Bert Embedding and Scoring for Scientific Automatic Essay Grading
The educational landscape is experiencing a surging demand for Automated Essay Grading (AEG), prompting the need for innovative solutions. This paper introduces a cutting-edge methodology that harnesses the power of Bidirectional Encoder Representation from Transformers (BERT) to embed and score ess...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Anhalt University of Applied Sciences
2024-03-01
|
| Series: | Proceedings of the International Conference on Applied Innovations in IT |
| Subjects: | |
| Online Access: | https://icaiit.org/paper.php?paper=12th_ICAIIT_1/2_7 |
| _version_ | 1797198179931783168 |
|---|---|
| author | Abeer Abdulkarem Anastasia Krivtsun |
| author_facet | Abeer Abdulkarem Anastasia Krivtsun |
| author_sort | Abeer Abdulkarem |
| collection | DOAJ |
| description | The educational landscape is experiencing a surging demand for Automated Essay Grading (AEG), prompting the need for innovative solutions. This paper introduces a cutting-edge methodology that harnesses the power of Bidirectional Encoder Representation from Transformers (BERT) to embed and score essays in the scientific AEG domain. Tackling challenges such as Out-of-Vocabulary (OOV), BERT's contextual embedding proves instrumental. The study meticulously evaluates a hybrid architecture on a prototype incorporating non-English essay answers, establishing a benchmark against state-of-the-art studies. Beyond the expeditious grading of essays, particularly in scientific realms, this paper makes a substantial contribution to the ever-evolving field of educational technology. The AEG task revolves around the automation of essay response grading, where input data encompasses essay answers, and output data comprises assigned scores. The adopted mathematical model seamlessly integrates BERT for contextual embedding and subsequent scoring. The evaluation uncovers compelling results, underscoring the effectiveness of the proposed BERT-based model. The model's architecture, characterized by bidirectional layers and a dense output, encompasses a notable 2,243,401 parameters. Significantly, the Kappa Score achieved by the model impressively stands at 0.9725, highlighting its superiority over existing methodologies. |
| first_indexed | 2024-04-24T06:55:45Z |
| format | Article |
| id | doaj.art-b2889033be3140e28bbdd482488cd790 |
| institution | Directory Open Access Journal |
| issn | 2199-8876 |
| language | English |
| last_indexed | 2024-04-24T06:55:45Z |
| publishDate | 2024-03-01 |
| publisher | Anhalt University of Applied Sciences |
| record_format | Article |
| series | Proceedings of the International Conference on Applied Innovations in IT |
| spelling | doaj.art-b2889033be3140e28bbdd482488cd7902024-04-22T11:41:39ZengAnhalt University of Applied SciencesProceedings of the International Conference on Applied Innovations in IT2199-88762024-03-01121115121http://dx.doi.org/10.25673/115649Bert Embedding and Scoring for Scientific Automatic Essay GradingAbeer Abdulkarem0https://orcid.org/0009-0003-1892-9408Anastasia Krivtsun1https://orcid.org/0000-0003-0332-4695Department of Information Technologies and Management, Platov South-Russian State Polytechnic University (NPI), Prosveshсhenie Str. 132, 346428 Novocherkassk, RussiaDepartment of Information Technologies and Management, Platov South-Russian State Polytechnic University (NPI), Prosveshсhenie Str. 132, 346428 Novocherkassk, RussiaThe educational landscape is experiencing a surging demand for Automated Essay Grading (AEG), prompting the need for innovative solutions. This paper introduces a cutting-edge methodology that harnesses the power of Bidirectional Encoder Representation from Transformers (BERT) to embed and score essays in the scientific AEG domain. Tackling challenges such as Out-of-Vocabulary (OOV), BERT's contextual embedding proves instrumental. The study meticulously evaluates a hybrid architecture on a prototype incorporating non-English essay answers, establishing a benchmark against state-of-the-art studies. Beyond the expeditious grading of essays, particularly in scientific realms, this paper makes a substantial contribution to the ever-evolving field of educational technology. The AEG task revolves around the automation of essay response grading, where input data encompasses essay answers, and output data comprises assigned scores. The adopted mathematical model seamlessly integrates BERT for contextual embedding and subsequent scoring. The evaluation uncovers compelling results, underscoring the effectiveness of the proposed BERT-based model. The model's architecture, characterized by bidirectional layers and a dense output, encompasses a notable 2,243,401 parameters. Significantly, the Kappa Score achieved by the model impressively stands at 0.9725, highlighting its superiority over existing methodologies.https://icaiit.org/paper.php?paper=12th_ICAIIT_1/2_7automatic essay gradingword embedding techniquesbert techniquesneural network |
| spellingShingle | Abeer Abdulkarem Anastasia Krivtsun Bert Embedding and Scoring for Scientific Automatic Essay Grading Proceedings of the International Conference on Applied Innovations in IT automatic essay grading word embedding techniques bert techniques neural network |
| title | Bert Embedding and Scoring for Scientific Automatic Essay Grading |
| title_full | Bert Embedding and Scoring for Scientific Automatic Essay Grading |
| title_fullStr | Bert Embedding and Scoring for Scientific Automatic Essay Grading |
| title_full_unstemmed | Bert Embedding and Scoring for Scientific Automatic Essay Grading |
| title_short | Bert Embedding and Scoring for Scientific Automatic Essay Grading |
| title_sort | bert embedding and scoring for scientific automatic essay grading |
| topic | automatic essay grading word embedding techniques bert techniques neural network |
| url | https://icaiit.org/paper.php?paper=12th_ICAIIT_1/2_7 |
| work_keys_str_mv | AT abeerabdulkarem bertembeddingandscoringforscientificautomaticessaygrading AT anastasiakrivtsun bertembeddingandscoringforscientificautomaticessaygrading |