Article: Gradient optimisation and cross-language transfer mechanism of English translation model based on LSTM-transformer Journal: International Journal of Information and Communication Technology (IJICT) 2026 Vol.27 No.26 pp.22 - 36 Abstract: Amid globalisation and growing cross-language information needs, machine translation is crucial for overcoming language barriers. Deep learning has advanced it, but transformer faces limitations: insufficient efficiency in capturing long-range dependencies and poor performance in low-resource translation. To address these, this study proposes three core solutions: 1) a hybrid LSTM-transformer architecture fusing LSTM's gating mechanism (long-sequence modelling) and transformer's self-attention (global context capture); 2) an adaptive gradient clipping (AGC) strategy for training stability; 3) dynamic weight sharing with adversarial domain adaptation to enhance cross-language transfer. Experiments on WMT14 English-German/French corpora show the model's BLEU value is 2.8 higher than benchmark Transformer, with 18% faster convergence; in English → Romanian low-resource scenarios, the transfer mechanism boosts BLEU by 5.3. This study validates the hybrid architecture and optimisation strategies, offering new ideas for efficient gradient optimisation and low-resource translation models. Inderscience Publishers - linking academia, business and industry through research

Title: Gradient optimisation and cross-language transfer mechanism of English translation model based on LSTM-transformer

Authors: Meizhen Zou

Addresses: Faculty of General Education, Zhejiang Agricultural Business College, Shaoxing, 312000, China

Abstract: Amid globalisation and growing cross-language information needs, machine translation is crucial for overcoming language barriers. Deep learning has advanced it, but transformer faces limitations: insufficient efficiency in capturing long-range dependencies and poor performance in low-resource translation. To address these, this study proposes three core solutions: 1) a hybrid LSTM-transformer architecture fusing LSTM's gating mechanism (long-sequence modelling) and transformer's self-attention (global context capture); 2) an adaptive gradient clipping (AGC) strategy for training stability; 3) dynamic weight sharing with adversarial domain adaptation to enhance cross-language transfer. Experiments on WMT14 English-German/French corpora show the model's BLEU value is 2.8 higher than benchmark Transformer, with 18% faster convergence; in English → Romanian low-resource scenarios, the transfer mechanism boosts BLEU by 5.3. This study validates the hybrid architecture and optimisation strategies, offering new ideas for efficient gradient optimisation and low-resource translation models.

Keywords: machine translation; LSTM-transformer; gradient cropping; cross-language transfer; adversarial learning.

DOI: 10.1504/IJICT.2026.152530

International Journal of Information and Communication Technology, 2026 Vol.27 No.26, pp.22 - 36

Received: 26 Aug 2025
Accepted: 19 Oct 2025
Published online: 25 Mar 2026 *

Title: Gradient optimisation and cross-language transfer mechanism of English translation model based on LSTM-transformer

Keep up-to-date