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 minimizing cross-lingual divergence using Optimal Transport improve F1 scores on SPARQL-S2S for low-resource languages more effectively than traditional data augmentation techniques? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.6/10.

This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 8.6/10.