用固定数量向量编码文档，显著降低存储开销且保持检索效果
Efficient Constant-Space Multi-Vector Retrieval
- 将文档映射为固定数量的向量，不再绑定原始词元
- 在MSMARCO和BEIR上保持原模型90%以上的检索效果
- 适合大规模检索系统，尤其关注存储效率的场景
多向量检索方法（如ColBERT）在检索延迟与效果之间表现出良好平衡，但需为输入语料库中每个词元存储（可能压缩的）向量，导致存储成本高昂。为此，我们提出将文档编码为固定数量的向量，这些向量不再与输入词元一一对应。该方法不仅大幅降低存储开销，还使文档表示在磁盘上大小固定，有助于操作系统的页面管理。在MSMARCO段落语料库和BEIR基准上，基于ColBERT-v2架构的实验表明，将段落有效编码为固定数量向量后，仍可保持原始性能的绝大部分。
原文摘要 · Abstract (English)
Multi-vector retrieval methods, exemplified by the ColBERT architecture, have shown substantial promise for retrieval by providing strong trade-offs in terms of retrieval latency and effectiveness. However, they come at a high cost in terms of storage since a (potentially compressed) vector needs to be stored for every token in the input collection. To overcome this issue, we propose encoding documents to a fixed number of vectors, which are no longer necessarily tied to the input tokens. Beyond reducing the storage costs, our approach has the advantage that document representations become of a fixed size on disk, allowing for better OS paging management. Through experiments using the MSMARCO passage corpus and BEIR with the ColBERT-v2 architecture, a representative multi-vector ranking model architecture, we find that passages can be effectively encoded into a fixed number of vectors while retaining most of the original effectiveness.
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。