Boosting Data Utilization for Multilingual Dense Retrieval
Year: 2025
Type: preprint
Abstract: Multilingual dense retrieval aims to retrieve relevant documents across different languages based on a unified retriever model. The challenge lies in aligning representations of different languages in a shared vector space. The common practice is to fine-tune the dense retriever via contrastive learning, whose effectiveness highly relies on the quality of the negative sample and the efficacy of mini-batch data. Different from the existing studies that focus on developing sophisticated model architecture, we propose a method to boost data utilization for multilingual dense retrieval by obtaining high-quality hard negative samples and effective mini-batch data. The extensive experimental results on a multilingual retrieval benchmark, MIRACL, with 16 languages demonstrate the effectiveness of our method by outperforming several existing strong baselines.
Source: arXiv (Cornell University)
Authors: Huang, Chao, Mo, Fengran, Chen, Yufeng, Guan, Changhao, Yue, Zhenrui, Wang, Xinyu, Xu, Jinan, Huang, Kaiyu
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7081571994
Cites:
Cited by:
Related to: