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


Abstract
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 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.
Anthology ID:
2022.findings-emnlp.132
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1837–1843
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.132
DOI:
10.18653/v1/2022.findings-emnlp.132
Bibkey:
Cite (ACL):
Jiali Zeng, Yufan Jiang, Yongjing Yin, Xu Wang, Binghuai Lin, and Yunbo Cao. 2022. DualNER: A Dual-Teaching framework for Zero-shot Cross-lingual Named Entity Recognition. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 1837–1843, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
DualNER: A Dual-Teaching framework for Zero-shot Cross-lingual Named Entity Recognition (Zeng et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.132.pdf