Zero-Shot Cross-Lingual Retrieval Accuracy of Multilingual Encoders Trained with Hybrid Batches and Code-Switching Data

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 impact of incorporating a code-switching dataset (e.g., WMT) on the zero-shot cross-lingual retrieval accuracy of multilingual encoders trained with the hybrid batch strategy, as evaluated on the MKQA benchmark?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.8/10.