Article: Intelligent English translation scoring method based on multi-angle semantic feature calculation model Journal: International Journal of Continuing Engineering Education and Life-Long Learning (IJCEELL) 2026 Vol.36 No.11 pp.50 - 73 Abstract: The research aims to construct an intelligent scoring model based on multi-angle semantic feature calculation to deal with the deficiencies of traditional methods. The research proposes a multi-angle semantic feature computing model based on a multi-level semantic collaboration mechanism (MMSF-ISM). This model organically integrates the deep semantic representation of BERT, the global attention of transformer, the long-term dependency modelling of LSTM, and the local feature extraction capabilities of convolutional networks through a semantic gating fusion mechanism, achieving four-dimensional collaborative evaluation at the lexical, grammatical, semantic, and text levels. The findings denote that the Pearson correlation coefficients between the intelligent scoring model based on multi-angle semantic feature calculation and manual scoring reach 89% and 85%, respectively, which is more than 40% higher than traditional methods. This model demonstrates good generalisation ability in practical application scenarios, making it important for advancing the progress of intelligent education technology. Inderscience Publishers - linking academia, business and industry through research

Title: Intelligent English translation scoring method based on multi-angle semantic feature calculation model

Authors: Qiongjie Jing

Addresses: School of Foreign Languages, Sias University, Zhengzhou, 450000, China

Abstract: The research aims to construct an intelligent scoring model based on multi-angle semantic feature calculation to deal with the deficiencies of traditional methods. The research proposes a multi-angle semantic feature computing model based on a multi-level semantic collaboration mechanism (MMSF-ISM). This model organically integrates the deep semantic representation of BERT, the global attention of transformer, the long-term dependency modelling of LSTM, and the local feature extraction capabilities of convolutional networks through a semantic gating fusion mechanism, achieving four-dimensional collaborative evaluation at the lexical, grammatical, semantic, and text levels. The findings denote that the Pearson correlation coefficients between the intelligent scoring model based on multi-angle semantic feature calculation and manual scoring reach 89% and 85%, respectively, which is more than 40% higher than traditional methods. This model demonstrates good generalisation ability in practical application scenarios, making it important for advancing the progress of intelligent education technology.

Keywords: English translation intelligent scoring; multi-angle semantic features; BERT; long short-term memory; LSTM; feature fusion; error detection.

DOI: 10.1504/IJCEELL.2026.154663

International Journal of Continuing Engineering Education and Life-Long Learning, 2026 Vol.36 No.11, pp.50 - 73

Received: 18 Nov 2025
Accepted: 03 Feb 2026
Published online: 09 Jul 2026 *

Title: Intelligent English translation scoring method based on multi-angle semantic feature calculation model

Keep up-to-date