复现发现长文档检索中首段内容主导性能表现
On the Reproducibility of Learned Sparse Retrieval Adaptations for Long Documents
- 复现多种长文档稀疏检索适配方法，验证其核心机制
- 首段信息在长文档检索中始终占据主导地位，贡献超70%效果
- 适用于对检索可解释性、模型稳定性有要求的研究者
文档检索是信息检索中的核心挑战，尤其在处理长文本时，常导致查询延迟上升与计算开销增加。近年来，学习型稀疏检索（LSR）成为应对该问题的可行方案。部分研究尝试通过分段聚合方式（如n-gram、邻近度评分、表征调整及信号集成）将LSR扩展至长文档场景。本研究旨在复现并深入分析此类方法的实现机制。实验表明，特定段落（尤其是首段）对检索性能具有决定性影响，其贡献显著高于其他段落。我们还对近期提出的ExactSDM和SoftSDM方法在不同长度文档（短至2段，长至3段以上）上进行了再评估，并设计多维度分析以探究全局信息在长文本适配中的作用。项目完整代码已开源：https://github.com/lionisakis/Reproducibilitiy-lsr-long。
原文摘要 · Abstract (English)
Document retrieval is one of the most challenging tasks in Information Retrieval. It requires handling longer contexts, often resulting in higher query latency and increased computational overhead. Recently, Learned Sparse Retrieval (LSR) has emerged as a promising approach to address these challenges. Some have proposed adapting the LSR approach to longer documents by aggregating segmented document using different post-hoc methods, including n-grams and proximity scores, adjusting representations, and learning to ensemble all signals. In this study, we aim to reproduce and examine the mechanisms of adapting LSR for long documents. Our reproducibility experiments confirmed the importance of specific segments, with the first segment consistently dominating document retrieval performance. Furthermore, We re-evaluate recently proposed methods -- ExactSDM and SoftSDM -- across varying document lengths, from short (up to 2 segments) to longer (3+ segments). We also designed multiple analyses to probe the reproduced methods and shed light on the impact of global information on adapting LSR to longer contexts. The complete code and implementation for this project is available at: https://github.com/lionisakis/Reproducibilitiy-lsr-long.
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。