GeoReasoner：基于地理空间接地上下文的自然语言理解推理
GeoReasoner: Reasoning On Geospatially Grounded Context For Natural Language Understanding
AI总结：
提出GeoReasoner语言模型，通过结合LLM生成的位置描述与方向距离伪句子空间嵌入，在锚点和邻居级别训练学习地理实体表示，在地名识别、链接和实体分类任务上优于现有基线。
摘要：
在人类阅读和交流中，个体倾向于进行地理空间推理，这涉及识别地理实体并对其相互关系做出有根据的推断。为了模拟这种认知过程，当前方法要么利用传统的自然语言理解工具包，要么直接应用在地理相关自然语言语料库上预训练的模型。然而，这些方法面临两个重大挑战：i）它们不能很好地泛化到未见过的地理空间场景，以及ii）它们忽视了将来自地理数据库的地理空间上下文与来自互联网的语言信息整合的重要性。为了应对这些挑战，我们提出了GeoReasoner，这是一种能够在地理空间接地自然语言上进行推理的语言模型。具体而言，它首先利用大型语言模型（LLMs）基于语言和地理空间信息生成全面的位置描述。它还通过将方向和距离信息视为伪句子，将其编码到空间嵌入中。因此，该模型在锚点级别和邻居级别输入上进行训练，以学习地理实体表示。广泛的实验结果表明，与最先进的基线相比，GeoReasoner在三个任务中表现出优越性：地名识别、地名链接和地理实体类型化。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
