CLEAR: Cross-Lingual Enhancement in Alignment via Reverse-training

TL;DR

CLEAR introduces a reverse-training loss function that enhances cross-lingual retrieval by leveraging English as a bridge, significantly improving performance especially in low-resource languages.

Contribution

The paper proposes a novel reverse-training scheme that improves cross-lingual alignment and retrieval performance, addressing limitations of contrastive learning methods.

Findings

Achieves up to 15% improvement in cross-lingual retrieval tasks.

Enhances performance in low-resource languages without degrading English results.

Effective even in multilingual training scenarios.

Abstract

Existing multilingual embedding models often encounter challenges in cross-lingual scenarios due to imbalanced linguistic resources and less consideration of cross-lingual alignment during training. Although standardized contrastive learning approaches for cross-lingual adaptation are widely adopted, they may struggle to capture fundamental alignment between languages and degrade performance in well-aligned languages such as English. To address these challenges, we propose Cross-Lingual Enhancement in Retrieval via Reverse-training (CLEAR), a novel loss function utilizing a reverse training scheme to improve retrieval performance across diverse cross-lingual retrieval scenarios. CLEAR leverages an English passage as a bridge to strengthen alignments between the target language and English, ensuring robust performance in the cross-lingual retrieval task. Our extensive experiments demonstrate that CLEAR achieves notable improvements in cross-lingual scenarios, with gains up to 15%, particularly in low-resource languages, while minimizing performance degradation in English. Furthermore, our findings highlight that CLEAR offers promising effectiveness even in multilingual training, suggesting its potential for broad application and scalability. We release the code at https://github.com/dltmddbs100/CLEAR.