Scaling Retrieval Accuracy of XLM-R with Optimal Transport Distillation in Low-Resource Languages on MTOP

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 retrieval accuracy of XLM-R with optimal transport distillation scale with varying amounts of labeled training data in low-resource languages, as measured by MRR or NDCG on MTOP?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.7/10.