{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T18:17:22Z","timestamp":1787941042925,"version":"build-2784847793"},"reference-count":35,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T00:00:00Z","timestamp":1787875200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>News texts are characterized by their timeliness, contextual dependence, and density of proper nouns. Cultural terms, often appearing as metaphors, allusions, or institutional terms, are frequently long-tailed words lacking sufficient corpus support, easily leading to semantic drift and cultural information loss in translation. To address these issues, this paper combines a diffusion model with a sparse coding strategy to improve the accuracy and cultural adaptability of cultural terms in English news translation. In the encoding stage, a sparse semantic extraction module based on L1 norm constraints and dictionary learning is constructed to sparsely represent the input sequence, strengthening the expression of key information about cultural terms. In the decoding stage, a diffusion generation mechanism is introduced to gradually reconstruct the target text through multi-step denoising. Simultaneously, by combining time-step-aware gating and cultural ontology knowledge constraints, end-to-end collaborative optimization of cultural feature extraction and target language generation is achieved. Experimental results show that compared with mainstream models such as Transformer, mBART-50 (many to many multilingual machine translation), and DiffuSeq (Sequence to sequence text generation with diffusion models), proposed model achieves BLEU (Bilingual Evaluation Understudy)-4 and METEOR (Metric for Evaluation of Translation with Explicit Ordering) scores of 27.8% and 29.2%, respectively, on long-tail news text (sentences of 46 words or more). In the unregistered vocabulary scenario, the accuracy and recall rates were 73.7% and 65.2%, respectively, and the cultural semantic consistency index reached 0.892. The results indicate that the proposed synergistic mechanism of sparse coding and diffusion generation facilitates weak semantic recognition and progressive semantic restoration, providing a technical path for cross-cultural machine translation in international news communication that combines accuracy with cultural adaptability.<\/jats:p>","DOI":"10.1371\/journal.pone.0356146","type":"journal-article","created":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T17:26:02Z","timestamp":1787937962000},"page":"e0356146","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Combining a diffusion model with a sparse coding strategy to improve the machine translation accuracy of culturally loaded words in English news texts"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2175-1556","authenticated-orcid":true,"given":"Qin","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Mai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,8,28]]},"reference":[{"issue":"1","key":"pone.0356146.ref001","doi-asserted-by":"crossref","first-page":"01","DOI":"10.32996\/ijtis.2021.1.1.1","article-title":"Cultural-Loaded Words in Journalistic Translation Between Arabic and English","volume":"1","author":"F Guessabi","year":"2021","journal-title":"IJTIS"},{"issue":"2","key":"pone.0356146.ref002","first-page":"1","article-title":"Evaluating three neural machine translation platforms for English-Arabic translation: A comparative study of linguistic accuracy and cultural fidelity","volume":"16","author":"SA Al Maaytah","year":"2026","journal-title":"World"},{"issue":"2","key":"pone.0356146.ref003","doi-asserted-by":"crossref","first-page":"259","DOI":"10.25077\/ar.12.2.259-273.2025","article-title":"Strategies, Errors, and Challenges in Translating Culture-Specific Items in Chinese-English Literary Works: A Systematic Review","volume":"12","author":"W Qiufen","year":"2025","journal-title":"Arbitrer"},{"issue":"3","key":"pone.0356146.ref004","first-page":"62","article-title":"Challenges of contextual appropriacy in machine translation: An analysis of translations between Bangla and English","volume":"8","author":"NS Shamron","year":"2025","journal-title":"Journal of ELT and Education"},{"issue":"6","key":"pone.0356146.ref005","article-title":"English Translation of Culture-Loaded Words\u2014A Corpus Based Study","volume":"12","author":"Y-W Pian","year":"2022","journal-title":"JLAS"},{"issue":"2","key":"pone.0356146.ref006","first-page":"89","article-title":"Translation of culture-loaded words from the perspective of cross-cultural communication","volume":"4","author":"R Ma","year":"2023","journal-title":"International Journal of Social Sciences and Economic Management"},{"issue":"1","key":"pone.0356146.ref007","doi-asserted-by":"crossref","first-page":"608","DOI":"10.29110\/soylemdergi.1602058","article-title":"An analysis of neural machine translation on cross-cultural communication: A case study of Airbnb\u2019s translation function","volume":"10","author":"D Bal","year":"2025","journal-title":"S\u00f6ylem Filoloji Dergisi"},{"issue":"6","key":"pone.0356146.ref008","doi-asserted-by":"crossref","first-page":"466","DOI":"10.5573\/IEIESPC.2023.12.6.466","article-title":"Automatic Chinese-English Translation Algorithm based on Out-of-vocabulary Words in the Context of Cross-cultural Communication","volume":"12","author":"J Duan","year":"2023","journal-title":"IEIESPC"},{"issue":"1","key":"pone.0356146.ref009","first-page":"81","article-title":"The Influence of Word Vectorization for Kawi Language to Indonesian Language Neural Machine Translation","volume":"7","author":"IGBA Budaya","year":"2022","journal-title":"J Inf Tech Comp Sci"},{"issue":"6","key":"pone.0356146.ref010","doi-asserted-by":"crossref","DOI":"10.12694\/scpe.v25i6.3296","article-title":"Research on English Translation Optimization Algorithm Based on Statistical Machine Learning","volume":"25","author":"J Wang","year":"2024","journal-title":"SCPE"},{"issue":"19","key":"pone.0356146.ref011","doi-asserted-by":"crossref","first-page":"6509","DOI":"10.3390\/s21196509","article-title":"A Transformer-Based Neural Machine Translation Model for Arabic Dialects That Utilizes Subword Units","volume":"21","author":"LH Baniata","year":"2021","journal-title":"Sensors (Basel)"},{"issue":"32","key":"pone.0356146.ref012","doi-asserted-by":"crossref","first-page":"195","DOI":"10.31449\/inf.v49i32.8834","article-title":"Adaptive transformer-based framework for cross-lingual translation similarity detection with bilingual embedding alignment","volume":"49","author":"J Jiao","year":"2025","journal-title":"Informatica"},{"issue":"4","key":"pone.0356146.ref013","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3626235","article-title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","volume":"56","author":"L Yang","year":"2023","journal-title":"ACM Comput Surv"},{"key":"pone.0356146.ref014","doi-asserted-by":"crossref","unstructured":"Chen H, Xu Z, Gu Z, Lan J, Zheng X, Li Y, et al. DiffUTE: Universal Text Editing Diffusion Model. In: Advances in Neural Information Processing Systems 36, 2023. 63062\u201374. https:\/\/doi.org\/10.52202\/075280-2753","DOI":"10.52202\/075280-2753"},{"issue":"4","key":"pone.0356146.ref015","first-page":"1","article-title":"Innovations and frontiers of diffusion models in natural language processing: A review","volume":"1","author":"Z Su","year":"2025","journal-title":"INNO-PRESS: Journal of Emerging Applied AI"},{"key":"pone.0356146.ref016","doi-asserted-by":"crossref","unstructured":"Lovelace J, Kishore V, Wan C, Shekhtman E, Weinberger K. Latent Diffusion for Language Generation. In: Advances in Neural Information Processing Systems 36, 2023. 56998\u20137025. https:\/\/doi.org\/10.52202\/075280-2492","DOI":"10.52202\/075280-2492"},{"key":"pone.0356146.ref017","doi-asserted-by":"crossref","unstructured":"Gulrajani I, Hashimoto T. Likelihood-Based Diffusion Language Models. In: Advances in Neural Information Processing Systems 36, 2023. 16693\u2013715. https:\/\/doi.org\/10.52202\/075280-0730","DOI":"10.52202\/075280-0730"},{"issue":"6","key":"pone.0356146.ref018","doi-asserted-by":"crossref","first-page":"2399","DOI":"10.26599\/TST.2023.9010097","article-title":"A Survey of Multilingual Neural Machine Translation Based on Sparse Models","volume":"30","author":"S Zhu","year":"2025","journal-title":"Tsinghua Sci Technol"},{"issue":"10","key":"pone.0356146.ref019","first-page":"543","article-title":"From idioms to algorithms: Translating culture-specific expressions in AI systems","volume":"7","author":"D Azizov","year":"2024","journal-title":"Iconic Research And Engineering Journals"},{"issue":"8","key":"pone.0356146.ref020","first-page":"1481","article-title":"Neural machine translation based on dictionary model fusion","volume":"44","author":"X Wang","year":"2022","journal-title":"Computer Engineering and Science"},{"issue":"5","key":"pone.0356146.ref021","first-page":"138","article-title":"Study on the robustness of neural machine translation models based on word order perturbations","volume":"9","author":"Y Zhao","year":"2023","journal-title":"Chinese Journal of Network & Information Security"},{"key":"pone.0356146.ref022","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TC.2022.3208206","article-title":"Dynamic Sparse Attention for Scalable Transformer Acceleration","author":"L Liu","year":"2022","journal-title":"IEEE Trans Comput"},{"issue":"4","key":"pone.0356146.ref023","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1007\/s11633-022-1393-5","article-title":"Transformer: A General Framework from Machine Translation to Others","volume":"20","author":"Y Zhao","year":"2023","journal-title":"Mach Intell Res"},{"issue":"1","key":"pone.0356146.ref024","doi-asserted-by":"crossref","DOI":"10.1186\/s44147-022-00159-4","article-title":"MarianCG: a code generation transformer model inspired by machine translation","volume":"69","author":"AS Soliman","year":"2022","journal-title":"J Eng Appl Sci"},{"issue":"1376","key":"pone.0356146.ref025","first-page":"17981","article-title":"Structured denoising diffusion models in discrete state-spaces","volume":"34","author":"J Austin","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pone.0356146.ref026","doi-asserted-by":"crossref","unstructured":"Wu T, Fan Z, Liu X, Zheng H-T, Gong Y, Shen Y, et al. AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation. In: Advances in Neural Information Processing Systems 36, 2023. 39957\u201374. https:\/\/doi.org\/10.52202\/075280-1737","DOI":"10.52202\/075280-1737"},{"key":"pone.0356146.ref027","doi-asserted-by":"crossref","unstructured":"Chen Z, Ma X, Fang G, Tan Z, Wang X. AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising. In: Advances in Neural Information Processing Systems 37, 2024. 95170\u201397. https:\/\/doi.org\/10.52202\/079017-3015","DOI":"10.52202\/079017-3015"},{"issue":"2","key":"pone.0356146.ref028","doi-asserted-by":"crossref","first-page":"534","DOI":"10.5715\/jnlp.31.534","article-title":"Revisiting Pre-training of Embedding Layers in Transformer-based Neural Machine Translation","volume":"31","author":"M Neishi","year":"2024","journal-title":"Journal of Natural Language Processing"},{"issue":"2","key":"pone.0356146.ref029","doi-asserted-by":"crossref","first-page":"243","DOI":"10.3390\/electronics14020243","article-title":"Transformer-Based Re-Ranking Model for Enhancing Contextual and Syntactic Translation in Low-Resource Neural Machine Translation","volume":"14","author":"A Javed","year":"2025","journal-title":"Electronics"},{"issue":"6","key":"pone.0356146.ref030","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3465383","article-title":"Exploration of Effective Attention Strategies for Neural Automatic Post-editing with Transformer","volume":"20","author":"J Shin","year":"2021","journal-title":"ACM Trans Asian Low-Resour Lang Inf Process"},{"issue":"4","key":"pone.0356146.ref031","doi-asserted-by":"crossref","first-page":"985","DOI":"10.17507\/tpls.1404.07","article-title":"An Evaluation of ChatGPT\u2019s Translation Accuracy Using BLEU Score","volume":"14","author":"M Ghassemiazghandi","year":"2024","journal-title":"tpls"},{"issue":"2","key":"pone.0356146.ref032","first-page":"60","article-title":"Machine translation quality based on TER analysis from English into Slovak","volume":"3","author":"M Nemergut","year":"2024","journal-title":"L10N Journal"},{"issue":"4","key":"pone.0356146.ref033","doi-asserted-by":"crossref","first-page":"1006","DOI":"10.3390\/math11041006","article-title":"A Survey on Evaluation Metrics for Machine Translation","volume":"11","author":"S Lee","year":"2023","journal-title":"Mathematics"},{"issue":"1","key":"pone.0356146.ref034","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1515\/les-2020-0009","article-title":"Automatische Evaluation der Human\u00fcbersetzung: BLEU vs. METEOR","volume":"65","author":"H-Y Chung","year":"2020","journal-title":"Lebende Sprachen"},{"issue":"2","key":"pone.0356146.ref035","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1017\/S1351324919000469","article-title":"How to evaluate machine translation: A review of automated and human metrics","volume":"26","author":"E Chatzikoumi","year":"2019","journal-title":"Nat Lang Eng"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0356146","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T17:26:11Z","timestamp":1787937971000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0356146"}},"subtitle":[],"editor":[{"given":"Issa","family":"Atoum","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,28]]},"references-count":35,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8,28]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0356146","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,28]]}}}