DualNER: A Dual-Teaching framework for Zero-shot Cross-lingual Named Entity Recognition
Jiali Zeng, Yufan Jiang, Yongjing Yin, Xu Wang, Binghuai Lin, Yunbo Cao · 2022
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 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 entityaware 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.