Comparing Optimal Transport and KL-Divergence Distillation for Zero-Shot Cross-Lingual Retrieval on XQuAD

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: How does optimal transport distillation compare to standard KL-divergence distillation in improving zero-shot cross-lingual retrieval accuracy on the XQuAD benchmark for low-resource languages?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.5/10.