用上下文相关短语提升检索精度与效率
H+ Embedding: Harmonizing Global and Token-Level Retrieval with Context-Dependent Phrases
- 根据上下文动态划分短语，融合全局向量与词粒度检索
- 在16项任务中，短语分支比全局向量高出6.91点nDCG@10
- 仅需13.7%更少的文档向量，适合资源受限场景
术语密集型检索，尤其在医疗领域，依赖于保留多词实体、缩写、数值约束和组合概念。现有表示方法处于两个极端：单向量检索器常过度压缩局部相关性信号，而词粒度晚期交互则保留每个分词子词，带来显著的索引、存储和打分开销。本文提出H+ Embedding，一种统一的多粒度检索框架，可预测变长短语片段，将未覆盖词保留为独立单元，并通过重要性引导的单元选择实现加权最大相似度交互。在16个科学、医学及双语任务上，其短语检索分支在宏平均nDCG@10上比全局检索分支高6.91点。同时，仅使用13.7%更少的文档向量，接近词粒度性能，且在中等向量预算下优于无内容依赖的分组规则。上下文相关的短语交互为实际检索系统提供了介于全局压缩与词粒度交互之间的质量-成本平衡点。
原文摘要 · Abstract (English)
Terminology-intensive retrieval, especially in medical settings, depends on preserving multi-word entities, abbreviations, numerical constraints, and compositional concepts. However, existing representations lie at two extremes: single-vector retrievers often over-compress local relevance signals, while token-level late interaction retains every tokenizer subword at substantial indexing, storage, and scoring cost. This mismatch raises a natural question: can context-dependent phrases provide a useful retrieval unit between global vectors and tokens? We introduce H+ Embedding, a unified multi-granularity retriever that predicts variable-length phrase partitions, preserves uncovered tokens as singletons, and applies importance-guided unit selection with weighted MaxSim interaction. Across 16 scientific, medical, and bilingual tasks, its phrase retrieval branch exceeds the global retrieval branch by 6.91 macro nDCG@10. It also nearly matches Token while using 13.7% fewer document vectors and outperforms content-independent grouping rules under moderate vector budgets. Context-dependent phrase interaction therefore provides an intermediate quality-cost point between global compression and token-level interaction for practical retrieval systems.
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。