Dense retrieval methods have demonstrated promising performance in
multilingual information retrieval, where queries and documents can be in
different languages. However, dense retrievers typically require a substantial
amount of paired data, which poses even greater challenges in multilingual
scenarios. This paper introduces UMR, an Unsupervised Multilingual dense
Retriever trained without any paired data. Our approach leverages the sequence
likelihood estimation capabilities of multilingual language models to acquire
pseudo labels for training dense retrievers. We propose a two-stage framework
which iteratively improves the performance of multilingual dense retrievers.
Experimental results on two benchmark datasets show that UMR outperforms
supervised baselines, showcasing the potential of training multilingual
retrievers without paired data, thereby enhancing their practicality. Our
source code, data, and models are publicly available at
this https URL

本研究介绍了 UMR，一种无需配对数据训练的无监督多语言密集检索器，通过利用多语言语言模型的序列似然估计能力来获取密集检索器训练的伪标签，提出了一个两阶段框架，逐步改善多语言密集检索器的性能，实验证明 UMR 优于有监督基线模型，提升了多语言检索器在实际应用中的可行性。