Interpretable Geometry Problem Solving Using Improved RetinaNet and Graph Convolutional Network
This paper proposes an interpretable geometry solution based on the formal language set of text and diagram. Geometry problems are solved using machines; however, machines encounter challenges in natural language processing and computer vision. Significant progress has improved existing methods in t...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/22/4578 |
| _version_ | 1797459557889343488 |
|---|---|
| author | Pengpeng Jian Fucheng Guo Cong Pan Yanli Wang Yangrui Yang Yang Li |
| author_facet | Pengpeng Jian Fucheng Guo Cong Pan Yanli Wang Yangrui Yang Yang Li |
| author_sort | Pengpeng Jian |
| collection | DOAJ |
| description | This paper proposes an interpretable geometry solution based on the formal language set of text and diagram. Geometry problems are solved using machines; however, machines encounter challenges in natural language processing and computer vision. Significant progress has improved existing methods in the extraction of geometric formal languages. However, the neglect of the graph structure information in the formal language and the lack of further refinement of the extracted language set can lead to poor theorem prediction and poor accuracy in problem solving. In this paper, a formal language graph is constructed using the extracted formal language set and applied to theorem prediction using a graph convolutional network. To better extract the relationship set of diagram elements, an improved diagram parser is proposed. The test results indicate that the improved method has good results when solving interpretable geometry problems. |
| first_indexed | 2024-03-09T16:53:04Z |
| format | Article |
| id | doaj.art-be99c02373de497dbf5cbe991e876669 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T16:53:04Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-be99c02373de497dbf5cbe991e8766692023-11-24T14:39:03ZengMDPI AGElectronics2079-92922023-11-011222457810.3390/electronics12224578Interpretable Geometry Problem Solving Using Improved RetinaNet and Graph Convolutional NetworkPengpeng Jian0Fucheng Guo1Cong Pan2Yanli Wang3Yangrui Yang4Yang Li5School of Information Engineering, North China University of Water Resources and Electric Power, Zhengzhou 450046, ChinaFaculty of Artificial Intelligence in Education, Central China Normal University, Wuhan 430079, ChinaSchool of Information Engineering, North China University of Water Resources and Electric Power, Zhengzhou 450046, ChinaCollege of Marxism, Henan University of Economics and Law, Zhengzhou 450046, ChinaSchool of Information Engineering, North China University of Water Resources and Electric Power, Zhengzhou 450046, ChinaSchool of Information Engineering, North China University of Water Resources and Electric Power, Zhengzhou 450046, ChinaThis paper proposes an interpretable geometry solution based on the formal language set of text and diagram. Geometry problems are solved using machines; however, machines encounter challenges in natural language processing and computer vision. Significant progress has improved existing methods in the extraction of geometric formal languages. However, the neglect of the graph structure information in the formal language and the lack of further refinement of the extracted language set can lead to poor theorem prediction and poor accuracy in problem solving. In this paper, a formal language graph is constructed using the extracted formal language set and applied to theorem prediction using a graph convolutional network. To better extract the relationship set of diagram elements, an improved diagram parser is proposed. The test results indicate that the improved method has good results when solving interpretable geometry problems.https://www.mdpi.com/2079-9292/12/22/4578interpretable solvingGCNRetinaNetformal languagediagram parsing |
| spellingShingle | Pengpeng Jian Fucheng Guo Cong Pan Yanli Wang Yangrui Yang Yang Li Interpretable Geometry Problem Solving Using Improved RetinaNet and Graph Convolutional Network Electronics interpretable solving GCN RetinaNet formal language diagram parsing |
| title | Interpretable Geometry Problem Solving Using Improved RetinaNet and Graph Convolutional Network |
| title_full | Interpretable Geometry Problem Solving Using Improved RetinaNet and Graph Convolutional Network |
| title_fullStr | Interpretable Geometry Problem Solving Using Improved RetinaNet and Graph Convolutional Network |
| title_full_unstemmed | Interpretable Geometry Problem Solving Using Improved RetinaNet and Graph Convolutional Network |
| title_short | Interpretable Geometry Problem Solving Using Improved RetinaNet and Graph Convolutional Network |
| title_sort | interpretable geometry problem solving using improved retinanet and graph convolutional network |
| topic | interpretable solving GCN RetinaNet formal language diagram parsing |
| url | https://www.mdpi.com/2079-9292/12/22/4578 |
| work_keys_str_mv | AT pengpengjian interpretablegeometryproblemsolvingusingimprovedretinanetandgraphconvolutionalnetwork AT fuchengguo interpretablegeometryproblemsolvingusingimprovedretinanetandgraphconvolutionalnetwork AT congpan interpretablegeometryproblemsolvingusingimprovedretinanetandgraphconvolutionalnetwork AT yanliwang interpretablegeometryproblemsolvingusingimprovedretinanetandgraphconvolutionalnetwork AT yangruiyang interpretablegeometryproblemsolvingusingimprovedretinanetandgraphconvolutionalnetwork AT yangli interpretablegeometryproblemsolvingusingimprovedretinanetandgraphconvolutionalnetwork |