GeoGLUE: A GeoGraphic Language Understanding Evaluation Benchmark

TL;DR

GeoGLUE is a comprehensive benchmark designed to evaluate geographic natural language understanding across six tasks, addressing a gap in standardized evaluation for geographic NLP models.

Contribution

It introduces the first unified benchmark for geographic NLP, with diverse tasks and data sources, facilitating consistent evaluation and comparison of models.

Findings

Baseline experiments demonstrate the benchmark's effectiveness.

The dataset covers six diverse geographic NLP tasks.

GeoGLUE highlights the need for specialized geographic NLP models.

Abstract

With a fast developing pace of geographic applications, automatable and intelligent models are essential to be designed to handle the large volume of information. However, few researchers focus on geographic natural language processing, and there has never been a benchmark to build a unified standard. In this work, we propose a GeoGraphic Language Understanding Evaluation benchmark, named GeoGLUE. We collect data from open-released geographic resources and introduce six natural language understanding tasks, including geographic textual similarity on recall, geographic textual similarity on rerank, geographic elements tagging, geographic composition analysis, geographic where what cut, and geographic entity alignment. We also pro vide evaluation experiments and analysis of general baselines, indicating the effectiveness and significance of the GeoGLUE benchmark.