{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T03:46:57Z","timestamp":1781927217328,"version":"3.54.5"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T00:00:00Z","timestamp":1717113600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T00:00:00Z","timestamp":1717113600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R &D Program of China","doi-asserted-by":"crossref","award":["2020AAA0106502"],"award-info":[{"award-number":["2020AAA0106502"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276078"],"award-info":[{"award-number":["62276078"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key R &D Program of Heilongjiang","award":["2022ZX01A32"],"award-info":[{"award-number":["2022ZX01A32"]}]},{"DOI":"10.13039\/501100012166","name":"National Key R &D Program of China","doi-asserted-by":"crossref","award":["2020AAA0106502"],"award-info":[{"award-number":["2020AAA0106502"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012166","name":"National Key R &D Program of China","doi-asserted-by":"crossref","award":["2020AAA0106502"],"award-info":[{"award-number":["2020AAA0106502"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012166","name":"National Key R &D Program of China","doi-asserted-by":"crossref","award":["62276078"],"award-info":[{"award-number":["62276078"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012166","name":"National Key R &D Program of China","doi-asserted-by":"crossref","award":["62276078"],"award-info":[{"award-number":["62276078"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Key R &D Program of Heilongjiang","award":["2022ZX01A32"],"award-info":[{"award-number":["2022ZX01A32"]}]},{"name":"Key R &D Program of Heilongjiang","award":["2022ZX01A32"],"award-info":[{"award-number":["2022ZX01A32"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1007\/s13042-024-02132-4","type":"journal-article","created":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T06:01:53Z","timestamp":1717135313000},"page":"3989-3998","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Pretraining without wordpieces: learning over a vocabulary of millions of words"],"prefix":"10.1007","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5909-1339","authenticated-orcid":false,"given":"Zhangyin","family":"Feng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Duyu","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaocheng","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cong","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junwei","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuangzhi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunbo","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuming","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,5,31]]},"reference":[{"issue":"Feb","key":"2132_CR1","first-page":"1137","volume":"3","author":"Y Bengio","year":"2003","unstructured":"Bengio Y, Ducharme R, Vincent P et al (2003) A neural probabilistic language model. J Mach Learn Res 3(Feb):1137\u20131155","journal-title":"J Mach Learn Res"},{"key":"2132_CR2","unstructured":"Bommasani R, Hudson DA, Adeli E et\u00a0al (2021) On the opportunities and risks of foundation models. arXiv preprint. arXiv:2108.07258"},{"key":"2132_CR3","unstructured":"Brown TB, Mann B, Ryder N et al (2020) Language models are few-shot learners. In: Proceeding of the 2020 advances in neural information processing systems, vol 33. Curran Associates, Inc., pp 1877\u20131901. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"2132_CR4","doi-asserted-by":"crossref","unstructured":"Cui Y, Che W, Liu T et al (2021) Pre-training with whole word masking for Chinese BERT. In: Proceedings of IEEE\/ACM transactions on audio, speech, and language processing, vol 29. pp 3504\u20133514. https:\/\/ieeexplore.ieee.org\/document\/9599397","DOI":"10.1109\/TASLP.2021.3124365"},{"key":"2132_CR5","unstructured":"Devlin J, Chang M, Lee K et al (2019) BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, vol 1 (long and short papers),. Association for Computational Linguistics, Minneapolis, Minnesota, pp 4171\u20134186. https:\/\/aclanthology.org\/N19-1423"},{"issue":"8","key":"2132_CR6","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"2132_CR7","doi-asserted-by":"publisher","unstructured":"Lewis M, Liu Y, Goyal N et\u00a0al (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. Association for Computational Linguistics, Online, pp 7871\u20137880. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.703. https:\/\/aclanthology.org\/2020.acl-main.703","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"2132_CR8","doi-asserted-by":"crossref","unstructured":"Li L, Dai Y, Tang D et al (2023) Markbert: marking word boundaries improves Chinese BERT. In: Proceedings of natural language processing and Chinese computing. NLPCC 2023. Lecture notes in computer science, vol 14302. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-031-44693-1_26","DOI":"10.1007\/978-3-031-44693-1_26"},{"key":"2132_CR9","unstructured":"Lieber O, Sharir O, Lenz B et\u00a0al (2021) Jurassic-1: technical details and evaluation. White Paper AI21 Labs"},{"key":"2132_CR10","unstructured":"Liu Y, Ott M, Goyal N et\u00a0al (2019) Roberta: a robustly optimized BERT pretraining approach. arXiv preprint. arXiv:1907.11692"},{"key":"2132_CR11","unstructured":"Mikolov T, Chen K, Corrado G et al (2013) Efficient estimation of word representations in vector space. In: Proceedings of international conference on learning representations. ICLR Workshop Track 2013, Scottsdale, AZ, USA. https:\/\/openreview.net\/forum?id=idpCdOWtqXd60"},{"key":"2132_CR12","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning C (2014) Glove: global vectors for word representation. In: Proceedings of the conference on empirical methods in natural language processing. Association for Computational Linguistics, Doha, Qatar, pp 1532\u20131543","DOI":"10.3115\/v1\/D14-1162"},{"key":"2132_CR13","doi-asserted-by":"publisher","unstructured":"Peters ME, Neumann M, Iyyer M et\u00a0al (2018) Deep contextualized word representations. In: Proceedings of the 2018 conference of the North American chapter of the association for computational linguistics: human language technologies, vol 1 (Long Papers). Association for Computational Linguistics, New Orleans, pp 2227\u20132237. https:\/\/doi.org\/10.18653\/v1\/N18-1202. https:\/\/aclanthology.org\/N18-1202","DOI":"10.18653\/v1\/N18-1202"},{"key":"2132_CR14","doi-asserted-by":"crossref","unstructured":"Rajpurkar P, Zhang J, Lopyrev K et al (2016) Squad: 100,000+ questions for machine comprehension of text. In: Proceedings of the 2016 conference on empirical methods in natural language processing. Association for Computational Linguistics, Austin, Texas, pp 2383\u20132392. https:\/\/aclanthology.org\/D16-1264","DOI":"10.18653\/v1\/D16-1264"},{"key":"2132_CR15","doi-asserted-by":"publisher","unstructured":"Rajpurkar P, Jia R, Liang P (2018) Know what you don\u2019t know: unanswerable questions for SQuAD. In: Proceedings of the 56th annual meeting of the association for computational linguistics (volume 2: short papers). Association for Computational Linguistics, Melbourne, pp 784\u2013789. https:\/\/doi.org\/10.18653\/v1\/P18-2124. https:\/\/aclanthology.org\/P18-2124","DOI":"10.18653\/v1\/P18-2124"},{"key":"2132_CR16","unstructured":"Sang EF, De\u00a0Meulder F (2003) Introduction to the CoNLL-2003 shared task: language-independent named entity recognition. arXiv preprint. arXiv:cs\/0306050"},{"key":"2132_CR17","unstructured":"Su J (2020) WoBERT: word-based Chinese BERT model-ZhuiyiAI. Technical report. https:\/\/github.com\/ZhuiyiTechnology\/WoBERT"},{"issue":"4","key":"2132_CR18","first-page":"415","volume":"30","author":"WL Taylor","year":"1953","unstructured":"Taylor WL (1953) \u201ccloze procedure\u2019\u2019: a new tool for measuring readability. J Q 30(4):415\u2013433","journal-title":"J Q"},{"key":"2132_CR19","unstructured":"Vaswani A, Shazeer N, Parmar N et al (2017) Attention is all you need. In: Advances in neural information processing systems. Curran Associates, Inc., pp 5998\u20136008.  https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"2132_CR20","doi-asserted-by":"crossref","unstructured":"Wang Z, Shang J, Liu L et al (2019) CrossWeigh: training named entity tagger from imperfect annotations. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), Association for Computational Linguistics, Hong Kong, China, pp 5154\u20135163. https:\/\/aclanthology.org\/D19-1519","DOI":"10.18653\/v1\/D19-1519"},{"key":"2132_CR21","unstructured":"Wu Y, Schuster M, Chen Z et\u00a0al (2016) Google\u2019s neural machine translation system: bridging the gap between human and machine translation. arXiv preprint. arXiv:1609.08144"},{"key":"2132_CR22","doi-asserted-by":"publisher","unstructured":"Xie Q, Lai G, Dai Z et\u00a0al (2018) Large-scale cloze test dataset created by teachers. In: Proceedings of the 2018 conference on empirical methods in natural language processing. Association for Computational Linguistics, Brussels, pp 2344\u20132356. https:\/\/doi.org\/10.18653\/v1\/D18-1257. https:\/\/aclanthology.org\/D18-1257","DOI":"10.18653\/v1\/D18-1257"},{"key":"2132_CR23","doi-asserted-by":"crossref","unstructured":"Xu J, Zhou H, Gan C et al (2021) Vocabulary learning via optimal transport for neural machine translation. In: Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing (volume 1: long papers). Association for Computational Linguistics, Online. pp 7361\u20137373","DOI":"10.18653\/v1\/2021.acl-long.571"},{"key":"2132_CR24","doi-asserted-by":"crossref","unstructured":"Xu L, Hu H, Zhang X et al (2020) CLUE: a Chinese language understanding evaluation benchmark. In: Proceedings of the 28th international conference on computational linguistics, International Committee on Computational Linguistics, Barcelona, Spain (Online), pp 4762\u20134772. https:\/\/aclanthology.org\/2020.coling-main.419","DOI":"10.18653\/v1\/2020.coling-main.419"},{"key":"2132_CR25","doi-asserted-by":"publisher","unstructured":"Yuan S, Zhao H, Du Z et al (2021) WuDaoCorpora: a super large-scale Chinese corpora for pre-training language models. AI Open 2:65\u201368. https:\/\/doi.org\/10.1016\/j.aiopen.2021.06.001. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S2666651021000152","DOI":"10.1016\/j.aiopen.2021.06.001"},{"key":"2132_CR26","doi-asserted-by":"crossref","unstructured":"Zhu Y, Kiros R, Zemel R et al (2015) Aligning books and movies: towards story-like visual explanations by watching movies and reading books. In: Proceedings of the IEEE international conference on computer vision. Institute of Electrical and Electronics Engineers (IEEE), Santiago, Chile,  pp 19\u201327","DOI":"10.1109\/ICCV.2015.11"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-024-02132-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-024-02132-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-024-02132-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,17]],"date-time":"2024-08-17T08:33:19Z","timestamp":1723883599000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-024-02132-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,31]]},"references-count":26,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["2132"],"URL":"https:\/\/doi.org\/10.1007\/s13042-024-02132-4","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,31]]},"assertion":[{"value":"29 April 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 March 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 May 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No potential conflict of interest was reported by the author(s).","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}