Neural IR has advanced through two distinct paths: entity-oriented approaches leveraging knowledge graphs and multi-vector models capturing fine-grained semantics. We introduce QDER, a neural re-ranking model that unifies these approaches by integrating knowledge graph semantics into a multi-vector model. QDER's key innovation lies in its modeling of query-document relationships: rather than computing similarity scores on aggregated embeddings, we maintain individual token and entity representations throughout the ranking process, performing aggregation only at the final scoring stage - an approach we call "late aggregation." We first transform these fine-grained representations through learned attention patterns, then apply carefully chosen mathematical operations for precise matches. Experiments across five standard benchmarks show that QDER achieves significant performance gains, with improvements of 36% in nDCG@20 over the strongest baseline on TREC Robust 2004 and similar improvements on other datasets. QDER particularly excels on difficult queries, achieving an nDCG@20 of 0.70 where traditional approaches fail completely (nDCG@20 = 0.0), setting a foundation for future work in entity-aware retrieval.

翻译：神经信息检索沿着两条不同的路径发展：利用知识图谱的实体导向方法，以及捕捉细粒度语义的多向量模型。我们提出了QDER，一种通过将知识图谱语义整合到多向量模型中从而统一这两种方法的神经重排序模型。QDER的核心创新在于其对查询-文档关系的建模：我们不在聚合嵌入上计算相似度分数，而是在整个排序过程中保持独立的词元表示和实体表示，仅在最终打分阶段进行聚合——我们称这种方法为“延迟聚合”。我们首先通过学习的注意力模式转换这些细粒度表示，然后应用精心选择的数学运算以实现精确匹配。在五个标准基准上的实验表明，QDER取得了显著的性能提升，在TREC Robust 2004数据集上，其nDCG@20比最强基线提高了36%，在其他数据集上也取得了类似的改进。QDER在处理困难查询时表现尤为突出，在传统方法完全失败（nDCG@20 = 0.0）的情况下，其nDCG@20达到了0.70，为未来实体感知检索的研究奠定了基础。