Optimal Transport Distillation for mBERT Performance Variance Reduction in MIRACL Retrieval

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: Does applying optimal transport distillation to mBERT reduce the performance variance between high and low-resource languages on the MIRACL retrieval benchmark more effectively than contrastive learning objectives?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.2/10.