Omni Geometry Representation Learning vs Large Language Models for Geospatial Entity Resolution

TL;DR

This paper introduces Omni, a novel geospatial entity resolution model that embeds diverse geometries and leverages language models, achieving significant accuracy improvements and exploring LLMs' potential in geospatial matching.

Contribution

The paper presents Omni, a new model capable of embedding heterogeneous geometries and integrating textual attributes, and evaluates LLMs' effectiveness for geospatial entity resolution.

Findings

Omni achieves up to 12% F1 improvement over existing methods.

Omni effectively embeds complex geometries like polygons and polylines.

LLMs show competitive results in geospatial ER tasks.

Abstract

The development, integration, and maintenance of geospatial databases rely heavily on efficient and accurate matching procedures of Geospatial Entity Resolution (ER). While resolution of points-of-interest (POIs) has been widely addressed, resolution of entities with diverse geometries has been largely overlooked. This is partly due to the lack of a uniform technique for embedding heterogeneous geometries seamlessly into a neural network framework. Existing neural approaches simplify complex geometries to a single point, resulting in significant loss of spatial information. To address this limitation, we propose Omni, a geospatial ER model featuring an omni-geometry encoder. This encoder is capable of embedding point, line, polyline, polygon, and multi-polygon geometries, enabling the model to capture the complex geospatial intricacies of the places being compared. Furthermore, Omni leverages transformer-based pre-trained language models over individual textual attributes of place records in an Attribute Affinity mechanism. The model is rigorously tested on existing point-only datasets and a new diverse-geometry geospatial ER dataset. Omni produces up to 12% (F1) improvement over existing methods. Furthermore, we test the potential of Large Language Models (LLMs) to conduct geospatial ER, experimenting with prompting strategies and learning scenarios, comparing the results of pre-trained language model-based methods with LLMs. Results indicate that LLMs show competitive results.