{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T05:51:07Z","timestamp":1757310667772,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":50,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789811979590"},{"type":"electronic","value":"9789811979606"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-981-19-7960-6_10","type":"book-chapter","created":{"date-parts":[[2022,12,8]],"date-time":"2022-12-08T13:06:07Z","timestamp":1670504767000},"page":"93-105","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A Multi-tasking and\u00a0Multi-stage Chinese Minority Pre-trained Language Model"],"prefix":"10.1007","author":[{"given":"Bin","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixuan","family":"Weng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shutao","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,12,9]]},"reference":[{"key":"10_CR1","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1016\/j.aiopen.2021.08.002","volume":"2","author":"X Han","year":"2021","unstructured":"Han, X., et al.: Pre-trained models: past, present and future. AI Open 2, 225\u2013250 (2021)","journal-title":"AI Open"},{"key":"10_CR2","doi-asserted-by":"publisher","first-page":"4037","DOI":"10.1109\/TPAMI.2020.2992393","volume":"43","author":"L Jing","year":"2021","unstructured":"Jing, L., Tian, Y.: Self-supervised visual feature learning with deep neural networks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 43, 4037\u20134058 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10_CR3","unstructured":"Radford, A., Narasimhan, K.: Improving language understanding by generative pre-training (2018)"},{"key":"10_CR4","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: North American Chapter of the Association for Computational Linguistics (2018)"},{"key":"10_CR5","unstructured":"Li, B., Weng, Y., Xia, F., Deng, H.: Towards better Chinese-centric neural machine translation for low-resource languages. arXiv preprint arXiv:2204.04344 (2022)"},{"key":"10_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3406095","volume":"53","author":"R Dabre","year":"2019","unstructured":"Dabre, R., Chu, C., Kunchukuttan, A.: A survey of multilingual neural machine translation. ACM Comput. Surv. 53, 1\u201338 (2019)","journal-title":"ACM Comput. Surv."},{"issue":"1","key":"10_CR7","first-page":"80","volume":"4","author":"X Zuo","year":"2007","unstructured":"Zuo, X.: China\u2019s policy towards minority languages in a globalising age. TCI (Transnatl. Curric. Inq.) 4(1), 80\u201391 (2007)","journal-title":"TCI (Transnatl. Curric. Inq.)"},{"key":"10_CR8","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1021\/cr300014x","volume":"112","author":"H-C Zhou","year":"2012","unstructured":"Zhou, H.-C., Long, J.R., Yaghi, O.M.: Introduction to metal-organic frameworks. Chem. Rev. 112, 673\u2013674 (2012)","journal-title":"Chem. Rev."},{"issue":"3","key":"10_CR9","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/BF02436131","volume":"21","author":"I Attan\u00e9","year":"2000","unstructured":"Attan\u00e9, I., Courbage, Y.: Transitional stages and identity boundaries: the case of ethnic minorities in china. Popul. Environ. 21(3), 257\u2013280 (2000)","journal-title":"Popul. Environ."},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Meeting of the Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"10_CR11","unstructured":"Shao, Y., et al.: CPT: a pre-trained unbalanced transformer for both Chinese language understanding and generation. arXiv, Computation and Language (2021)"},{"key":"10_CR12","first-page":"415","volume":"30","author":"WL Taylor","year":"1953","unstructured":"Taylor, W.L.: Cloze procedure: a new tool for measuring readability. J. Mass Commun. Q. 30, 415\u2013433 (1953)","journal-title":"J. Mass Commun. Q."},{"key":"10_CR13","unstructured":"Wang, H., Ma, S., Dong, L., Huang, S., Zhang, D., Wei, F.: DeepNet: scaling transformers to 1,000 layers (2022)"},{"key":"10_CR14","unstructured":"Clark, K., Luong, M.-T., Le, Q.V., Manning, C.D.: ELECTRA: pre-training text encoders as discriminators rather than generators. Learning (2020)"},{"key":"10_CR15","unstructured":"He, P., Gao, J., Chen, W.: DeBERTaV 3: improving DeBERTa using ELECTRA-style pre-training with gradient-disentangled embedding sharing. arxiv, Computation and Language (2021)"},{"key":"10_CR16","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv e-prints (2019)"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Conneau, A., et al.: Unsupervised cross-lingual representation learning at scale. In: Meeting of the Association for Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"10_CR18","unstructured":"Wenzek, G., et al.: CCNet: extracting high quality monolingual datasets from web crawl data. In: Language Resources and Evaluation (2019)"},{"key":"10_CR19","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1162\/tacl_a_00343","volume":"8","author":"Y Liu","year":"2020","unstructured":"Liu, Y., et al.: Multilingual denoising pre-training for neural machine translation. Trans. Assoc. Comput. Linguist. 8, 726\u2013742 (2020)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10_CR20","unstructured":"Fan, A., et al.: Beyond English-centric multilingual machine translation. arxiv, Computation and Language (2020)"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.-J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, Philadelphia, Pennsylvania, USA, pp. 311\u2013318. Association for Computational Linguistics, July 2002","DOI":"10.3115\/1073083.1073135"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Luo, F., et al.: VECO: variable and flexible cross-lingual pre-training for language understanding and generation. In: Meeting of the Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.acl-long.308"},{"key":"10_CR23","unstructured":"Chaudhari, S., Polatkan, G., Ramanath, R., Mithal, V.: An attentive survey of attention models. arxiv, Learning (2019)"},{"key":"10_CR24","unstructured":"Song, Z., et al.: switch-GLAT: multilingual parallel machine translation via code-switch decoder. In: International Conference on Learning Representations (2021)"},{"key":"10_CR25","unstructured":"Yang, Z., et al.: CINO: a Chinese minority pre-trained language model (2022)"},{"key":"10_CR26","unstructured":"Lample, G., Conneau, A.: Cross-lingual language model pretraining. In: Advances in Neural Information Processing Systems (2019)"},{"key":"10_CR27","unstructured":"Dong, L., et al.: Unified language model pre-training for natural language understanding and generation. In: Advances in Neural Information Processing Systems (2019)"},{"key":"10_CR28","unstructured":"Bao, H., et al.: Unilmv2: pseudo-masked language models for unified language model pre-training. In: International Conference on Machine Learning (2020)"},{"key":"10_CR29","unstructured":"Du, Z., et al.: All NLP tasks are generation tasks: a general pretraining framework. arXiv, Computation and Language (2021)"},{"key":"10_CR30","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS 2017, Red Hook, NY, USA, pp. 6000\u20136010. Curran Associates Inc. (2017)"},{"key":"10_CR31","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: 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, Volume 1 (Long and Short Papers), Minneapolis, Minnesota, pp. 4171\u20134186. Association for Computational Linguistics, June 2019"},{"key":"10_CR32","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1007\/978-3-319-69005-6_39","volume-title":"Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data","author":"N Qun","year":"2017","unstructured":"Qun, N., Li, X., Qiu, X., Huang, X.: End-to-end neural text classification for Tibetan. In: Sun, M., Wang, X., Chang, B., Xiong, D. (eds.) CCL\/NLP-NABD -2017. LNCS (LNAI), vol. 10565, pp. 472\u2013480. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-69005-6_39"},{"key":"10_CR33","unstructured":"Xu, L., et al.: CLUE: a Chinese language understanding evaluation benchmark. In: Proceedings of the 28th International Conference on Computational Linguistics, Barcelona, Spain (Online), pp. 4762\u20134772. International Committee on Computational Linguistics, December 2020"},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Hu, B., Chen, Q., Zhu, F.: LCSTS: a large scale Chinese short text summarization dataset. In: Empirical Methods in Natural Language Processing (2015)","DOI":"10.18653\/v1\/D15-1229"},{"key":"10_CR35","unstructured":"Barrault, L., et al.: Findings of the 2020 Conference on Machine Translation (WMT20). In: Empirical Methods in Natural Language Processing (2020)"},{"key":"10_CR36","unstructured":"Bajaj, P., et al.: MS MARCO: a human generated machine reading comprehension dataset. arXiv, Computation and Language (2016)"},{"key":"10_CR37","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1162\/tacl_a_00276","volume":"7","author":"T Kwiatkowski","year":"2019","unstructured":"Kwiatkowski, T., et al.: Natural questions: a benchmark for question answering research. Trans. Assoc. Comput. Linguist. 7, 453\u2013466 (2019)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10_CR38","doi-asserted-by":"crossref","unstructured":"Li, M., Zhang, T., Chen, Y., Smola, A.J.: Efficient mini-batch training for stochastic optimization. In: Knowledge Discovery and Data Mining (2014)","DOI":"10.1145\/2623330.2623612"},{"key":"10_CR39","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1007\/978-981-33-6162-1_6","volume-title":"Machine Translation","author":"C Chen","year":"2020","unstructured":"Chen, C., Zong, Q., Luo, Q., Qiu, B., Li, M.: Transformer-based unified neural network for quality estimation and transformer-based re-decoding model for machine translation. In: Li, J., Way, A. (eds.) CCMT 2020. CCIS, vol. 1328, pp. 66\u201375. Springer, Singapore (2020). https:\/\/doi.org\/10.1007\/978-981-33-6162-1_6"},{"key":"10_CR40","unstructured":"Tay, Y., et al.: Scale efficiently: insights from pre-training and fine-tuning transformers. arXiv, Computation and Language (2021)"},{"key":"10_CR41","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: International Conference on Artificial Intelligence and Statistics (2010)"},{"key":"10_CR42","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1162\/tacl_a_00300","volume":"8","author":"M Joshi","year":"2020","unstructured":"Joshi, M., Chen, D., Liu, Y., Weld, D.S., Zettlemoyer, L., Levy, O.: SpanBERT: improving pre-training by representing and predicting spans. Trans. Assoc. Comput. Linguist. 8, 64\u201377 (2020)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10_CR43","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32. Curran Associates Inc. (2019)"},{"key":"10_CR44","unstructured":"Wolf, T., et al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38\u201345. Association for Computational Linguistics, October 2020"},{"key":"10_CR45","doi-asserted-by":"crossref","unstructured":"Rajbhandari, S., Rasley, J., Ruwase, O., He, Y.: Zero: memory optimizations toward training trillion parameter models. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2020. IEEE Press (2020)","DOI":"10.1109\/SC41405.2020.00024"},{"key":"10_CR46","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2018)"},{"key":"10_CR47","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"10_CR48","unstructured":"Lin, C.-Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, Barcelona, Spain, pp. 74\u201381. Association for Computational Linguistics, July 2004"},{"key":"10_CR49","doi-asserted-by":"crossref","unstructured":"Denkowski, M., Lavie, A.: Meteor universal: language specific translation evaluation for any target language. In: Proceedings of the Ninth Workshop on Statistical Machine Translation, Baltimore, Maryland, USA, pp. 376\u2013380. Association for Computational Linguistics June 2014","DOI":"10.3115\/v1\/W14-3348"},{"key":"10_CR50","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: CIDEr: consensus-based image description evaluation. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"}],"container-title":["Communications in Computer and Information Science","Machine Translation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-19-7960-6_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,8]],"date-time":"2022-12-08T13:08:02Z","timestamp":1670504882000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-19-7960-6_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9789811979590","9789811979606"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-981-19-7960-6_10","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"9 December 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCMT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China Conference on Machine Translation","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lhasa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccmt2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/sc.cipsc.org.cn\/mt\/conference\/2022\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Softconf","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"73","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"16","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"22% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}