Cross-lingual Data Augmentation versus Multilingual Transfer Learning for Zero-shot XNLI Performance in Low-resource Languages

While natural language processing systems often focus on a single language, multilingual transfer learning has the potential to improve performance, especially for low-resource languages. We introduce XLDA, cross-lingual data augmentation, a method that replaces a segment of the input text with its translation in another language. XLDA enhances performance of all 14 tested languages of the cross-lingual natural language inference (XNLI) benchmark. With improvements of up to \$4.8\%\$, training with XLDA achieves state-of-the-art performance for Greek, Turkish, and Urdu. XLDA is in contrast to, a

Research goal: How does the cross-lingual data augmentation (XLDA) method compare to other multilingual transfer learning techniques (e.g., multitask fine-tuning, cross-lingual pretraining) in terms of zero-shot performance on the XNLI benchmark, particularly for low-resource languages?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.9/10.