Prompt-Tuning Can Be Much Better Than Fine-Tuning on Cross-lingual Understanding With Multilingual Language Models

Lifu Tu, Caiming Xiong, Yingbo Zhou


Abstract
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-lingualevaluation 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 transfer-ability of representations on downstream tasks with better aligned decision boundaries.
Anthology ID:
2022.findings-emnlp.401
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5478–5485
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.401
DOI:
10.18653/v1/2022.findings-emnlp.401
Bibkey:
Cite (ACL):
Lifu Tu, Caiming Xiong, and Yingbo Zhou. 2022. Prompt-Tuning Can Be Much Better Than Fine-Tuning on Cross-lingual Understanding With Multilingual Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 5478–5485, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Prompt-Tuning Can Be Much Better Than Fine-Tuning on Cross-lingual Understanding With Multilingual Language Models (Tu et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.401.pdf