A Multi-Semantic Feature Fusion Method for Complex Address Matching of Chinese Addresses

Accurate address matching is crucial for the analysis, integration, and intelligent management of urban geospatial data and is also a key step in achieving geocoding. However, due to the complexity, diversity, and irregularity of address expression, address matching becomes a challenging task. This...

Full description

Saved in:
Bibliographic Details
Main Authors: Pengpeng Li, Qing Zhu, Jiping Liu, Tao Liu, Ping Du, Shuangtong Liu, Yuting Zhang
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:ISPRS International Journal of Geo-Information
Subjects:
Online Access:https://www.mdpi.com/2220-9964/14/6/227
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849432965984026624
author Pengpeng Li
Qing Zhu
Jiping Liu
Tao Liu
Ping Du
Shuangtong Liu
Yuting Zhang
author_facet Pengpeng Li
Qing Zhu
Jiping Liu
Tao Liu
Ping Du
Shuangtong Liu
Yuting Zhang
author_sort Pengpeng Li
collection DOAJ
description Accurate address matching is crucial for the analysis, integration, and intelligent management of urban geospatial data and is also a key step in achieving geocoding. However, due to the complexity, diversity, and irregularity of address expression, address matching becomes a challenging task. This paper proposes a multi-semantic feature fusion method for complex address matching of Chinese addresses that formulates address matching as a classification task that directly predicts whether two addresses refer to the same location, without relying on predefined similarity thresholds. First, the address is resolved into address elements, and the Word2vec model is trained to generate word vector representations using these address elements. Then, multi-semantic features of the addresses are extracted using a Text Recurrent Convolutional Neural Network (Text-RCNN) and a Graph Attention Network (GAT). Finally, the Enhanced Sequential Inference Model (ESIM) is used to perform both local inference and inference composition on the multi-semantic features of the addresses to achieve accurate matching of addresses. Experiments were conducted using Points of Interest (POI) address data from Baidu Maps, Tencent Maps, and Amap within the Chengdu area. The results demonstrate that the proposed method outperforms existing address matching methods, with precision, recall, and F1 values all exceeding 95%. In addition, transfer experiments using datasets from five other cities including Beijing, Shanghai, Xi’an, Guangzhou, and Wuhan show that the model maintains strong generalization ability, achieving F1 values above 84% in cities such as Xi’an and Wuhan.
format Article
id doaj-art-7642b9c2e0be467ca7174c6eac2e3b3e
institution Kabale University
issn 2220-9964
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series ISPRS International Journal of Geo-Information
spelling doaj-art-7642b9c2e0be467ca7174c6eac2e3b3e2025-08-20T03:27:14ZengMDPI AGISPRS International Journal of Geo-Information2220-99642025-06-0114622710.3390/ijgi14060227A Multi-Semantic Feature Fusion Method for Complex Address Matching of Chinese AddressesPengpeng Li0Qing Zhu1Jiping Liu2Tao Liu3Ping Du4Shuangtong Liu5Yuting Zhang6Faculty of Geomatics, Lanzhou Jiaotong University, Lanzhou 730070, ChinaFaculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu 610031, ChinaResearch Center of Geospatial Big Data Application, Chinese Academy of Surveying and Mapping, Beijing 100830, ChinaFaculty of Geomatics, Lanzhou Jiaotong University, Lanzhou 730070, ChinaFaculty of Geomatics, Lanzhou Jiaotong University, Lanzhou 730070, ChinaFaculty of Geomatics, Lanzhou Jiaotong University, Lanzhou 730070, ChinaFaculty of Geomatics, Lanzhou Jiaotong University, Lanzhou 730070, ChinaAccurate address matching is crucial for the analysis, integration, and intelligent management of urban geospatial data and is also a key step in achieving geocoding. However, due to the complexity, diversity, and irregularity of address expression, address matching becomes a challenging task. This paper proposes a multi-semantic feature fusion method for complex address matching of Chinese addresses that formulates address matching as a classification task that directly predicts whether two addresses refer to the same location, without relying on predefined similarity thresholds. First, the address is resolved into address elements, and the Word2vec model is trained to generate word vector representations using these address elements. Then, multi-semantic features of the addresses are extracted using a Text Recurrent Convolutional Neural Network (Text-RCNN) and a Graph Attention Network (GAT). Finally, the Enhanced Sequential Inference Model (ESIM) is used to perform both local inference and inference composition on the multi-semantic features of the addresses to achieve accurate matching of addresses. Experiments were conducted using Points of Interest (POI) address data from Baidu Maps, Tencent Maps, and Amap within the Chengdu area. The results demonstrate that the proposed method outperforms existing address matching methods, with precision, recall, and F1 values all exceeding 95%. In addition, transfer experiments using datasets from five other cities including Beijing, Shanghai, Xi’an, Guangzhou, and Wuhan show that the model maintains strong generalization ability, achieving F1 values above 84% in cities such as Xi’an and Wuhan.https://www.mdpi.com/2220-9964/14/6/227address matchingmulti-semantic feature fusionText-RCNNGATESIM
spellingShingle Pengpeng Li
Qing Zhu
Jiping Liu
Tao Liu
Ping Du
Shuangtong Liu
Yuting Zhang
A Multi-Semantic Feature Fusion Method for Complex Address Matching of Chinese Addresses
ISPRS International Journal of Geo-Information
address matching
multi-semantic feature fusion
Text-RCNN
GAT
ESIM
title A Multi-Semantic Feature Fusion Method for Complex Address Matching of Chinese Addresses
title_full A Multi-Semantic Feature Fusion Method for Complex Address Matching of Chinese Addresses
title_fullStr A Multi-Semantic Feature Fusion Method for Complex Address Matching of Chinese Addresses
title_full_unstemmed A Multi-Semantic Feature Fusion Method for Complex Address Matching of Chinese Addresses
title_short A Multi-Semantic Feature Fusion Method for Complex Address Matching of Chinese Addresses
title_sort multi semantic feature fusion method for complex address matching of chinese addresses
topic address matching
multi-semantic feature fusion
Text-RCNN
GAT
ESIM
url https://www.mdpi.com/2220-9964/14/6/227
work_keys_str_mv AT pengpengli amultisemanticfeaturefusionmethodforcomplexaddressmatchingofchineseaddresses
AT qingzhu amultisemanticfeaturefusionmethodforcomplexaddressmatchingofchineseaddresses
AT jipingliu amultisemanticfeaturefusionmethodforcomplexaddressmatchingofchineseaddresses
AT taoliu amultisemanticfeaturefusionmethodforcomplexaddressmatchingofchineseaddresses
AT pingdu amultisemanticfeaturefusionmethodforcomplexaddressmatchingofchineseaddresses
AT shuangtongliu amultisemanticfeaturefusionmethodforcomplexaddressmatchingofchineseaddresses
AT yutingzhang amultisemanticfeaturefusionmethodforcomplexaddressmatchingofchineseaddresses
AT pengpengli multisemanticfeaturefusionmethodforcomplexaddressmatchingofchineseaddresses
AT qingzhu multisemanticfeaturefusionmethodforcomplexaddressmatchingofchineseaddresses
AT jipingliu multisemanticfeaturefusionmethodforcomplexaddressmatchingofchineseaddresses
AT taoliu multisemanticfeaturefusionmethodforcomplexaddressmatchingofchineseaddresses
AT pingdu multisemanticfeaturefusionmethodforcomplexaddressmatchingofchineseaddresses
AT shuangtongliu multisemanticfeaturefusionmethodforcomplexaddressmatchingofchineseaddresses
AT yutingzhang multisemanticfeaturefusionmethodforcomplexaddressmatchingofchineseaddresses