GeoReasoner: Reasoning On Geospatially Grounded Context For Natural Language Understanding

TL;DR

GeoReasoner is a novel language model designed to improve geospatial reasoning in natural language understanding by integrating geographic data and linguistic context, outperforming existing methods in key geospatial NLP tasks.

Contribution

It introduces a new approach that combines large language models with geospatial data encoding to enhance reasoning on geographic entities in natural language.

Findings

Superior performance in toponym recognition

Improved toponym linking accuracy

Enhanced geo-entity typing results

Abstract

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.