CLAIMay 9, 2022

Enhancing Cross-lingual Transfer by Manifold Mixup

CMU
arXiv:2205.04182v149 citationsh-index: 60
Originality Incremental advance
AI Analysis

It improves cross-lingual transfer for multilingual NLP tasks, but is incremental as it builds on existing pre-trained representations.

The paper tackles the performance gap between source and target languages in cross-lingual transfer by addressing cross-lingual representation discrepancy, proposing X-Mixup which achieves 1.8% performance gains on the XTREME benchmark.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes