Aug 2026· Discover Internet of Things· Vol 6· 0 citations· 33 references
TL;DR
The proposed AI-IEMS based on DynAc-Trans-ELSTM is a potential solution to the previous drawbacks of the models and will be more effective with regard to quality evaluation in a wider range of translation contexts.
Abstract
The evaluation of the quality of translation is an essential and important aspect in translation, which is mostly done by human judgment, whether in machine translation or human translation. Current automatic systems lack in capturing the subtleties of context, and the quality of the translation, which makes them not so scalable or accurate for real-world use. The research introduces a novel approach combining the Dynamic Ant Colony-Transformer-based Enhanced Long Short-Term Memory (DynAc-Trans-ELSTM) model with an AI-Enabled Intelligent Evaluation Modeling System (AI-IEMS) to assess the quality of English translations. The dataset is a large collection of parallel corpora, such as human-generated translations and expert evaluations from different translation platforms. Data pre-processing includes WordPiece Tokenization, BERT for subword text segmentation pre-processing and semantic learning. To extract, identify, and weight terms in the data set that are important, based on their frequency and importance, the term frequency-inverse document frequency (TF-IDF) is used. DynAc-Trans-ELSTM is a novel idea in the area of machine translation evaluation because it dynamically modifies the evaluation process by an intelligent model that is a combination of ACA, Transformer and ELSTM networks. The results show that DynAc-Trans-ELSTM shows better performance than all the baselines and with better accuracy (93.68%). The proposed AI-IEMS based on DynAc-Trans-ELSTM is a potential solution to the previous drawbacks of the models and will be more effective with regard to quality evaluation in a wider range of translation contexts.
A novel fusion-based Japanese-English translation system is presented to address the persistent challenges posed by heterogeneous, multi-domain text data in practical engineering environments. The study proposes an algorithmic framework designed to efficiently handle formal, informal, and technical language forms. It uses rule-based symbolic processing and advanced neural network translation models. The method aims to prepare complex Japanese input translation thru strict multistage data normalization, highly featured word segmentation, and adaptive contextual annotation. The core dual-path architecture dynamically controls the contribution of symbolic and neural components thru a context-aware weighting mechanism. This helps optimize translation fidelity based on the language characteristics and domain relevance of the input text. According to a comprehensive empirical evaluation, the system performs well in high variability domains and rare/ambiguous language patterns, and outperforms traditional neural network and symbolic baseline models in terms of efficiency and accuracy. Quantitative results show that the BLEU's appropriateness indicators, scores, and human fluency have been greatly improved. The technical design ensures industrial-grade throughput and scalability thru parallel reasoning and optimization. By combining symbolic language features and neural representation learning, the framework provides a reliable and adaptable solution to the limitations of current machine translation, and lays a technical foundation for advanced multilingual applications.
Na Qi· The 2026 International Confe...· 0 citations
The research offers a Lotus Effect-Attention-based Bi-directional Gated Recurrent Unit (LE-Att-Bi-GRU) deep learning model for automatic translation quality assessment that improves semantic representation by incorporating a lotus-inspired division method that decreases noise and focuses essential semantic cues.
Intelligent semantic information processing and adaptive knowledge generation have become key enabling technologies for next-generation communication and information systems. This study proposes a New Quality of Translation Productivity framework based on Large Language Models (NQTP-LLM) for intelligent multilingual information processing and adaptive educational support. The framework integrates transformer-based neural machine translation, Direct Preference Optimization (DPO), Retrieval-Augmented Generation (RAG), semantic embedding representation, and human-in-the-loop optimization to enhance contextual consistency, semantic fidelity, and translation efficiency. A multimodal translation evaluation architecture is established using semantic feature extraction, contextual knowledge retrieval, quality assessment, and adaptive feedback mechanisms. Experiments conducted on the AI vs TTM Translation Evaluation Dataset demonstrate that the proposed framework achieves a BLEU score of 0.961, with substantial improvements in METEOR, ROUGE, chrF, BERTScore, COMET, BLEURT, Google-BLEU, and NIST metrics while reducing post-editing effort by 3.9%. The results verify the effectiveness of integrating intelligent knowledge retrieval, semantic information fusion, and adaptive optimization for high-accuracy multilingual information processing. The proposed framework provides a practical approach for intelligent communication systems, semantic information services, human–AI collaborative decision support, and next-generation knowledge-centric digital environments.
W. Zhou, X. Zhou· Advanced Electromagnetics· 0 citations
It is noted that current use cases highly depend on the severity and context of the situation in which translations are being produced, but that the future of language models supporting accessible and quality translations is optimistic.
This paper presents a technical solution for the translation of classical texts by integrating a deep learning-based preliminary translation model with a real-time neural post-editing framework. The system uses an advanced Transformer architecture for initial translation and a hierarchical attention mechanism to optimize translation output in real time. Data preprocessing techniques for classical corpora ensure the preservation of rare lexical items and syntactic complexity. Experimental evaluation was performed using a high-performance computing environment, and the fidelity and running efficiency of the translation were evaluated. It outperforms the transformer-only and traditional rule-based baselines on BLEU and Translation Edit Rate metrics. Experimental evaluation is performed on a large-scale, curated parallel dataset of historical texts. The analysis results show that the inference latency is reduced, the semantic alignment is enhanced, and the domain-specific expressions can be effectively handled. The neural post-editing module can correct surface and deep contextual errors, thus generating translation results that are very close to expert human translation. This proves the effectiveness of the system in large-scale, high-precision translation tasks in the fields of computational linguistics and digital humanities. The study also pointed out the technical problems in the current industry adaptation and resource utilization, and emphasized the necessity of further improvement of the technology.
Ming-Hua Yuan· International Conference on...· 0 citations
Machine Translation has become one of the major application areas of Artificial Intelligence (AI) and Natural Language Processing (NLP), especially in multilingual countries like India. Although recent Neural Machine Translation systems have shown good performance for several language pairs, translation quality is still inconsistent for many Indian languages because of linguistic and structural differences between English and Indian language families. Most Indian languages are morphologically rich and contain flexible word order, complex agreement patterns, compound constructions, and context-dependent grammatical forms. Because of this, direct translation from English often produces structurally incorrect or semantically weak output. In many existing systems, the source sentence is passed to the translation model without sufficient linguistic analysis. As a result, ambiguity present in the source text propagates further during translation. This work focuses on the importance of linguistic enrichment before the translation stage. The proposed framework, named Unified Linguistic-Aware Pre-Parsing Framework, introduces a coordinated pre-processing layer for English-to-Indian Machine Translation (MT). A key contribution of this research is the development of a novel linguistically enriched intermediate representation that extends beyond conventional text normalization. By transforming noisy input text into linguistically enriched translation-ready representation, the proposed approach facilitates effective knowledge transfer to machine translation models, leading to improve contextual adequacy, linguistic fidelity, and overall translation performance. The framework combines multiple linguistic processing stages including POS tagging, NE detection, clause boundary analysis, contextual token handling, syntactic structure preparation, and morphology-related processing. Instead of executing these modules independently, the proposed system allows interaction between lexical, syntactic, and morphological information during analysis. This helps reduce structural ambiguity and improves sentence-level interpretation before translation begins. The need for such a framework becomes more relevant in the context of Indian languages where morphology and grammatical relations carry significant semantic information. This framework is especially relevant for Indian languages, where semantic information is often encoded through morphological variations and grammatical dependencies. The proposed framework can be effectively integrated with both conventional machine translation architectures and modern large language models. The overall study highlights how classical linguistic analysis can still play an important role in improving multilingual AI systems for Indian languages.
Prashant Chaudhary, Pavan Kurariya, Jahnavi Bodhankar et al.· NLP & Big Data· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
