In human reading and communication, individuals tend to engage in geospatial reasoning, which involves recognizing geographic entities and making informed inferences about their interrelationships. To mimic such cognitive process, current methods either utilize conventional natural language understanding toolkits, or directly apply models pretrained on geo-related natural language corpora. However, these methods face two significant challenges: i) they do not generalize well to unseen geospatial scenarios, and ii) they overlook the importance of integrating geospatial context from geographical databases with linguistic information from the Internet. To handle these challenges, we propose GeoReasoner, a language model capable of reasoning on geospatially grounded natural language. Specifically, it first leverages Large Language Models (LLMs) to generate a comprehensive location description based on linguistic and geospatial information. It also encodes direction and distance information into spatial embedding via treating them as pseudo-sentences. Consequently, the model is trained on both anchor-level and neighbor-level inputs to learn geo-entity representation. Extensive experimental results demonstrate GeoReasoner's superiority in three tasks: toponym recognition, toponym linking, and geo-entity typing, compared to the state-of-the-art baselines.

翻译：在人类阅读与交流过程中，个体倾向于进行地理空间推理，即识别地理实体并对其相互关系做出有依据的推断。为模拟此类认知过程，现有方法或采用传统自然语言理解工具包，或直接应用基于地理相关自然语言语料预训练的模型。然而，这些方法面临两大挑战：其一，对未见地理空间场景的泛化能力不足；其二，忽视了将地理数据库中的空间上下文与互联网语言信息相融合的重要性。为应对这些挑战，本文提出GeoReasoner——一种能够对地理空间锚定的自然语言进行推理的语言模型。具体而言，该模型首先利用大语言模型（LLMs）基于语言与地理空间信息生成全面的位置描述；同时通过将方向与距离信息视为伪句子编码为空间嵌入。在此基础上，模型通过锚点层级与邻近层级的联合训练学习地理实体表示。大量实验结果表明，在地名识别、地名链接与地理实体分类三项任务中，GeoReasoner相较现有最优基线模型均展现出显著优势。