QUERY-SYNERGY: Leveraging English for Improving Retrieval Performance Across Multiple Languages

ACL ARR 2025 July Submission1432 Authors

Abstract: We propose Query-Synergy, a training-free approach to improving retrieval performance using multilingual embeddings. Retrieval systems depend on queries that match the document language, which may not fully exploit the abundant semantic representations available in high-resource languages. Our method utilizes additional queries in English to complement source language queries. Our method integrates similarity scores from both queries, effectively improving retrieval performance. We evaluate our approach across five languages (Arabic, Chinese, Greek, Thai, and Turkish) using four multilingual embedding models on two datasets. Our experiments show that this approach outperforms conventional source query retireval methods, achieving superior nDCG scores across various configurations and translation settings. These results confirm that Query-Synergy is a simple yet effective method for retrieval across multiple languages.

Paper Type: Short

Research Area: Multilingualism and Cross-Lingual NLP

Research Area Keywords: Multilingualism, multilingual representations, dense retrieval, passage retrieval, resources for less-resourced languages

Contribution Types: Approaches to low-resource settings, Approaches low compute settings-efficiency, Publicly available software and/or pre-trained models

Languages Studied: Arabic, Chinese, English, Greek, Thai, Turkish

Previous URL: https://openreview.net/forum?id=Oite6h4khG

Reassignment Request Area Chair: Yes, I want a different area chair for our submission

Reassignment Request Reviewers: Yes, I want a different set of reviewers

A1 Limitations Section: This paper has a limitations section.

A2 Potential Risks: Yes

A2 Elaboration: Limitations

B Use Or Create Scientific Artifacts: Yes

B1 Cite Creators Of Artifacts: Yes

B1 Elaboration: Section3 and Appendix A

B2 Discuss The License For Artifacts: Yes

B2 Elaboration: Section3 and Appendix A

B3 Artifact Use Consistent With Intended Use: Yes

B3 Elaboration: Section3 and Appendix A

B4 Data Contains Personally Identifying Info Or Offensive Content: N/A

B5 Documentation Of Artifacts: N/A

B6 Statistics For Data: No

B6 Elaboration: The datasets are publicly available, so readers can see it.

C Computational Experiments: Yes

C1 Model Size And Budget: Yes

C1 Elaboration: Section3 and Appendix A

C2 Experimental Setup And Hyperparameters: Yes

C2 Elaboration: Section3, 4 and Appendix A

C3 Descriptive Statistics: Yes

C3 Elaboration: Section3,4

C4 Parameters For Packages: Yes

C4 Elaboration: Section3

D Human Subjects Including Annotators: No

D1 Instructions Given To Participants: N/A

D2 Recruitment And Payment: N/A

D3 Data Consent: N/A

D4 Ethics Review Board Approval: N/A

D5 Characteristics Of Annotators: N/A

E Ai Assistants In Research Or Writing: No

E1 Information About Use Of Ai Assistants: N/A

Author Submission Checklist: yes

Submission Number: 1432