Article: English diversified and high-fidelity translation based on adaptive label smoothing algorithm Journal: International Journal of Information and Communication Technology (IJICT) 2026 Vol.27 No.42 pp.20 - 46 Abstract: This study proposes a novel English translation method using an adaptive label smoothing algorithm to address issues of rigid and non-diverse outputs. It employs three modules: a grammar feature capture module (redefined as a 'multi-modal syntactic structure modeller'), a component attention-enhanced encoder, and an adaptive label smoothing decoder. These create an interaction mechanism of syntactic feature, attention, and loss weight flows to better represent sentence structures and generate varied translations. Experimental results show the model's repetition rate reduced to 0.09, beating diverse beam search (0.12). It achieved a syntactic tree similarity score of 0.87, outperforming a grammar-enhanced model by 0.09. With ten candidate outputs, it showed higher diversity in sentence length and n-gram differences (8.60 and 0.92) compared to baseline methods. The model also demonstrated efficient convergence, with loss dropping to 0.98 after 50 epochs. The method enhances translation accuracy, semantic fidelity, and output diversity under a clear evaluation framework. Inderscience Publishers - linking academia, business and industry through research

Title: English diversified and high-fidelity translation based on adaptive label smoothing algorithm

Authors: Xi Chen

Addresses: School of Humanities and Law, Zhengzhou Technology and Business University, Zhengzhou, 451400, China

Abstract: This study proposes a novel English translation method using an adaptive label smoothing algorithm to address issues of rigid and non-diverse outputs. It employs three modules: a grammar feature capture module (redefined as a 'multi-modal syntactic structure modeller'), a component attention-enhanced encoder, and an adaptive label smoothing decoder. These create an interaction mechanism of syntactic feature, attention, and loss weight flows to better represent sentence structures and generate varied translations. Experimental results show the model's repetition rate reduced to 0.09, beating diverse beam search (0.12). It achieved a syntactic tree similarity score of 0.87, outperforming a grammar-enhanced model by 0.09. With ten candidate outputs, it showed higher diversity in sentence length and n-gram differences (8.60 and 0.92) compared to baseline methods. The model also demonstrated efficient convergence, with loss dropping to 0.98 after 50 epochs. The method enhances translation accuracy, semantic fidelity, and output diversity under a clear evaluation framework.

Keywords: English translation; label smoothing algorithm; constituent attention; grammar feature capture; mixture of experts model.

DOI: 10.1504/IJICT.2026.153383

International Journal of Information and Communication Technology, 2026 Vol.27 No.42, pp.20 - 46

Received: 13 Oct 2025
Accepted: 28 Jan 2026
Published online: 06 May 2026 *

Title: English diversified and high-fidelity translation based on adaptive label smoothing algorithm

Keep up-to-date