Synergistic Approach for Simultaneous Optimization of Monolingual, Cross-lingual, and Multilingual Information Retrieval
This addresses the challenge of language bias in multilingual information retrieval for NLP applications, though it is incremental as it builds on existing multilingual pre-trained models.
The paper tackled the problem of optimizing information retrieval across monolingual, cross-lingual, and multilingual settings simultaneously, proposing a hybrid batch training strategy that achieved comparable or superior zero-shot retrieval results on benchmark datasets like XQuAD-R, MLQA-R, and MIRACL while reducing language bias.
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 language models using a mix of monolingual and cross-lingual question-answer pair batches sampled based on dataset size. Experiments on XQuAD-R, MLQA-R, and MIRACL benchmark datasets show that the proposed method consistently achieves comparable or superior results in zero-shot retrieval across various languages and retrieval tasks compared to monolingual-only or cross-lingual-only training. Hybrid batch training also substantially reduces language bias in multilingual retrieval compared to monolingual training. These results demonstrate the effectiveness of the proposed approach for learning language-agnostic representations that enable strong zero-shot retrieval performance across diverse languages.