Soft Layer Selection with Meta-Learning for Zero-Shot Cross-Lingual Transfer
arXiv:2107.09840
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).
arXiv commentMetaNLP at ACL 2021
References in corpus (8)
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Neural Architecture Search with Reinforcement Learning
- Large-Scale Evolution of Image Classifiers
- Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks
- Learned Optimizers that Scale and Generalize
- Zero-Shot Cross-lingual Classification Using Multilingual Neural Machine Translation
- Exploring Fine-tuning Techniques for Pre-trained Cross-lingual Models via Continual Learning
- Enhanced Meta-Learning for Cross-lingual Named Entity Recognition with Minimal Resources