Cross-Lingual BERT Transformation for Zero-Shot Dependency Parsing
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.
Cite
@article{arxiv.1909.06775,
title = {Cross-Lingual BERT Transformation for Zero-Shot Dependency Parsing},
author = {Yuxuan Wang and Wanxiang Che and Jiang Guo and Yijia Liu and Ting Liu},
journal= {arXiv preprint arXiv:1909.06775},
year = {2019}
}
Comments
to appear at EMNLP 2019