CLJul 21, 2021

Soft Layer Selection with Meta-Learning for Zero-Shot Cross-Lingual Transfer

arXiv:2107.09840v1713 citations
Originality Incremental advance
AI Analysis

This addresses the challenge of fine-tuning multilingual models for better transfer to low-resource languages, though it appears incremental as it builds on existing meta-learning and fine-tuning methods.

The paper tackles the problem of improving zero-shot cross-lingual transfer by proposing a meta-optimizer to soft-select layers to freeze during fine-tuning, resulting in performance gains over baselines on cross-lingual natural language inference tasks.

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).

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes