用多语言语义桥，让稀疏编码器跨语言精准检索
SemBridge: Language Transfer in Sparse Encoders via Multilingual Semantic Bridges
- 用多语言稠密嵌入做桥梁，对齐源语言与目标语言词汇语义
- 仅选少量核心同义词初始化目标语言词，提升检索精度
- 跨5语言4架构验证，零样本和微调后均优于现有方法
稀疏编码器通过词汇空间中的词重要性表示实现高精度检索，但其以英语为中心的结构严重限制了非英语语言的迁移能力。为此，我们提出SemBridge，一种基于多语言桥模型的嵌入初始化方法，用于稀疏编码器的跨语言适应。SemBridge利用多语言稠密嵌入作为桥梁，建立源语言与目标语言词汇间的语义对齐。不依赖全部源语言词，而是选择少量语义相关源词，用它们初始化每个目标语言词，有效过滤语义噪声，并将目标词重构为关键同义词的精确线性组合。该方法加速微调收敛，提升训练效率。在五种语言和四种稀疏架构上的大量实验表明，SemBridge在零样本检索中表现更优，且微调后检索性能持续领先基线。结果验证了SemBridge在多语言环境下部署高性能稀疏检索系统的实用性。
原文摘要 · Abstract (English)
Sparse encoders offer high-precision retrieval by representing term importance within a vocabulary space, yet their English-centric structures pose a critical impediment to language transfer for non-English languages. To overcome this structural limitation, we propose SemBridge, a novel embedding initialization method designed for cross-lingual adaptation in sparse encoders by leveraging multilingual bridge models. SemBridge establishes semantic alignments between source and target vocabularies using multilingual dense embeddings as a bridge. Rather than directly relying on all source tokens, SemBridge selects a small set of semantically related source-language tokens and uses them to initialize each target-language token, effectively filtering out semantic noise and reconstructing target tokens as precise linear combinations of core synonyms. This accelerates convergence during fine-tuning and improves training efficiency. Extensive experiments across five languages and four sparse architectures demonstrate that SemBridge achieves superior zero-shot retrieval performance and consistently improves retrieval performance after fine-tuning compared to existing baselines. These results validate SemBridge as a practical solution for deploying high-performance sparse retrieval systems in diverse linguistic environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。