{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:34:23Z","timestamp":1763202863303,"version":"3.37.3"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"17-18","license":[{"start":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T00:00:00Z","timestamp":1718668800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T00:00:00Z","timestamp":1718668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976015","61976016","61876198","61370130"],"award-info":[{"award-number":["61976015","61976016","61876198","61370130"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376019"],"award-info":[{"award-number":["62376019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1007\/s10489-024-05586-9","type":"journal-article","created":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T07:03:26Z","timestamp":1718694206000},"page":"7958-7968","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Curriculum pre-training for stylized neural machine translation"],"prefix":"10.1007","volume":"54","author":[{"given":"Aixiao","family":"Zou","sequence":"first","affiliation":[]},{"given":"Xuanxuan","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Xinjie","family":"Li","sequence":"additional","affiliation":[]},{"given":"Ting","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Fuwei","family":"Cui","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0170-626X","authenticated-orcid":false,"given":"Jinan","family":"Xu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,6,18]]},"reference":[{"key":"5586_CR1","unstructured":"Cohn T, Lapata M (2007) Machine translation by triangulation: making effective use of multi-parallel corpora. In: Proceedings of the 45th annual meeting of the association of computational linguistics, pp 728\u2013735"},{"key":"5586_CR2","doi-asserted-by":"publisher","unstructured":"Chen Y, Liu Y, Cheng Y, Li VOK (2017) A teacher-student framework for zero-resource neural machine translation. In: Proceedings of the 55th annual meeting of the association for computational linguistics, vol 1 pp 1925-1935. https:\/\/doi.org\/10.18653\/v1\/P17-1176","DOI":"10.18653\/v1\/P17-1176"},{"key":"5586_CR3","doi-asserted-by":"publisher","unstructured":"Yang J, Wang M, Zhou H, Zhao C, Zhang W, Yu Y, Li L (2020) Towards making the most of bert in neural machine translation. In: Proceedings of the AAAI conference on artificial intelligence, vol 34 pp 9378\u20139385. https:\/\/doi.org\/10.1609\/aaai.v34i05.6479","DOI":"10.1609\/aaai.v34i05.6479"},{"key":"5586_CR4","unstructured":"Zhu J, Xia Y, Wu L, He D, Qin T, Zhou W, Li H, Liu T (2020) Incorporating BERT into neural machine translation. International conference on learning representations"},{"key":"5586_CR5","doi-asserted-by":"crossref","unstructured":"Wu Y, Wang Y, Liu S (2020) A dataset for low-resource stylized sequence-to-sequence generation. In: Proceedings of the AAAI conference on artificial intelligence vol 34, pp 9290\u20139297","DOI":"10.1609\/aaai.v34i05.6468"},{"key":"5586_CR6","unstructured":"Niu X, Rao S, Carpuat M (2018) Multi-task neural models for translating between styles within and across languages. In: Proceedings of the 27th international conference on computational linguistics, pp 1008\u20131021"},{"key":"5586_CR7","doi-asserted-by":"crossref","unstructured":"Niu X, Carpuat M (2020) Controlling neural machine translation formality with synthetic supervision. In: Proceedings of the AAAI conference on artificial intelligence, vol 34 pp 8568\u20138575","DOI":"10.1609\/aaai.v34i05.6379"},{"key":"5586_CR8","doi-asserted-by":"publisher","unstructured":"Wu X, Liu J, Li X, Xu J, Chen Y, Zhang Y, Huang H (2021) Improving stylized neural machine translation with iterative dual knowledge transfer. In: Proceedings of the thirtieth international joint conference on artificial intelligence, pp 3971-3977. https:\/\/doi.org\/10.24963\/ijcai.2021\/547","DOI":"10.24963\/ijcai.2021\/547"},{"key":"5586_CR9","doi-asserted-by":"publisher","unstructured":"Li J, Jia R, He H, Liang P (2018) Delete, retrieve, generate: a simple approach to sentiment and style transfer. In: Proceedings of the 2018 conference of the north american chapter of the association for computational linguistics: human language technologies, pp 1865\u20131874. https:\/\/doi.org\/10.18653\/v1\/N18-1169","DOI":"10.18653\/v1\/N18-1169"},{"key":"5586_CR10","doi-asserted-by":"publisher","unstructured":"Sudhakar A, Upadhyay B, Maheswaran A (2019) Transforming delete, retrieve, generate approach for controlled text style transfer. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing, pp 3269-3279. https:\/\/doi.org\/10.18653\/v1\/D19-1322","DOI":"10.18653\/v1\/D19-1322"},{"key":"5586_CR11","first-page":"7298","volume":"31","author":"Z Yang","year":"2018","unstructured":"Yang Z, Hu Z, Dyer C, Xing EP, Berg-Kirkpatrick T (2018) Unsupervised text style transfer using language models as discriminators. Adv Neural Inf Process Syst 31:7298\u20137309","journal-title":"Adv Neural Inf Process Syst"},{"key":"5586_CR12","first-page":"11034","volume":"32","author":"Ke Wang","year":"2019","unstructured":"Wang Ke, Hua Hang, Wan Xiaojun (2019) Controllable unsupervised text attribute transfer via editing entangled latent representation. Adv Neural Inf Process Syst 32:11034\u201311044","journal-title":"Adv Neural Inf Process Syst"},{"key":"5586_CR13","doi-asserted-by":"crossref","unstructured":"Fu Z, Tan X, Peng N, Zhao D, Yan R (2018) Style transfer in text: exploration and evaluation. In: Proceedings of the AAAI conference on artificial intelligence, vol 32 pp 663\u2013670","DOI":"10.1609\/aaai.v32i1.11330"},{"key":"5586_CR14","doi-asserted-by":"publisher","unstructured":"Rao S, Tetreault J (2018) Dear sir or madam, may i introduce the gyafc dataset: corpus, benchmarks and metrics for formality style transfer. In: Proceedings of the 2018 conference of the North American chapter of the association for computational linguistics: human language technologies, pp 129\u2013140 https:\/\/doi.org\/10.18653\/v1\/N18-1012","DOI":"10.18653\/v1\/N18-1012"},{"key":"5586_CR15","doi-asserted-by":"publisher","unstructured":"Wang Y, Wu Y, Mou L, Li Z, Chao W (2019) Harnessing pre-trained neural networks with rules for formality style transfer. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing, pp 3573\u20133578. https:\/\/doi.org\/10.18653\/v1\/D19-1365","DOI":"10.18653\/v1\/D19-1365"},{"key":"5586_CR16","doi-asserted-by":"publisher","unstructured":"Chawla K, Yang D (2020) Semi-supervised formality style transfer using language model discriminator and mutual information maximization. In: Findings of the association for computational linguistics: EMNLP 2020, pp 2340-2354. https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.212","DOI":"10.18653\/v1\/2020.findings-emnlp.212"},{"key":"5586_CR17","doi-asserted-by":"publisher","unstructured":"Zhang Y, Ge T, Sun X (2020) Parallel data augmentation for formality style transfer. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp 3221-3228. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.294","DOI":"10.18653\/v1\/2020.acl-main.294"},{"key":"5586_CR18","doi-asserted-by":"crossref","unstructured":"Bengio Y, Louradour J, Collobert R, Weston J (2009) Curriculum learning. In: Proceedings of the 26th annual international conference on machine learning, pp 41-48","DOI":"10.1145\/1553374.1553380"},{"issue":"9","key":"5586_CR19","doi-asserted-by":"publisher","first-page":"4555","DOI":"10.1109\/TPAMI.2021.3069908","volume":"44","author":"X Wang","year":"2022","unstructured":"Wang X, Chen Y, Zhu W (2022) A survey on curriculum learning. IEEE Trans Pattern Anal Mach Intell 44(9):4555\u20134576. https:\/\/doi.org\/10.1109\/TPAMI.2021.3069908","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5586_CR20","doi-asserted-by":"publisher","unstructured":"Zhang X, Shapiro P, Kumar G, McNamee P, Carpuat M, Duh K (2019) Curriculum learning for domain adaptation in neural machine translation. Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, vol 1, pp 1903\u20131915. https:\/\/doi.org\/10.18653\/v1\/N19-1189","DOI":"10.18653\/v1\/N19-1189"},{"key":"5586_CR21","doi-asserted-by":"publisher","unstructured":"Wang W, Tian Y, Ngiam J, Yang Y, Caswell I, Parekh Z (2020) Learning a multi-domain curriculum for neural machine translation. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp 7711-7723. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.689","DOI":"10.18653\/v1\/2020.acl-main.689"},{"key":"5586_CR22","doi-asserted-by":"publisher","unstructured":"Wang C, Wu Y, Liu S, Zhou M, Yang Z (2020) Curriculum pre-training for end-to-end speech translation. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp 3728-3738. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.344","DOI":"10.18653\/v1\/2020.acl-main.344"},{"key":"5586_CR23","doi-asserted-by":"publisher","unstructured":"Kenton J, Devlin M-WC, Toutanova LK (2019) BERT: Pre-training of deep bidirectional transformers for language understandingg. In: Proceedings of the 2019 Conference of the North American Chapter of the association for computational linguistics: human language technologies, vol 1 pp 4171\u20134186. https:\/\/doi.org\/10.18653\/v1\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"5586_CR24","first-page":"7057","volume":"32","author":"A Conneau","year":"2019","unstructured":"Conneau A, Lample G (2019) Cross-lingual language model pretraining. Adv Neural Inf Process Sys 32:7057\u20137067","journal-title":"Adv Neural Inf Process Sys"},{"key":"5586_CR25","doi-asserted-by":"publisher","unstructured":"Lewis M, Liu Y, Goyal N, Ghazvininejad M, Mohamed A, Levy O, Stoyanov V, Zettlemoyer L (2020) BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 7871-7880. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.703","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"5586_CR26","doi-asserted-by":"publisher","unstructured":"Jawahar G, Sagot B, Seddah D (2019) What does BERT learn about the structure of language? In: Proceedings of the 57th annual meeting of the association for computational linguistics, pp 3651\u20133657. https:\/\/doi.org\/10.18653\/v1\/P19-1356","DOI":"10.18653\/v1\/P19-1356"},{"key":"5586_CR27","doi-asserted-by":"publisher","unstructured":"Papineni K, Roukos S, Ward T, Zhu W-J (2002) Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting of the association for computational linguistics, pp 311-318. https:\/\/doi.org\/10.3115\/1073083.1073135","DOI":"10.3115\/1073083.1073135"},{"key":"5586_CR28","doi-asserted-by":"publisher","first-page":"5998","DOI":"10.18653\/v1\/P16-1009","volume":"30","author":"Ashish Vaswani","year":"2017","unstructured":"Vaswani Ashish, Shazeer Noam, Parmar Niki, Uszkoreit Jakob, Jones Llion, Gomez Aidan N, Kaiser \u0141ukasz, Polosukhin Illia (2017) Attention is all you need. Adv Neural Inf Process Syst 30:5998\u20136008. https:\/\/doi.org\/10.18653\/v1\/P16-1009","journal-title":"Adv Neural Inf Process Syst"},{"key":"5586_CR29","doi-asserted-by":"publisher","unstructured":"Sennrich R, Haddow B, Birch A (2016) Neural machine translation of rare words with subword units. In: Proceedings of the 54th annual meeting of the association for computational linguistics, pp 1715\u20131725. https:\/\/doi.org\/10.18653\/v1\/P16-1162","DOI":"10.18653\/v1\/P16-1162"},{"key":"5586_CR30","unstructured":"Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: 3rd international conference on learning representations"},{"key":"5586_CR31","doi-asserted-by":"publisher","unstructured":"Sennrich R, Haddow B, Birch A (2016) Edinburgh neural machine translation systems for WMT 16. In: Proceedings of the first conference on machine translation: volume 2, association for computational linguistics, pp 371-376. https:\/\/doi.org\/10.18653\/v1\/w16-2323","DOI":"10.18653\/v1\/w16-2323"},{"key":"5586_CR32","doi-asserted-by":"crossref","unstructured":"Yiwei L, Tiange L, Jiacheng S, Todd H, Honglak L (2023) Fine-grained text style transfer with diffusion-based language models. In: Proceedings of the 8th workshop on representation learning for NLP, association for computational linguistics, pp 65\u201374. https:\/\/aclanthology.org\/2023.repl4nlp-1.6","DOI":"10.18653\/v1\/2023.repl4nlp-1.6"},{"key":"5586_CR33","doi-asserted-by":"publisher","unstructured":"Emily R, Daphne I, Ann Y, Andy C, Chris C-B, Jason W (2022) A recipe for arbitrary text style transfer with large language models. In: Proceedings of the 60th annual meeting of the association for computational linguistics (volume 2: short papers), 837-848. https:\/\/doi.org\/10.18653\/v1\/2022.acl-short.94","DOI":"10.18653\/v1\/2022.acl-short.94"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-05586-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-024-05586-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-05586-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T02:22:23Z","timestamp":1732242143000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-024-05586-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,18]]},"references-count":33,"journal-issue":{"issue":"17-18","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["5586"],"URL":"https:\/\/doi.org\/10.1007\/s10489-024-05586-9","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2024,6,18]]},"assertion":[{"value":"1 June 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 June 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}