Cross-Lingual BERT Transformation for Zero-Shot Dependency Parsing

Yuxuan Wang, Wanxiang Che, Jiang Guo, Yijia Liu, Ting Liu


Abstract
This paper investigates the problem of learning cross-lingual representations in a contextual space. We propose Cross-Lingual BERT Transformation (CLBT), a simple and efficient approach to generate cross-lingual contextualized word embeddings based on publicly available pre-trained BERT models (Devlin et al., 2018). In this approach, a linear transformation is learned from contextual word alignments to align the contextualized embeddings independently trained in different languages. We demonstrate the effectiveness of this approach on zero-shot cross-lingual transfer parsing. Experiments show that our embeddings substantially outperform the previous state-of-the-art that uses static embeddings. We further compare our approach with XLM (Lample and Conneau, 2019), a recently proposed cross-lingual language model trained with massive parallel data, and achieve highly competitive results.
Anthology ID:
D19-1575
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
5721–5727
Language:
URL:
https://aclanthology.org/D19-1575
DOI:
10.18653/v1/D19-1575
Bibkey:
Cite (ACL):
Yuxuan Wang, Wanxiang Che, Jiang Guo, Yijia Liu, and Ting Liu. 2019. Cross-Lingual BERT Transformation for Zero-Shot Dependency Parsing. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 5721–5727, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Cross-Lingual BERT Transformation for Zero-Shot Dependency Parsing (Wang et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1575.pdf
Attachment:
 D19-1575.Attachment.pdf
Code
 WangYuxuan93/CLBT