Article: Design and implementation of a real-time intelligent translation system for network language based on incremental learning Journal: International Journal of Continuing Engineering Education and Life-Long Learning (IJCEELL) 2026 Vol.36 No.9 pp.21 - 39 Abstract: This paper proposes a real-time intelligent system based on incremental learning for translating network language, in order to solve the problem of traditional translation systems being unable to cope with language changes, resulting in insufficient translation accuracy and adaptability. This paper adopts a converter model to construct a translation architecture, which effectively processes complex language structures using its self-attention mechanism while receiving and processing network language data in real-time, ensuring the efficiency of data flow. The introduction of incremental learning mechanism enables the model to dynamically absorb new language features, and in the process of continuously inputting new data, the translation results can be continuously optimised. The experimental results show that the incremental learning model outperforms the traditional model in bilingual evaluation understudy (BLEU) score and accuracy, and significantly outperforms the traditional model in training time (5 hours) and average translation time (0.4 seconds). Inderscience Publishers - linking academia, business and industry through research

Title: Design and implementation of a real-time intelligent translation system for network language based on incremental learning

Authors: Ying Liu

Addresses: Foreign Languages Teaching Department, Changchun University of Chinese Medicine, Changchun, 130117, Jilin, China

Abstract: This paper proposes a real-time intelligent system based on incremental learning for translating network language, in order to solve the problem of traditional translation systems being unable to cope with language changes, resulting in insufficient translation accuracy and adaptability. This paper adopts a converter model to construct a translation architecture, which effectively processes complex language structures using its self-attention mechanism while receiving and processing network language data in real-time, ensuring the efficiency of data flow. The introduction of incremental learning mechanism enables the model to dynamically absorb new language features, and in the process of continuously inputting new data, the translation results can be continuously optimised. The experimental results show that the incremental learning model outperforms the traditional model in bilingual evaluation understudy (BLEU) score and accuracy, and significantly outperforms the traditional model in training time (5 hours) and average translation time (0.4 seconds).

Keywords: incremental learning; network language; transformer model; real-time translation; intelligent translation system; system design; implementation.

DOI: 10.1504/IJCEELL.2026.153587

International Journal of Continuing Engineering Education and Life-Long Learning, 2026 Vol.36 No.9, pp.21 - 39

Received: 19 Feb 2025
Accepted: 15 Oct 2025
Published online: 18 May 2026 *

Title: Design and implementation of a real-time intelligent translation system for network language based on incremental learning

Keep up-to-date