Soft Layer Selection for Multimodal Zero-Shot Cross-Lingual Transfer

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

Research goal: Can the soft layer selection method be extended to multimodal models (e.g., CLIP, OWL-ViT) to improve zero-shot cross-lingual transfer performance on vision-language tasks, as measured by accuracy on XTREME-R images subtasks?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.5/10.