arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2404.02805cs.IR
收藏

使用位向量的高效多向量稠密检索

Efficient Multi-Vector Dense Retrieval Using Bit Vectors

Franco Maria Nardini, Cosimo Rulli, Rossano Venturini

AI总结:

本文提出 EMVB 框架,通过位向量预过滤、SIMD 列向质心交互、PQ 压缩和逐文档词项过滤,实现多向量稠密检索的高效查询处理。

摘要:

稠密检索技术采用预训练大语言模型构建查询和段落的高维表示。这些表示使用高效的相似度度量来计算段落相对于查询的相关性。在这一方向上,多向量表示通过在逐 token 层级对查询和文档进行编码,展现出更高的有效性,但代价是内存占用和查询延迟增加一个数量级。最近,PLAID 通过引入基于质心的词项表示来降低多向量系统的内存影响,从而解决了这些问题。通过利用质心交互机制,PLAID 过滤掉不相关文档,进而降低后续排序阶段的成本。本文提出“使用位向量的高效多向量稠密检索”(EMVB),这是一种用于多向量稠密检索中高效查询处理的新颖框架。首先,EMVB 使用优化的位向量对段落执行高效的预过滤步骤。其次,质心交互的计算按列进行,并利用 SIMD 指令,从而降低其延迟。第三,EMVB 利用乘积量化(PQ)减少存储向量表示的内存占用,同时共同支持快速的延迟交互。第四,我们引入一种逐文档词项过滤方法,进一步提升最后一步的效率。在 MS MARCO 和 LoTTE 上的实验表明,与 PLAID 相比,EMVB 的速度最高提升至 2.8 倍,同时内存占用降低 1.8 倍,且检索准确性没有损失。

英文摘要:

Dense retrieval techniques employ pre-trained large language models to build a high-dimensional representation of queries and passages. These representations compute the relevance of a passage w.r.t. to a query using efficient similarity measures. In this line, multi-vector representations show improved effectiveness at the expense of a one-order-of-magnitude increase in memory footprint and query latency by encoding queries and documents on a per-token level. Recently, PLAID has tackled these problems by introducing a centroid-based term representation to reduce the memory impact of multi-vector systems. By exploiting a centroid interaction mechanism, PLAID filters out non-relevant documents, thus reducing the cost of the successive ranking stages. This paper proposes ``Efficient Multi-Vector dense retrieval with Bit vectors'' (EMVB), a novel framework for efficient query processing in multi-vector dense retrieval. First, EMVB employs a highly efficient pre-filtering step of passages using optimized bit vectors. Second, the computation of the centroid interaction happens column-wise, exploiting SIMD instructions, thus reducing its latency. Third, EMVB leverages Product Quantization (PQ) to reduce the memory footprint of storing vector representations while jointly allowing for fast late interaction. Fourth, we introduce a per-document term filtering method that further improves the efficiency of the last step. Experiments on MS MARCO and LoTTE show that EMVB is up to 2.8x faster while reducing the memory footprint by 1.8x with no loss in retrieval accuracy compared to PLAID.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑