Abstract
Multilingual pre-trained contextual embedding models (Devlin et al., 2019) have achieved impressive performance on zero-shot cross-lingual transfer tasks. Finding the most effective fine-tuning strategy to fine-tune these models on high-resource languages so that it transfers well to the zero-shot languages is a non-trivial task. In this paper, we propose a novel meta-optimizer to soft-select which layers of the pre-trained model to freeze during fine-tuning. We train the meta-optimizer by simulating the zero-shot transfer scenario. Results on cross-lingual natural language inference show that our approach improves over the simple fine-tuning baseline and X-MAML (Nooralahzadeh et al., 2020).- Anthology ID:
- 2021.metanlp-1.2
- Volume:
- Proceedings of the 1st Workshop on Meta Learning and Its Applications to Natural Language Processing
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Venue:
- MetaNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 11–18
- Language:
- URL:
- https://aclanthology.org/2021.metanlp-1.2
- DOI:
- 10.18653/v1/2021.metanlp-1.2
- Cite (ACL):
- Weijia Xu, Batool Haider, Jason Krone, and Saab Mansour. 2021. Soft Layer Selection with Meta-Learning for Zero-Shot Cross-Lingual Transfer. In Proceedings of the 1st Workshop on Meta Learning and Its Applications to Natural Language Processing, pages 11–18, Online. Association for Computational Linguistics.
- Cite (Informal):
- Soft Layer Selection with Meta-Learning for Zero-Shot Cross-Lingual Transfer (Xu et al., MetaNLP 2021)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2021.metanlp-1.2.pdf
- Data
- XNLI