Neural machine translation (NMT) plays a vital role in modern communication by bridging language barriers and enabling effective information exchange across diverse linguistic communities. Due to the limited availability of data in low-resource languages, NMT faces significant translation challenges. Data sparsity limits NMT models’ ability to learn, generalize, and produce accurate translations, which leads to low coherence and poor context awareness. This paper proposes a transformer-based approach incorporating an encoder–decoder structure, bilingual curriculum learning, and contrastive re-ranking mechanisms. Our approach enriches the training dataset using back-translation and enhances the model’s contextual learning through BERT embeddings. An incomplete-trust (in-trust) loss function is introduced to replace the traditional cross-entropy loss during training. The proposed model effectively handles out-of-vocabulary words and integrates named entity recognition techniques to maintain semantic accuracy. Additionally, the self-attention layers in the transformer architecture enhance the model’s syntactic analysis capabilities, which enables better context awareness and more accurate translations. Extensive experiments are performed on a diverse Chinese–Urdu parallel corpus, developed using human effort and publicly available datasets such as OPUS, WMT, and WiLi. The proposed model demonstrates a BLEU score improvement of 1.80% for Zh→Ur and 2.22% for Ur→Zh compared to the highest-performing comparative model. This significant enhancement indicates better translation quality and accuracy.

Detecting fake news is essential in natural language processing to verify news authenticity and prevent misinformation-driven social, political, and economic disruptions targeting specific groups. A major challenge in multimodal fake news detection is effectively integrating textual and visual modalities, as semantic gaps and contextual variations between images and text complicate alignment, interpretation, and the detection of subtle or blatant inconsistencies. To enhance accuracy in fake news detection, this article introduces an ensemble-based framework that integrates textual and visual data using ViLBERT’s two-stream architecture, incorporates VADER sentiment analysis to detect emotional language, and uses Image–Text Contextual Similarity to identify mismatches between visual and textual elements. These features are processed through the Bi-GRU classifier, Transformer-XL, DistilBERT, and XLNet, combined via a stacked ensemble method with soft voting, culminating in a T5 metaclassifier that predicts the outcome for robustness. Results on the Fakeddit and Weibo benchmarking datasets show that our method outperforms state-of-the-art models, achieving up to 96% and 94% accuracy in fake news detection, respectively. This study highlights the necessity for advanced multimodal fake news detection systems to address the increasing complexity of misinformation and offers a promising solution.

Breast cancer is one of the leading causes of cancer-related deaths among women worldwide, making early and accurate detection essential. Although mammography remains the primary imaging modality for screening, its effectiveness is often hindered by noise, artifacts, and the difficulty of identifying small tumors in dense breast tissue. Existing approaches frequently suffer from high false positive and false negative rates as well as limited generalization. This paper introduces a framework that synergistically integrates sophisticated preprocessing techniques, including noise reduction using the Center Adaptive Median Filter (CEAMF), contrast enhancement, and illumination correction, with a U-MDC-based semantic segmentation module for precise tumor delineation. A customized Convolutional Neural Network (CNN) enhanced by the Willow Catkin Optimization (WCO) algorithm serves as the baseline, while fine-tuned VGG19, ResNet152, and ResNet50 models are employed for classification. The proposed models were evaluated on the CBIS-DDSM and INbreast datasets. The best-performing ResNet50 model achieved 97.80% accuracy on CBIS-DDSM and 97.10% on INbreast, along with strong precision and recall. By effectively addressing key challenges in mammography analysis, the framework achieves encouraging results on the evaluated benchmark datasets and provides a promising basis for future external clinical validation.