Enhancing Cross-lingual Transfer by Manifold MixupDownload PDF

Published: 28 Jan 2022, Last Modified: 22 Oct 2023ICLR 2022 PosterReaders: Everyone
Keywords: cross-lingual transfer, cross-lingual understanding, manifold mixup
Abstract: 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.
One-sentence Summary: We propose the cross-lingual manifold mixup method to improve the cross-lingual transfer.
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 2 code implementations](https://www.catalyzex.com/paper/arxiv:2205.04182/code)
17 Replies