Scaling of Cross-Lingual Retrieval Performance with Model Size via Optimal Transport Distillation

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 the performance of cross-lingual retrieval models trained with optimal transport distillation scale with increasing model size, as measured by accuracy on the XTR-TREC benchmark? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.3/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 9.3/10.