H+ Embedding: Harmonizing Global and Token-Level Retrieval with Context-Dependent Phrases

2026-07-28

AI Summary

Existing retrieval methods struggle to balance global semantic compression with fine-grained token-level interactions in terminology-intensive tasks, resulting in a pronounced trade-off between indexing cost and retrieval effectiveness. This work proposes a unified multi-granularity retrieval framework that introduces, for the first time, context-dependent variable-length phrases as an intermediate retrieval unit, while preserving uncovered tokens as singletons. The approach integrates importance-guided unit selection with a weighted MaxSim interaction mechanism. Evaluated across 16 scientific, medical, and bilingual retrieval tasks, the phrase-based branch achieves an average improvement of 6.91 macro nDCG@10 over the global branch and approaches token-level performance while reducing document vectors by only 13.7%, substantially enhancing both effectiveness and efficiency in terminology-dense retrieval scenarios.

Abstract

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.

Problem

• terminology-intensive retrieval
• multi-granularity retrieval
• context-dependent phrases
• token-level interaction
• global vector representation

Innovation

• context-dependent phrases
• multi-granularity retrieval
• H+ Embedding
• importance-guided unit selection
• weighted MaxSim