Empowering Dual-encoder With Query Generator For Cross-lingual Dense Retrieval

Abstract

In monolingual dense retrieval, lots of works focus on how to distill knowledge from cross-encoder re-ranker to dual-encoder retriever and these methods achieve better performance due to the effectiveness of cross-encoder re-ranker. However, we find that the performance of the cross-encoder re-ranker is heavily influenced by the number of training samples and the quality of negative samples, which is hard to obtain in the cross-lingual setting. In this paper, we propose to use a query generator as the teacher in the cross-lingual setting, which is less dependent on enough training samples and high-quality negative samples. In addition to traditional knowledge distillation, we further propose a novel enhancement method, which uses the query generator to help the dual-encoder align queries from different languages, but does not need any additional parallel sentences. The experimental results show that our method outperforms the state-of-the-art methods on two benchmark datasets.

Stats

• citations6
• S2 citations—
• github stars0
• HF likes0
• heat score6.34
• arxiv keyren2023empowering

Related papers

• Augmenting Passage Representations With Query Generation For Enhanced Cross-lingual Dense Retrieval (2023)8.14
• Translate-distill: Learning Cross-language Dense Retrieval By Translation And Distillation (2024)8.60
• Learning Diverse Document Representations With Deep Query Interactions For Dense Retrieval (2022)2.51
• Boosting Data Utilization For Multilingual Dense Retrieval (2025)0.00
• What Drives Cross-lingual Ranking? Retrieval Approaches With Multilingual Language Models (2025)0.00
• Query Encoder Distillation Via Embedding Alignment Is A Strong Baseline Method To Boost Dense Retriever Online Efficiency (2023)0.00
• On Cross-lingual Retrieval With Multilingual Text Encoders (2021)10.35
• How To Make Cross Encoder A Good Teacher For Efficient Image-text Retrieval? (2024)5.24