Prompt-Tuning Can Be Much Better Than Fine-Tuning on Cross-lingual Understanding With Multilingual Language Models
This addresses the problem of efficient cross-lingual transfer for natural language understanding tasks, showing a significant improvement over standard methods.
The paper tackles cross-lingual understanding by comparing prompt-tuning to fine-tuning on multilingual language models, finding that prompt-tuning achieves much better transfer across languages with only 0.1% to 0.3% tuned parameters.
Pre-trained multilingual language models show significant performance gains for zero-shot cross-lingual model transfer on a wide range of natural language understanding (NLU) tasks. Previously, for zero-shot cross-lingual evaluation, pre-trained models are only fine-tuned on English data and tested on a variety of target languages. In this paper, we do cross-lingual evaluation on various NLU tasks (sentence classification, sequence labeling, question answering) using prompt-tuning and compare it with fine-tuning. The results show that prompt tuning achieves much better cross-lingual transfer than fine-tuning across datasets, with only 0.1% to 0.3% tuned parameters. Additionally, we demonstrate through the analysis that prompt tuning can have better cross-lingual transferability of representations on downstream tasks with better aligned decision boundaries.