Abstract
Prompting shows promising results in few-shot scenarios. However, its strength for multilingual/cross-lingual problems has not been fully exploited. hao and Schütze (2021) made initial explorations in this direction by presenting that cross-lingual prompting outperforms cross-lingual finetuning. In this paper, we conduct an empirical exploration on the effect of each component in cross-lingual prompting and derive Universal Prompting, which helps alleviate the discrepancies between source-language training and target-language inference. Based on this, we propose DPA, a dual prompt augmentation framework, aiming at relieving the data scarcity issue in few-shot cross-lingual prompting. Notably, for XNLI, our method achieves 46.54% with only 16 English training examples per class, significantly better than 34.99% of fine-tuning. Our code is available at https://github.com/DAMO-NLP-SG/DPA.- Anthology ID:
- 2023.findings-acl.700
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2023
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 11008–11020
- Language:
- URL:
- https://aclanthology.org/2023.findings-acl.700
- DOI:
- 10.18653/v1/2023.findings-acl.700
- Cite (ACL):
- Meng Zhou, Xin Li, Yue Jiang, and Lidong Bing. 2023. Enhancing Cross-lingual Prompting with Dual Prompt Augmentation. In Findings of the Association for Computational Linguistics: ACL 2023, pages 11008–11020, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Enhancing Cross-lingual Prompting with Dual Prompt Augmentation (Zhou et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2023.findings-acl.700.pdf