for zero-shot cross-lingual named entity recognition (NER). In particular, we combine two complementary learning paradigms of NER, i.e., sequence labeling and span prediction, into a unified multi-task framework. After obtaining a sufficient NER model trained on the source data, we further train it on the target data in a {\it dual-teaching} manner, in which the pseudo-labels for one task are constructed from the prediction of the other task. Moreover, based on the span prediction, an entity-aware regularization is proposed to enhance the intrinsic cross-lingual alignment between the same entities in different languages. Experiments and analysis demonstrate the effectiveness of our DualNER. Code is available at https://github.com/lemon0830/dualNER.
@article{arxiv.2211.08104,
title = {DualNER: A Dual-Teaching framework for Zero-shot Cross-lingual Named Entity Recognition},
author = {Jiali Zeng and Yufan Jiang and Yongjing Yin and Xu Wang and Binghuai Lin and Yunbo Cao},
journal= {arXiv preprint arXiv:2211.08104},
year = {2022}
}