Impact of Typological Language Features on Zero-Shot Retrieval in XLM-R via Hybrid Batch Training

Information retrieval across different languages is an increasingly important challenge in natural language processing. Recent approaches based on multilingual pre-trained language models have achieved remarkable success, yet they often optimize for either monolingual, cross-lingual, or multilingual retrieval performance at the expense of others. This paper proposes a novel hybrid batch training strategy to simultaneously improve zero-shot retrieval performance across monolingual, cross-lingual, and multilingual settings while mitigating language bias. The approach fine-tunes multilingual lang

Research goal: What is the effect of incorporating typological language features into the hybrid batch training approach on zero-shot retrieval performance in the XLM-R benchmark, measured by NDCG@10 and MAP scores?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.6/10.