A geometric neural solving method based on a diagram text information fusion analysis
Abstract The long-standing problem of geometric problem solving in artificial intelligence education has attracted widespread attention. It is necessary to combine geometry diagrams and text descriptions to form a logical representation. This involves combining the knowledge of mathematical theorems...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-12-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-83287-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559574632464384 |
|---|---|
| author | Bin Ma Pengpeng Jian Cong Pan Yanli Wang Wei Ma |
| author_facet | Bin Ma Pengpeng Jian Cong Pan Yanli Wang Wei Ma |
| author_sort | Bin Ma |
| collection | DOAJ |
| description | Abstract The long-standing problem of geometric problem solving in artificial intelligence education has attracted widespread attention. It is necessary to combine geometry diagrams and text descriptions to form a logical representation. This involves combining the knowledge of mathematical theorems, generating a solution sequence, and executing to obtain the answer. However, deficiencies in the feature extraction of geometry diagrams and the fusion of diagram text information can lead to poor performance in solving geometry problems. To effectively extract geometry diagram features, this study proposes an improved diagram parser DenseNet, and enhances the semantic representation of cross-modal information by adding auxiliary tasks. A structural and semantic pre-training strategy was used to parse the text description to avoid different problem solving schemes due to subtle differences in the interpretation of text content. Information fusion was realized by connecting the two modal labels, and then the information was sent to the encoder for fusion. The geometric knowledge was generated under the guidance of multi-modal information, and these programs were executed to obtain the results. Additionally, the performance of the proposed geometric neural solution method on the PGPS9K dataset is improved by 1.3% on average. Compared with the Geometry3K dataset, the effectiveness was proven. |
| format | Article |
| id | doaj-art-b493ba23c34a498185b15ff2be56bef8 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-b493ba23c34a498185b15ff2be56bef82025-01-05T12:23:41ZengNature PortfolioScientific Reports2045-23222024-12-0114111510.1038/s41598-024-83287-6A geometric neural solving method based on a diagram text information fusion analysisBin Ma0Pengpeng Jian1Cong Pan2Yanli Wang3Wei Ma4North China University of Water Resources and Electric PowerNorth China University of Water Resources and Electric PowerNorth China University of Water Resources and Electric PowerHenan University of Economics and LawNorth China University of Water Resources and Electric PowerAbstract The long-standing problem of geometric problem solving in artificial intelligence education has attracted widespread attention. It is necessary to combine geometry diagrams and text descriptions to form a logical representation. This involves combining the knowledge of mathematical theorems, generating a solution sequence, and executing to obtain the answer. However, deficiencies in the feature extraction of geometry diagrams and the fusion of diagram text information can lead to poor performance in solving geometry problems. To effectively extract geometry diagram features, this study proposes an improved diagram parser DenseNet, and enhances the semantic representation of cross-modal information by adding auxiliary tasks. A structural and semantic pre-training strategy was used to parse the text description to avoid different problem solving schemes due to subtle differences in the interpretation of text content. Information fusion was realized by connecting the two modal labels, and then the information was sent to the encoder for fusion. The geometric knowledge was generated under the guidance of multi-modal information, and these programs were executed to obtain the results. Additionally, the performance of the proposed geometric neural solution method on the PGPS9K dataset is improved by 1.3% on average. Compared with the Geometry3K dataset, the effectiveness was proven.https://doi.org/10.1038/s41598-024-83287-6Geometry problem solvingMulti-modal informationFeature extractionDiagram parser |
| spellingShingle | Bin Ma Pengpeng Jian Cong Pan Yanli Wang Wei Ma A geometric neural solving method based on a diagram text information fusion analysis Scientific Reports Geometry problem solving Multi-modal information Feature extraction Diagram parser |
| title | A geometric neural solving method based on a diagram text information fusion analysis |
| title_full | A geometric neural solving method based on a diagram text information fusion analysis |
| title_fullStr | A geometric neural solving method based on a diagram text information fusion analysis |
| title_full_unstemmed | A geometric neural solving method based on a diagram text information fusion analysis |
| title_short | A geometric neural solving method based on a diagram text information fusion analysis |
| title_sort | geometric neural solving method based on a diagram text information fusion analysis |
| topic | Geometry problem solving Multi-modal information Feature extraction Diagram parser |
| url | https://doi.org/10.1038/s41598-024-83287-6 |
| work_keys_str_mv | AT binma ageometricneuralsolvingmethodbasedonadiagramtextinformationfusionanalysis AT pengpengjian ageometricneuralsolvingmethodbasedonadiagramtextinformationfusionanalysis AT congpan ageometricneuralsolvingmethodbasedonadiagramtextinformationfusionanalysis AT yanliwang ageometricneuralsolvingmethodbasedonadiagramtextinformationfusionanalysis AT weima ageometricneuralsolvingmethodbasedonadiagramtextinformationfusionanalysis AT binma geometricneuralsolvingmethodbasedonadiagramtextinformationfusionanalysis AT pengpengjian geometricneuralsolvingmethodbasedonadiagramtextinformationfusionanalysis AT congpan geometricneuralsolvingmethodbasedonadiagramtextinformationfusionanalysis AT yanliwang geometricneuralsolvingmethodbasedonadiagramtextinformationfusionanalysis AT weima geometricneuralsolvingmethodbasedonadiagramtextinformationfusionanalysis |