Robustness of Hybrid Batch Training in Multilingual Retrieval Under Domain Shift
Description
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: How does the robustness of hybrid batch training with optimized sample ratios perform against domain shift in multilingual retrieval tasks, compared to independent monolingual and cross-lingual training, when evaluated using MRR and recall@k across diverse domains?
Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.1/10.