H2CE：面向POI重排序的异构两阶段交叉编码器
原标题：H2CE: Modeling Geo-Semantic Interactions for POI Reranking with Heterogeneous Two-Stage Cross-Encoders
AI 摘要
该论文提出 H2CE，一种用于兴趣点（POI）重排序的异构两阶段交叉编码器。它通过将分桶数值描述符插入交叉编码器输入、并用独立 MLP 处理精确标量值，再经潜在空间聚合融合语义与数值嵌入，从而建模地理与语义的交互。在 5,743 条查询的本地搜索测试集上，H2CE 达到 67.48% NDCG@5，比 XGBoost LTR 绝对提升 22.82%，比零样本 LLM 重排序器提升 35.89%。
正文节选
H2CE: Modeling Geo-Semantic Interactions for POI Reranking with Heterogeneous Two-Stage Cross-Encoders Abstract. Point-of-Interest (POI) reranking in local search must model query-conditioned tradeoffs among lexical semantics, geospatial proximity, and numerical quality signals such as rating and review count, while remaining practical under real-time serving constraints. A close POI may only partially satisfy the query intent, while a farther one may offer stronger semantic and quality evidence