Automated essay scoring with SBERT embeddings and LSTM-Attention networks
Automated essay scoring (AES) is essential in the field of educational technology, providing rapid and accurate evaluations of student writing. This study presents an innovative AES method that integrates Sentence-BERT (SBERT) with Long Short-Term Memory (LSTM) networks and attention mechanisms to i...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2025-02-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-2634.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Automated essay scoring (AES) is essential in the field of educational technology, providing rapid and accurate evaluations of student writing. This study presents an innovative AES method that integrates Sentence-BERT (SBERT) with Long Short-Term Memory (LSTM) networks and attention mechanisms to improve the scoring process. SBERT generates embedding vectors for each essay, which are subsequently analyzed using a bidirectional LSTM (BiLSTM) to learn the features of these embedding vectors. An attention layer is introduced to enable the system to prioritize the most significant components of the essay. Evaluated using a benchmark dataset, our approach shows significant improvements in scoring accuracy, highlighting its ability to improve the reliability and efficiency of automated assessment systems. |
|---|---|
| ISSN: | 2376-5992 |