An automatic grading model for semantic complexity of english texts using bidirectional attention-based autoencoder
With the advent of the information age, the massive increase of English text data puts forward higher requirements for text analysis and processing. The aim of this study is to accurately evaluate the semantic complexity of English text through an autoencoder structure based on bidirectional attenti...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Published: |
World Scientific
2024
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/114245/ |
| _version_ | 1848866437229182976 |
|---|---|
| author | Chen, Ruo Han Ng, Boon Sim Paramasivam, Shamala Ren, Li |
| author_facet | Chen, Ruo Han Ng, Boon Sim Paramasivam, Shamala Ren, Li |
| author_sort | Chen, Ruo Han |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | With the advent of the information age, the massive increase of English text data puts forward higher requirements for text analysis and processing. The aim of this study is to accurately evaluate the semantic complexity of English text through an autoencoder structure based on bidirectional attention. This paper first analyzes the importance of automatic classification of semantic complexity in English text, and then builds an autoencoder structure based on bidirectional attention, which captures bidirectional information in text, and then uses the autoencoder structure for feature extraction and dimension reduction, which further strengthens the model’s ability to capture semantic complexity. Finally, A Bidirectional Attention Self-Encoding English Text Semantic Complexity Automatic Grading Model (BSETG) is established. This study conducted experimental verification based on semantic Evaluation (SemEval) dataset, convolutional neural network (CNN)/Daily Mail dataset and Penn Treebank dataset, and conducted a comparative analysis with existing semantic complexity evaluation methods. The experimental results show that the overall accuracy of BSETG algorithm is maintained between 70% and 90%, the response speed of BSETG algorithm is relatively fast, and the success rate of BSETG algorithm is relatively stable to a large extent. |
| first_indexed | 2025-11-15T14:20:35Z |
| format | Article |
| id | upm-114245 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-15T14:20:35Z |
| publishDate | 2024 |
| publisher | World Scientific |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-1142452025-01-10T01:55:04Z http://psasir.upm.edu.my/id/eprint/114245/ An automatic grading model for semantic complexity of english texts using bidirectional attention-based autoencoder Chen, Ruo Han Ng, Boon Sim Paramasivam, Shamala Ren, Li With the advent of the information age, the massive increase of English text data puts forward higher requirements for text analysis and processing. The aim of this study is to accurately evaluate the semantic complexity of English text through an autoencoder structure based on bidirectional attention. This paper first analyzes the importance of automatic classification of semantic complexity in English text, and then builds an autoencoder structure based on bidirectional attention, which captures bidirectional information in text, and then uses the autoencoder structure for feature extraction and dimension reduction, which further strengthens the model’s ability to capture semantic complexity. Finally, A Bidirectional Attention Self-Encoding English Text Semantic Complexity Automatic Grading Model (BSETG) is established. This study conducted experimental verification based on semantic Evaluation (SemEval) dataset, convolutional neural network (CNN)/Daily Mail dataset and Penn Treebank dataset, and conducted a comparative analysis with existing semantic complexity evaluation methods. The experimental results show that the overall accuracy of BSETG algorithm is maintained between 70% and 90%, the response speed of BSETG algorithm is relatively fast, and the success rate of BSETG algorithm is relatively stable to a large extent. World Scientific 2024 Article PeerReviewed Chen, Ruo Han and Ng, Boon Sim and Paramasivam, Shamala and Ren, Li (2024) An automatic grading model for semantic complexity of english texts using bidirectional attention-based autoencoder. Journal of Circuits, Systems and Computers, 33 (18). ISSN 0218-1266; eISSN: 1793-6454 https://www.worldscientific.com/doi/epdf/10.1142/S0218126625500069 10.1142/S0218126625500069 |
| spellingShingle | Chen, Ruo Han Ng, Boon Sim Paramasivam, Shamala Ren, Li An automatic grading model for semantic complexity of english texts using bidirectional attention-based autoencoder |
| title | An automatic grading model for semantic complexity of english texts using bidirectional attention-based autoencoder |
| title_full | An automatic grading model for semantic complexity of english texts using bidirectional attention-based autoencoder |
| title_fullStr | An automatic grading model for semantic complexity of english texts using bidirectional attention-based autoencoder |
| title_full_unstemmed | An automatic grading model for semantic complexity of english texts using bidirectional attention-based autoencoder |
| title_short | An automatic grading model for semantic complexity of english texts using bidirectional attention-based autoencoder |
| title_sort | automatic grading model for semantic complexity of english texts using bidirectional attention-based autoencoder |
| url | http://psasir.upm.edu.my/id/eprint/114245/ http://psasir.upm.edu.my/id/eprint/114245/ http://psasir.upm.edu.my/id/eprint/114245/ |