用动态顶p掩码提升跨语言检索效果
Top-P Masking for Cross Language Information Retrieval
- 采用类似大模型核采样的顶p动态掩码策略
- 在跨语言检索任务中超越传统顶k掩码
- 适合需要高效稀疏表示的多语言信息检索场景
Top-K 掩码已被用于信息检索任务以促进稀疏表示，作为浮点运算每秒（FLOPS）正则化的简单替代方案。例如，双语词汇与文档扩展模型（BLADE）将此方法作为后处理阶段使用。本文提出采用类似于大语言模型中核采样（Nucleus Sampling）的顶p动态掩码，并在跨语言信息检索（CLIR）领域验证其性能优于传统的 Top-K 掩码。
原文摘要 · Abstract (English)
Top-K masking schemes have been proposed as a method to promote sparse representations in Information Retrieval (IR) tasks, as a simple alternative to Floating Point Operations per Second (FLOPS) regularization. Algorithms such as Bilingual Lexical and Document Expansion Model (BLADE), adopt this approach as a post-processing stage. We propose using Top-P Dynamic Masking similar to Nucleus Sampling in Large Language Models, and demonstrate better performance than Top-K masking. Specifically, we evaluate our methods in the domain of Cross Language Information Retrieval (CLIR)
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。