发表机构
RMIT University（皇家墨尔本理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究评估文本编码器能否作为空间语义索引，通过对比暴力最近邻与层次束搜索两种检索策略，发现无约束密集检索易出错，层次约束改善粗粒度定位但细粒度仍有限。
AI 中文摘要
地理信息检索（GeoIR）任务要求系统解释模糊地名以供下游应用。传统上，地名消解依赖地名辞典提供地点实体和空间关系的显式索引。近年来，无地名辞典方法试图减少对手工搜索的依赖：密集检索利用文本编码器捕获丰富上下文，超越了词汇搜索的局限。然而，文本编码器隐含地假设学习到的表示能够充当可靠的空间语义索引。在本文中，我们通过空间语义索引设置评估这一假设：给定一个上下文化的模糊地名提及，我们检索由地名辞典知识图谱中派生的文本所表示的对应地名辞典实体。我们在两种检索策略下对五个冻结的文本编码器进行基准测试：对实体表示进行暴力最近邻检索，以及一种神经符号层次束搜索，该搜索约束检索（即，将搜索与地名辞典层次结构链接）。实验结果显示一种明显的粗粒度与细粒度之间的权衡。无约束的密集检索经常导致灾难性的空间错误。相反，层次约束改善了粗粒度的地理定位，但对细粒度定位指标仍带来有限的益处：原始文本编码器无法捕获地名辞典中编码的细尺度空间保真度。我们的代码在此 https URL 公开可用。
英文摘要
Geographic information retrieval (GeoIR) tasks require systems to interpret ambiguous toponyms for downstream applications. Traditionally, toponym resolution relies on gazetteers to provide an explicit index of place entities and spatial relationships. Recently, gazetteer-free approaches seek to reduce dependence on handcrafted searches: dense retrieval utilizes text encoders to capture rich context, moving beyond the limitations of lexical search. However, text encoders implicitly assume that learned representations can function as reliable spatial-semantic indexes. In this paper, we evaluate this assumption through a spatial-semantic indexing setup: given a contextualized toponym mention, we retrieve the corresponding gazetteer entity represented by text derived from a gazetteer knowledge graph. We benchmark five frozen text encoders under two retrieval strategies: brute-force nearest-neighbor retrieval over entity representations, and a neuro-symbolic hierarchical beam search that constrains retrieval (i.e. chaining the search with gazetteer hierarchy). Experimental results reveal a distinct coarse-versus-fine trade-off. Unconstrained dense retrieval frequently incurs catastrophic spatial errors. Conversely, hierarchical constraints improve coarse geographic grounding, but still yield limited benefit for fine-grained localization metrics: vanilla text encoders fail to capture the fine-scale spatial fidelity encoded in gazetteers. Our code is publicly available at: https://doi.org/10.25439/rmt.31094269
CommentsAccepted to ACM SIGSPATIAL '26
