GeoReasoner: Reasoning On Geospatially Grounded Context For Natural Language Understanding
This addresses the challenge of improving geospatial reasoning for AI systems in applications like mapping or location-based services, but it is incremental as it builds on existing LLM and embedding methods.
The paper tackled the problem of geospatial reasoning in natural language understanding by proposing GeoReasoner, which integrates linguistic and geospatial information, achieving state-of-the-art results in tasks like toponym recognition, linking, and typing.
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.