Zero-Shot Cross-Lingual Retrieval Performance on Multilingual MS MARCO Across High and Low-Resource Languages

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 zero-shot cross-lingual retrieval models compare between high-resource and low-resource languages when evaluated on the multilingual MS MARCO benchmark, using nDCG@10 as the primary metric?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.7/10.