Hybrid Training Data Ratios and Retrieval Robustness Across Diverse Language Pairs in MKQA

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 varying the ratio of monolingual and cross-lingual data in the hybrid training approach on the robustness of retrieval performance across diverse language pairs in MKQA?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.1/10.