Md. Rajib Ahamed, S. M. Ahanaf Tahmid
Instructor of Computer Science & Technology, Daffodil Polytechnic Institute
Institute, Dhaka, Bangladesh, Computer Science and Engineering, Chongqing University of Technology
Abstract
With the recent development of deep learning models in natural language processing more opportunities are extended to intelligent language translation systems. This work examines Implementing CNN and Transformer Architecture to improve the performance of Translation from source language towards the target language. Through considering themselves the semantic and the syntactic differences of different languages, thus, our strategy directly uses the qualitative approaches and the newest deep learning trends to provide the target audience with high-quality translations and with no distortions. These open-source models are trained on different multilingual datasets to deliver dogmatic and highly-scalable approaches. To demonstrate the effectiveness of our proposed system, we provide empirical assessment of the system along with comparison with other existing translation systems. This means that the outcomes show the improvements in accuracy when it comes to interpreting the structures in complex languages and the decrease in the number of computations needed. This paper also describes the future prospects of deep learning based translation systems, more specifically in real time applications, and gives some recommendations of further studies.
Keywords
Deep Learning, Natural Language Processing, Neural Networks, Transformer Models, Language Translation Systems
Citation
Md. Rajib Ahamed, & S. M. Ahanaf Tahmid. (2025). Deep Learning-Based Intelligent Language Translation Systems. In Journal of Global Knowledge and Innovation (1.1, Vol. 2, Number 4, pp. 127–134). Journal of Global Knowledge and Innovation (JGKI). https://doi.org/10.5281/zenodo.14635266