Boosting Data Utilization for Multilingual Dense Retrieval
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909781970649088 |
|---|---|
| author | Huang, Chao Mo, Fengran Chen, Yufeng Guan, Changhao Yue, Zhenrui Wang, Xinyu Xu, Jinan Huang, Kaiyu |
| author_facet | Huang, Chao Mo, Fengran Chen, Yufeng Guan, Changhao Yue, Zhenrui Wang, Xinyu Xu, Jinan Huang, Kaiyu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_09459 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Boosting Data Utilization for Multilingual Dense Retrieval Huang, Chao Mo, Fengran Chen, Yufeng Guan, Changhao Yue, Zhenrui Wang, Xinyu Xu, Jinan Huang, Kaiyu Information Retrieval 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. |
| title | Boosting Data Utilization for Multilingual Dense Retrieval |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2509.09459 |