Optimal Transport Distillation versus Teacher-Student Knowledge Distillation for Multimodal Low-Resource Retrieval on Multi30k

Benefiting from transformer-based pre-trained language models, neural ranking models have made significant progress. More recently, the advent of multilingual pre-trained language models provides great support for designing neural cross-lingual retrieval models. However, due to unbalanced pre-training data in different languages, multilingual language models have already shown a performance gap between high and low-resource languages in many downstream tasks. And cross-lingual retrieval models built on such pre-trained models can inherit language bias, leading to suboptimal result for low-reso

Research goal: What is the effect of optimal transport distillation on the convergence speed and final retrieval accuracy of multimodal models for low-resource languages in the Multi30k dataset relative to teacher-student knowledge distillation?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.6/10.