Based on large-scale pre-trained multilingual representations, recent cross-lingual transfer methods have achieved impressive transfer performances. However, the performance of target languages still lags far behind the source language. In this paper, our analyses indicate such a performance gap is strongly associated with the cross-lingual representation discrepancy. To achieve better cross-lingual transfer performance, we propose the cross-lingual manifold mixup (X-Mixup) method, which adaptively calibrates the representation discrepancy and gives a compromised representation for target languages. Experiments on the XTREME benchmark show X-Mixup achieves 1.8% performance gains on multiple text understanding tasks, compared with strong baselines, and significantly reduces the cross-lingual representation discrepancy.
@article{arxiv.2205.04182,
title = {Enhancing Cross-lingual Transfer by Manifold Mixup},
author = {Huiyun Yang and Huadong Chen and Hao Zhou and Lei Li},
journal= {arXiv preprint arXiv:2205.04182},
year = {2022}
}