Comparative Scaling of Cross-Lingual Retrieval via Optimal Transport versus Contrastive Distillation in Low-Resource XLSD

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 comparative effect of optimal transport distillation versus contrastive distillation on the scaling behavior of cross-lingual retrieval accuracy when increasing the number of low-resource languages in the XLSD dataset?

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