A Novel Address-Matching Framework Based on Region Proposal

Bibliographic Data

ID22033366
AuthorsYizhuo Quan (Chinese Academy of Sciences), Yuanfei Chang (0009-0008-7998-0801, Chinese Academy of Sciences), Linlin Liang (0009-0003-4889-8817, Chinese Academy of Sciences), Yanyou Qiao (Chinese Academy of Sciences), Chengbo Wang (0000-0003-0535-1769, Chinese Academy of Sciences, corresponding author)
Year2024
Volume13
Issue4
Pages138
Publication date2024-04-21
Peer ReviewedYes
Open AccessYes
TypeARTICLE
VenueISPRS International Journal of Geo-Information (JOURNAL)
Journal identifiersISSN: 2220-9964 • E-ISSN: 2220-9964
PublisherMDPI AG (PUBLISHER • IT)
DOI10.3390/ijgi13040138
OpenAlexW4395010189
LanguageEN
Citations received2
References cited21

Geocoding is a fundamental component of geographic information science that plays a crucial role in various geographical studies and applications involving text data. Current mainstream geocoding methods fall into two categories: geodesic-grid prediction and address matching. However, the geodesic-grid-prediction method’s localization accuracy is hindered by the density of grid partitioning, struggling to strike a balance between prediction accuracy and grid density. Address-matching methods mainly focus on the semantics of query text. However, they tend to ignore keyword information that can be used to distinguish candidates and introduce potential interference, which reduces matching accuracy. Inspired by the human map-usage process, we propose a two-stage address-matching approach that integrates geodesic-grid prediction and text-matching models. Initially, a multi-level text-classification model is used to generate a retrieval region proposal for an input query text. Subsequently, we search for the most relevant point of interest (POI) within the region-proposal area using a semantics-based text-retrieval model. We evaluated the proposed method using POI data from the Beijing Chaoyang District. The experimental results indicate that the proposed method provides high address-matching accuracy, increasing Recall@1 by 0.55 to 1.56 percentage points and MRR@5 by 0.54 to 1.68 percentage points

Beijing · Cartography · Data mining · Geocoding · Geography · Grid · Information retrieval · Precision and recall · Computer Science · Data Management and Algorithms · Geographic Information Systems Studies · Human Mobility and Location-Based Analysis · Mathematics · Artificial Intelligence

Tools

Open DOIOpen Access