Wider & Closer: Mixture of Short-channel Distillers for Zero-shot Cross-lingual Named Entity Recognition

Jun-Yu Ma, Beiduo Chen, Jia-Chen Gu, Zhenhua Ling, Wu Guo, Quan Liu, Zhigang Chen, Cong Liu


Abstract
Zero-shot cross-lingual named entity recognition (NER) aims at transferring knowledge from annotated and rich-resource data in source languages to unlabeled and lean-resource data in target languages. Existing mainstream methods based on the teacher-student distillation framework ignore the rich and complementary information lying in the intermediate layers of pre-trained language models, and domain-invariant information is easily lost during transfer. In this study, a mixture of short-channel distillers (MSD) method is proposed to fully interact the rich hierarchical information in the teacher model and to transfer knowledge to the student model sufficiently and efficiently. Concretely, a multi-channel distillation framework is designed for sufficient information transfer by aggregating multiple distillers as a mixture. Besides, an unsupervised method adopting parallel domain adaptation is proposed to shorten the channels between the teacher and student models to preserve domain-invariant features. Experiments on four datasets across nine languages demonstrate that the proposed method achieves new state-of-the-art performance on zero-shot cross-lingual NER and shows great generalization and compatibility across languages and fields.
Anthology ID:
2022.emnlp-main.345
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5171–5183
Language:
URL:
https://aclanthology.org/2022.emnlp-main.345
DOI:
10.18653/v1/2022.emnlp-main.345
Bibkey:
Cite (ACL):
Jun-Yu Ma, Beiduo Chen, Jia-Chen Gu, Zhenhua Ling, Wu Guo, Quan Liu, Zhigang Chen, and Cong Liu. 2022. Wider & Closer: Mixture of Short-channel Distillers for Zero-shot Cross-lingual Named Entity Recognition. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 5171–5183, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Wider & Closer: Mixture of Short-channel Distillers for Zero-shot Cross-lingual Named Entity Recognition (Ma et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.345.pdf