Lingfang Li^1,2, Weijian Hu², Mingxing Luo^1,*

CMC-Computers, Materials & Continua, Vol.84, No.3, pp. 5915-5935, 2025, DOI:10.32604/cmc.2025.064349 - 30 July 2025

Abstract Neural machine translation (NMT) has been widely applied to high-resource language pairs, but its dependence on large-scale data results in poor performance in low-resource scenarios. In this paper, we propose a transfer-learning-based approach called shared space transfer for zero-resource NMT. Our method leverages a pivot pre-trained language model (PLM) to create a shared representation space, which is used in both auxiliary source→pivot (Ms2p) and pivot→target (Mp2t) translation models. Specifically, we exploit pivot PLM to initialize the Ms2p decoder and Mp2t encoder, while adopting a freezing strategy during the training process. We further propose a feature… More >

Erlin Tian¹, Zengchao Zhu^2,*, Fangmei Liu², Zuhe Li²

CMC-Computers, Materials & Continua, Vol.83, No.2, pp. 2305-2322, 2025, DOI:10.32604/cmc.2025.061145 - 16 April 2025

Abstract Within the realm of multimodal neural machine translation (MNMT), addressing the challenge of seamlessly integrating textual data with corresponding image data to enhance translation accuracy has become a pressing issue. We saw that discrepancies between textual content and associated images can lead to visual noise, potentially diverting the model’s focus away from the textual data and so affecting the translation’s comprehensive effectiveness. To solve this visual noise problem, we propose an innovative KDNR-MNMT model. The model combines the knowledge distillation technique with an anti-noise interaction mechanism, which makes full use of the synthesized graphic knowledge… More >

Murun Yang^1,*, Fuxue Li²

CMC-Computers, Materials & Continua, Vol.82, No.2, pp. 2061-2075, 2025, DOI:10.32604/cmc.2024.058248 - 17 February 2025

Abstract Preserving formal style in neural machine translation (NMT) is essential, yet often overlooked as an optimization objective of the training processes. This oversight can lead to translations that, though accurate, lack formality. In this paper, we propose how to improve NMT formality with large language models (LLMs), which combines the style transfer and evaluation capabilities of an LLM and the high-quality translation generation ability of NMT models to improve NMT formality. The proposed method (namely INMTF) encompasses two approaches. The first involves a revision approach using an LLM to revise the NMT-generated translation, ensuring a… More >

Muhammad Naeem Ul Hassan^1,2, Zhengtao Yu^1,2,*, Jian Wang^1,2, Ying Li^1,2, Shengxiang Gao^1,2, Shuwan Yang^1,2, Cunli Mao^1,2

CMC-Computers, Materials & Continua, Vol.81, No.1, pp. 951-969, 2024, DOI:10.32604/cmc.2024.054673 - 15 October 2024

Abstract Thanks to the strong representation capability of pre-trained language models, supervised machine translation models have achieved outstanding performance. However, the performances of these models drop sharply when the scale of the parallel training corpus is limited. Considering the pre-trained language model has a strong ability for monolingual representation, it is the key challenge for machine translation to construct the in-depth relationship between the source and target language by injecting the lexical and syntactic information into pre-trained language models. To alleviate the dependence on the parallel corpus, we propose a Linguistics Knowledge-Driven Multi-Task (LKMT) approach to… More >

Liqing Wang^*, Yiheng Xiao

Intelligent Automation & Soft Computing, Vol.39, No.4, pp. 619-631, 2024, DOI:10.32604/iasc.2024.052971 - 06 September 2024

Abstract Neural Machine Translation is one of the key research directions in Natural Language Processing. However, limited by the scale and quality of parallel corpus, the translation quality of low-resource Neural Machine Translation has always been unsatisfactory. When Reinforcement Learning from Human Feedback (RLHF) is applied to low-resource machine translation, commonly encountered issues of substandard preference data quality and the higher cost associated with manual feedback data. Therefore, a more cost-effective method for obtaining feedback data is proposed. At first, optimizing the quality of preference data through the prompt engineering of the Large Language Model (LLM), More >

Huma Israr^1,*, Safdar Abbas Khan¹, Muhammad Ali Tahir¹, Muhammad Khuram Shahzad¹, Muneer Ahmad¹, Jasni Mohamad Zain^2,*

CMC-Computers, Materials & Continua, Vol.75, No.2, pp. 2981-3009, 2023, DOI:10.32604/cmc.2023.035814 - 31 March 2023

Abstract In bilingual translation, attention-based Neural Machine Translation (NMT) models are used to achieve synchrony between input and output sequences and the notion of alignment. NMT model has obtained state-of-the-art performance for several language pairs. However, there has been little work exploring useful architectures for Urdu-to-English machine translation. We conducted extensive Urdu-to-English translation experiments using Long short-term memory (LSTM)/Bidirectional recurrent neural networks (Bi-RNN)/Statistical recurrent unit (SRU)/Gated recurrent unit (GRU)/Convolutional neural network (CNN) and Transformer. Experimental results show that Bi-RNN and LSTM with attention mechanism trained iteratively, with a scalable data set, make precise predictions on unseen… More >

Sarah Alissa^1,*, Mike Wald²

CMC-Computers, Materials & Continua, Vol.75, No.2, pp. 3479-3495, 2023, DOI:10.32604/cmc.2023.033647 - 31 March 2023

Abstract Reading and writing are the main interaction methods with web content. Text simplification tools are helpful for people with cognitive impairments, new language learners, and children as they might find difficulties in understanding the complex web content. Text simplification is the process of changing complex text into more readable and understandable text. The recent approaches to text simplification adopted the machine translation concept to learn simplification rules from a parallel corpus of complex and simple sentences. In this paper, we propose two models based on the transformer which is an encoder-decoder structure that achieves state-of-the-art… More >

Shijie Hu¹, Xiaoyu Li^1,*, Jiayu Bai¹, Hang Lei¹, Weizhong Qian¹, Sunqiang Hu¹, Cong Zhang², Akpatsa Samuel Kofi¹, Qian Qiu^2,3, Yong Zhou⁴, Shan Yang⁵

CMC-Computers, Materials & Continua, Vol.74, No.2, pp. 2803-2815, 2023, DOI:10.32604/cmc.2023.032732 - 31 October 2022

Abstract When the Transformer proposed by Google in 2017, it was first used for machine translation tasks and achieved the state of the art at that time. Although the current neural machine translation model can generate high quality translation results, there are still mistranslations and omissions in the translation of key information of long sentences. On the other hand, the most important part in traditional translation tasks is the translation of key information. In the translation results, as long as the key information is translated accurately and completely, even if other parts of the results are… More >

Sajadul Hassan Kumhar¹, Syed Immamul Ansarullah², Akber Abid Gardezi³, Shafiq Ahmad⁴, Abdelaty Edrees Sayed⁴, Muhammad Shafiq^5,*

CMC-Computers, Materials & Continua, Vol.74, No.2, pp. 3899-3912, 2023, DOI:10.32604/cmc.2023.032290 - 31 October 2022

Abstract English to Urdu machine translation is still in its beginning and lacks simple translation methods to provide motivating and adequate English to Urdu translation. In order to make knowledge available to the masses, there should be mechanisms and tools in place to make things understandable by translating from source language to target language in an automated fashion. Machine translation has achieved this goal with encouraging results. When decoding the source text into the target language, the translator checks all the characteristics of the text. To achieve machine translation, rule-based, computational, hybrid and neural machine translation… More >

Walaa Gad^1,*, Anas Alokla¹, Waleed Nazih², Mustafa Aref¹, Abdel-badeeh Salem¹

CMC-Computers, Materials & Continua, Vol.70, No.2, pp. 3117-3132, 2022, DOI:10.32604/cmc.2022.019884 - 27 September 2021

Abstract Understanding the content of the source code and its regular expression is very difficult when they are written in an unfamiliar language. Pseudo-code explains and describes the content of the code without using syntax or programming language technologies. However, writing Pseudo-code to each code instruction is laborious. Recently, neural machine translation is used to generate textual descriptions for the source code. In this paper, a novel deep learning-based transformer (DLBT) model is proposed for automatic Pseudo-code generation from the source code. The proposed model uses deep learning which is based on Neural Machine Translation (NMT)… More >