{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T13:08:18Z","timestamp":1753880898474,"version":"3.41.2"},"reference-count":28,"publisher":"World Scientific Pub Co Pte Ltd","issue":"04","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62371144"],"award-info":[{"award-number":["62371144"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Wavelets Multiresolut Inf. Process."],"published-print":{"date-parts":[[2025,7]]},"abstract":"<jats:p> In the field of neural machine translation (NMT), improving translation quality remains a significant challenge, especially for low-resource language pairs. Inspired by the prompt-based method, we propose a novel approach called prompt-enhanced pseudo-dynamic smoothing (PEPDS). This method leverages prompts to optimize the attention mechanism and enhance the model\u2019s learning capacity during the training process. Our approach provides additional contextual information through the use of prompts and enhances the model\u2019s ability to handle long-distance dependencies and complex grammatical structures. The PEPDS framework utilize linguistic insights to create effective contextual cues. We focus on four parts of speech in English sentences: nouns, adjectives, adverbs and verbs, to generate prompts that enrich the contextual information available to the model. This method can be viewed as a form of inside knowledge enhancement, particularly beneficial for low-resource scenarios and long sentences. We apply the prompt method during the inference phase, further enhancing the model\u2019s translation performance. We evaluate PEPDS across multiple language pairs, demonstrating significant improvements in translation quality, especially for low-resource language pairs and complex sentences. Experimental results, attention pattern studies and translation case studies all demonstrate the effectiveness of our method. <\/jats:p>","DOI":"10.1142\/s0219691325500158","type":"journal-article","created":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T05:07:12Z","timestamp":1745644032000},"source":"Crossref","is-referenced-by-count":0,"title":["A pseudo-dynamic smoothing approach for low-resource neural machine translation using prompts"],"prefix":"10.1142","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8166-4406","authenticated-orcid":false,"given":"Shangjing","family":"Dai","sequence":"first","affiliation":[{"name":"School of Computer, Electronics and Information, Guangxi University, Nanning 530004, P. R. China"},{"name":"Guangxi Key Laboratory of Multimedia Communications and Network Technology, Guangxi University, Nanning 530004, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2704-1914","authenticated-orcid":false,"given":"Lina","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer, Electronics and Information, Guangxi University, Nanning 530004, P. R. China"},{"name":"Guangxi Key Laboratory of Multimedia Communications and Network Technology, Guangxi University, Nanning 530004, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1222-1249","authenticated-orcid":false,"given":"Bingzhen","family":"Wang","sequence":"additional","affiliation":[{"name":"Guangxi Key Laboratory of Multimedia Communications and Network Technology, Guangxi University, Nanning 530004, P. R. China"},{"name":"School of Electrical Engineering, Guangxi University, Nanning 530004, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2838-2058","authenticated-orcid":false,"given":"Thomas","family":"Wu","sequence":"additional","affiliation":[{"name":"Guangxi Key Laboratory of Multimedia Communications and Network Technology, Guangxi University, Nanning 530004, P. R. China"},{"name":"School of Electrical Engineering, Guangxi University, Nanning 530004, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4449-377X","authenticated-orcid":false,"given":"Jing","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer, Electronics and Information, Guangxi University, Nanning 530004, P. R. China"},{"name":"Guangxi Key Laboratory of Multimedia Communications and Network Technology, Guangxi University, Nanning 530004, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6887-130X","authenticated-orcid":false,"given":"Yuan Yan","family":"Tang","sequence":"additional","affiliation":[{"name":"Faculty of Science and Technology, University of Macau, Macau 999078, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2025,5,28]]},"reference":[{"journal-title":"Comput. Sci.","year":"2014","author":"Bahdanau D.","key":"S0219691325500158BIB003"},{"key":"S0219691325500158BIB005","first-page":"7057","volume":"32","author":"Conneau A.","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"S0219691325500158BIB009","doi-asserted-by":"publisher","DOI":"10.1007\/s10439-023-03272-4"},{"key":"S0219691325500158BIB010","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"first-page":"1700","volume-title":"Proc. 2013 Conf. Empirical Methods in Natural Language Processing","author":"Kalchbrenner N.","key":"S0219691325500158BIB012"},{"key":"S0219691325500158BIB013","doi-asserted-by":"publisher","DOI":"10.3390\/s20092464"},{"issue":"2","key":"S0219691325500158BIB015","first-page":"1097","volume":"25","author":"Krizhevsky A.","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"S0219691325500158BIB016","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"first-page":"2579","volume-title":"Findings of the Association for Computational Linguistics: ACL 2022","author":"Li Y.","key":"S0219691325500158BIB017"},{"key":"S0219691325500158BIB018","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"S0219691325500158BIB019","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00343"},{"key":"S0219691325500158BIB020","doi-asserted-by":"publisher","DOI":"10.1145\/1380584.1380586"},{"first-page":"311","volume-title":"Proc. of the 40th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Papineni K.","key":"S0219691325500158BIB022"},{"key":"S0219691325500158BIB023","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"issue":"140","key":"S0219691325500158BIB025","first-page":"1","volume":"21","author":"Raffel C.","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"S0219691325500158BIB026","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26585"},{"key":"S0219691325500158BIB027","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.213"},{"key":"S0219691325500158BIB028","doi-asserted-by":"crossref","unstructured":"B. Romera-Paredes and  P. H. S. Torr,  An Embarrassingly Simple Approach to Zero-Shot Learning, Visual Attributes, eds.   R. S. Feris,  C. Lampert and  D. Parikh  (Springer International Publishing,  Cham,  2017),  pp. 11\u201330.","DOI":"10.1007\/978-3-319-50077-5_2"},{"key":"S0219691325500158BIB029","first-page":"89","volume":"44","author":"Schjoldager A. G.","year":"2010","journal-title":"Hermes"},{"key":"S0219691325500158BIB031","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"S0219691325500158BIB034","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00492-0"},{"key":"S0219691325500158BIB035","first-page":"3104","volume":"27","author":"Sutskever I.","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"first-page":"192","volume-title":"Proc. 18th Int. Conf. on Spoken Language Translation (IWSLT 2021)","author":"Wu X.","key":"S0219691325500158BIB038"},{"volume-title":"Paper presented at 5th Int. Conf. on Learning Representations, ICLR 2017","year":"2017","author":"Xie Z.","key":"S0219691325500158BIB039"},{"first-page":"523","volume-title":"Proc. of the 39th Annual Meeting of the Association for Computational Linguistics","author":"Yamada K.","key":"S0219691325500158BIB040"},{"issue":"01","key":"S0219691325500158BIB041","first-page":"387","volume":"33","author":"Yang B.","year":"2019","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"first-page":"4495","volume-title":"Proc. 28th Int. Conf. on Computational Linguistics","author":"Zhao Y.","key":"S0219691325500158BIB043"},{"first-page":"16619","volume-title":"Proc. 2024 Joint Int. Conf. on Computational Linguistics, Language Resources and Evaluation (LRECCOLING 2024))","author":"Zhu S.","key":"S0219691325500158BIB044"}],"container-title":["International Journal of Wavelets, Multiresolution and Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0219691325500158","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T09:09:57Z","timestamp":1750842597000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S0219691325500158"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,28]]},"references-count":28,"journal-issue":{"issue":"04","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["10.1142\/S0219691325500158"],"URL":"https:\/\/doi.org\/10.1142\/s0219691325500158","relation":{},"ISSN":["0219-6913","1793-690X"],"issn-type":[{"type":"print","value":"0219-6913"},{"type":"electronic","value":"1793-690X"}],"subject":[],"published":{"date-parts":[[2025,5,28]]},"article-number":"2550015"}}