Deep learning has been used in many fields including natural language processing. This paper aims to study the effect of applying deep learning in machine translation processes including word segmentation and translation model generation. We compare the results of the process from traditional statistical method and deep learning and analyze the difference. From experiment, the results indicated that the processes from deep learning obtained higher score in overall. Word segmentation from Bidirectional neural network yielded 0.861 f1 score which was higher than standard n-gram based system for 0.081. The translation results within dataset show that the neural-network-based translation got the best BLEU score in average for 0.43 in which are higher than the traditional statistical approach for 0.16. The result analysis indicates that the neural-network-based translation can translate better for Thai sentences containing unknown words and those with numerical classifier expression.
In the evolving cybersecurity landscape, detecting Thai-English code-mixed malicious scripts within high-trust domains such as governmental and academic portals presents a significant defensive challenge. While Transformer-based architectures excel in semantic parsing, they often exhibit ‘Structural Bias,’ misinterpreting the high-entropy syntax of benign legacy HyperText Markup Language (HTML) as malicious obfuscation due to inherent ‘Attention Deficit’ in token-limited models. To address this, we propose an Explainable AI (XAI)-Driven Hybrid Architecture grounded in a ‘Selective Integration’ strategy. Unlike traditional hybrid models, our framework mathematically formalizes the fusion process by synergizing context-aware WangChanBERTa embeddings with orthogonal structural statistics through Dempster-Shafer Theory and Conditional Mutual Information (CMI). The proposed model was validated on a high-fidelity corpus, achieving a state-of-the-art F1-score of 0.9908, significantly outperforming standalone Transformers, Random Forest, and unsupervised baselines. XAI diagnostics revealed a ‘Dual-Validation’ mechanism where structural features act as an epistemic anchor. This mechanism effectively triggers a ‘Semantic Veto’ to filter hallucinations caused by benign complexity, achieving a remarkably low False Positive Rate (FPR) of 0.0116. Our findings demonstrate that hybridization is most effective when engineered features provide mathematical orthogonality to semantic embeddings. This work offers a robust, theoretically grounded framework for securing critical digital infrastructures in low-resource linguistic environments.
Pre-trained Language Models (PLMs) have become foundational in Natural Language Processing, yet they remain vulnerable to backdoor attacks where hidden triggers manipulate model behavior. Existing defenses, particularly perturbationbased methods (e.g., STRIP) and perplexity-based approaches (e.g., ONION), exhibit critical failures when facing "Signal Dilution" in long-context documents, often degrading to randomguess performance. Furthermore, these methods typically operate as black boxes, lacking interpretability. To address these challenges, we propose D XAI, an explainable backdoor detection framework that unmasks triggers by analyzing the model's internal attribution landscape. Leveraging the proposed Funnel Effect mechanism-where triggers monopolize gradient flow-D XAI fuses Attribution Energy (signal intensity) and Distribution Inequality (signal sparsity) to isolate the distinctive signature of backdoor triggers. Extensive experiments across four benchmarks (SST-2, AG News, IMDb, and Thai Wongnai) demonstrate D XAI's superiority, achieving robust detection (AUROC ≈ 1.00) on long-context samples where baselines fail. Moreover, D XAI offers a computationally efficient inference capability, operating over 10× faster than perturbation-based counterparts, establishing it as a transparent and practical defense for deployed PLMs.