An interactive address matching method based on a graph attention mechanism
Problem:: Modernizing and standardizing place names and addresses is a key challenge in the development of smart cities. Purpose:: This paper proposes a solution to address matching challenges, such as incomplete descriptions, reversed word order, and the diverse descriptions often found in Chinese...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2025-12-01
|
| Series: | International Journal of Cognitive Computing in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S266630742400055X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841560516443504640 |
|---|---|
| author | Ming Li Jialin Su Zhiyu Song Juping Qiu Yongping Lin |
| author_facet | Ming Li Jialin Su Zhiyu Song Juping Qiu Yongping Lin |
| author_sort | Ming Li |
| collection | DOAJ |
| description | Problem:: Modernizing and standardizing place names and addresses is a key challenge in the development of smart cities. Purpose:: This paper proposes a solution to address matching challenges, such as incomplete descriptions, reversed word order, and the diverse descriptions often found in Chinese addresses. Method:: Leveraging the hierarchical structure of Chinese addresses, this study introduces the interactive address matching graph attention model (IAMGAM). In the IAMGAM, an attention-based feature interaction method (AFIM) is employed. To reflect the hierarchical nature of address elements, a directed graph is used to model the address data, and the model is trained and tested using a graph attention mechanism. Results:: Experiments demonstrate that the IAMGAM achieves an accuracy and F1-score of 99.61%. Compared with the existing address matching methods, the IAMGAM improves the accuracy by 0.66% to 2.57%, and the F1-score by 0.68% to 2.55%, outperforming baseline models. Additionally, ablation experiments confirm the effectiveness of each component within the model. Furthermore, when fine-tuned using ChatGLM2-6B, the results show that the IAMGAM still outperforms ChatGLM2-6B. Conclusion:: IAMGAM demonstrates excellent performance in Chinese address matching tasks, and the Large Language Model (LLM)-based methods, such as ChatGLM2-6B, show great potential for future development in this area. |
| format | Article |
| id | doaj-art-d408d64ebd4f487180c4cdb24168283e |
| institution | Kabale University |
| issn | 2666-3074 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | International Journal of Cognitive Computing in Engineering |
| spelling | doaj-art-d408d64ebd4f487180c4cdb24168283e2025-01-04T04:57:04ZengKeAi Communications Co., Ltd.International Journal of Cognitive Computing in Engineering2666-30742025-12-016191200An interactive address matching method based on a graph attention mechanismMing Li0Jialin Su1Zhiyu Song2Juping Qiu3Yongping Lin4School of Optoelectronic and Communication Engineering, Xiamen University of Technology, No. 600 Ligong Road, Jimei District, Xiamen, 361024, Fujian, ChinaSchool of Optoelectronic and Communication Engineering, Xiamen University of Technology, No. 600 Ligong Road, Jimei District, Xiamen, 361024, Fujian, ChinaSchool of Optoelectronic and Communication Engineering, Xiamen University of Technology, No. 600 Ligong Road, Jimei District, Xiamen, 361024, Fujian, ChinaSchool of Optoelectronic and Communication Engineering, Xiamen University of Technology, No. 600 Ligong Road, Jimei District, Xiamen, 361024, Fujian, ChinaCorresponding author.; School of Optoelectronic and Communication Engineering, Xiamen University of Technology, No. 600 Ligong Road, Jimei District, Xiamen, 361024, Fujian, ChinaProblem:: Modernizing and standardizing place names and addresses is a key challenge in the development of smart cities. Purpose:: This paper proposes a solution to address matching challenges, such as incomplete descriptions, reversed word order, and the diverse descriptions often found in Chinese addresses. Method:: Leveraging the hierarchical structure of Chinese addresses, this study introduces the interactive address matching graph attention model (IAMGAM). In the IAMGAM, an attention-based feature interaction method (AFIM) is employed. To reflect the hierarchical nature of address elements, a directed graph is used to model the address data, and the model is trained and tested using a graph attention mechanism. Results:: Experiments demonstrate that the IAMGAM achieves an accuracy and F1-score of 99.61%. Compared with the existing address matching methods, the IAMGAM improves the accuracy by 0.66% to 2.57%, and the F1-score by 0.68% to 2.55%, outperforming baseline models. Additionally, ablation experiments confirm the effectiveness of each component within the model. Furthermore, when fine-tuned using ChatGLM2-6B, the results show that the IAMGAM still outperforms ChatGLM2-6B. Conclusion:: IAMGAM demonstrates excellent performance in Chinese address matching tasks, and the Large Language Model (LLM)-based methods, such as ChatGLM2-6B, show great potential for future development in this area.http://www.sciencedirect.com/science/article/pii/S266630742400055XAddress matchingInteractive address matching graph attention modelAttention-based feature interaction methodDirected graph |
| spellingShingle | Ming Li Jialin Su Zhiyu Song Juping Qiu Yongping Lin An interactive address matching method based on a graph attention mechanism International Journal of Cognitive Computing in Engineering Address matching Interactive address matching graph attention model Attention-based feature interaction method Directed graph |
| title | An interactive address matching method based on a graph attention mechanism |
| title_full | An interactive address matching method based on a graph attention mechanism |
| title_fullStr | An interactive address matching method based on a graph attention mechanism |
| title_full_unstemmed | An interactive address matching method based on a graph attention mechanism |
| title_short | An interactive address matching method based on a graph attention mechanism |
| title_sort | interactive address matching method based on a graph attention mechanism |
| topic | Address matching Interactive address matching graph attention model Attention-based feature interaction method Directed graph |
| url | http://www.sciencedirect.com/science/article/pii/S266630742400055X |
| work_keys_str_mv | AT mingli aninteractiveaddressmatchingmethodbasedonagraphattentionmechanism AT jialinsu aninteractiveaddressmatchingmethodbasedonagraphattentionmechanism AT zhiyusong aninteractiveaddressmatchingmethodbasedonagraphattentionmechanism AT jupingqiu aninteractiveaddressmatchingmethodbasedonagraphattentionmechanism AT yongpinglin aninteractiveaddressmatchingmethodbasedonagraphattentionmechanism AT mingli interactiveaddressmatchingmethodbasedonagraphattentionmechanism AT jialinsu interactiveaddressmatchingmethodbasedonagraphattentionmechanism AT zhiyusong interactiveaddressmatchingmethodbasedonagraphattentionmechanism AT jupingqiu interactiveaddressmatchingmethodbasedonagraphattentionmechanism AT yongpinglin interactiveaddressmatchingmethodbasedonagraphattentionmechanism |