Automated essay scoring with SBERT embeddings and LSTM-Attention networks
PeerJ Computer Science · 11.02.2025 · 11 · e2634
DOI: 10.7717/peerj-cs.2634 ↗Kurz gefasst
Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 11.02.2025. Verfasst von Yuzhe Nie. Beteiligte Einrichtung: School of Foreign Languages, Shanghai University, Shanghai, China. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
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.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Foreign Languages, Shanghai University, Shanghai, China.
Zitieren
APA
Nie, Y. (2025). Automated essay scoring with SBERT embeddings and LSTM-Attention networks. PeerJ Computer Science, 11, e2634. https://doi.org/10.7717/peerj-cs.2634
Vancouver
Nie Y. Automated essay scoring with SBERT embeddings and LSTM-Attention networks. PeerJ Computer Science. 2025;11:e2634. doi:10.7717/peerj-cs.2634
BibTeX
@article{Nie2025,
author = {Nie, Yuzhe},
title = {Automated essay scoring with SBERT embeddings and LSTM-Attention networks},
journal = {PeerJ Computer Science},
year = {2025},
volume = {11},
pages = {e2634},
doi = {10.7717/peerj-cs.2634}
}
EUVIMED