Multilingual pre-trained models have achieved remarkable performance on cross-lingual transfer learning. Some multilingual models such as mBERT, have been pre-trained on unlabeled corpora, therefore the embeddings of different languages in the models may not be aligned very well. In this paper, we aim to improve the zero-shot cross-lingual transfer performance by proposing a pre-training task named Word-Exchange Aligning Model (WEAM), which uses the statistical alignment information as the prior knowledge to guide cross-lingual word prediction. We evaluate our model on multilingual machine reading comprehension task MLQA and natural language interface task XNLI. The results show that WEAM can significantly improve the zero-shot performance.
@article{arxiv.2106.01732,
title = {Bilingual Alignment Pre-Training for Zero-Shot Cross-Lingual Transfer},
author = {Ziqing Yang and Wentao Ma and Yiming Cui and Jiani Ye and Wanxiang Che and Shijin Wang},
journal= {arXiv preprint arXiv:2106.01732},
year = {2021}
}