{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T15:13:11Z","timestamp":1777734791051,"version":"3.51.4"},"reference-count":28,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2019,5,31]],"date-time":"2019-05-31T00:00:00Z","timestamp":1559260800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"State Key Program of National Science Foundation of China","award":["61836006"],"award-info":[{"award-number":["61836006"]}]},{"name":"National Natural Science Fund for Distinguished Young Scholar","award":["61625204"],"award-info":[{"award-number":["61625204"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Asian Low-Resour. Lang. Inf. Process."],"published-print":{"date-parts":[[2020,1,31]]},"abstract":"<jats:p>Ancient Chinese brings the wisdom and spirit culture of the Chinese nation. Automatic translation from ancient Chinese to modern Chinese helps to inherit and carry forward the quintessence of the ancients. However, the lack of large-scale parallel corpus limits the study of machine translation in ancient\u2013modern Chinese. In this article, we propose an ancient\u2013modern Chinese clause alignment approach based on the characteristics of these two languages. This method combines both lexical-based information and statistical-based information, which achieves 94.2 F1-score on our manual annotation Test set. We use this method to create a new large-scale ancient\u2013modern Chinese parallel corpus that contains 1.24M bilingual pairs. To our best knowledge, this is the first large high-quality ancient\u2013modern Chinese dataset. Furthermore, we analyzed and compared the performance of the SMT and various NMT models on this dataset and provided a strong baseline for this task.<\/jats:p>","DOI":"10.1145\/3325887","type":"journal-article","created":{"date-parts":[[2019,6,3]],"date-time":"2019-06-03T12:23:16Z","timestamp":1559564596000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Ancient\u2013Modern Chinese Translation with a New Large Training Dataset"],"prefix":"10.1145","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8755-8941","authenticated-orcid":false,"given":"Dayiheng","family":"Liu","sequence":"first","affiliation":[{"name":"College of Computer Science, State Key Laboratory of Hydraulics and Mountain River Engineering, Sichuan University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kexin","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Sichuan University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"Qu","sequence":"additional","affiliation":[{"name":"College of Computer Science, Sichuan University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiancheng","family":"Lv","sequence":"additional","affiliation":[{"name":"College of Computer Science, State Key Laboratory of Hydraulics and Mountain River Engineering, Sichuan University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,5,31]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E. Hinton","author":"Ba Jimmy Lei","year":"2016"},{"key":"e_1_2_1_2_1","volume-title":"Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473","author":"Bahdanau Dzmitry","year":"2014"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.3115\/981344.981366"},{"key":"e_1_2_1_4_1","volume-title":"Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio.","author":"Cho Kyunghyun","year":"2014"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3003726"},{"key":"e_1_2_1_6_1","volume-title":"Proceedings of the Conference and Workshop on Neural Information Processing Systems (NIPS\u201916)","author":"Gal Yarin","year":"2016"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/972450.972455"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_1_9_1","volume-title":"Proceedings of the 6th Workshop on Statistical Machine Translation.","author":"Heafield Kenneth","year":"2011"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.3115\/992133.992174"},{"key":"e_1_2_1_12_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2014"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1075\/ijcl.9.1.02kit"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/1557769.1557821"},{"key":"e_1_2_1_15_1","volume-title":"Modeling source syntax for neural machine translation. arXiv preprint arXiv:1705.01020","author":"Li Junhui","year":"2017"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-72586-2_164"},{"key":"e_1_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Ying Liu and Nan Wang. 2012. Sentence alignment for ancient and modern Chinese parallel corpus. In Emerging Research in Artificial Intelligence and Computational Intelligence.  Ying Liu and Nan Wang. 2012. Sentence alignment for ancient and modern Chinese parallel corpus. In Emerging Research in Artificial Intelligence and Computational Intelligence.","DOI":"10.1007\/978-3-642-34240-0_54"},{"key":"e_1_2_1_18_1","volume-title":"Manning","author":"Luong Minh-Thang","year":"2015"},{"key":"e_1_2_1_19_1","volume-title":"Proceedings of the Conference and Workshop on Neural Information Processing Systems (NIPS\u201913)","author":"Mnih Andriy","year":"2013"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3138815"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"e_1_2_1_23_1","volume-title":"Proceedings of the Conference and Workshop on Neural Information Processing Systems (NIPS\u201914)","author":"Sutskever Ilya"},{"key":"e_1_2_1_24_1","volume-title":"Proceedings of the Conference and Workshop on Neural Information Processing Systems (NIPS\u201917)","author":"Vaswani Ashish","year":"2017"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30586-6_43"},{"key":"e_1_2_1_26_1","unstructured":"Yonghui Wu Mike Schuster Zhifeng Chen Quoc V. Le Mohammad Norouzi Wolfgang Macherey Maxim Krikun Yuan Cao Qin Gao Klaus Macherey etal 2016. Google\u2019s neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144 (2016).  Yonghui Wu Mike Schuster Zhifeng Chen Quoc V. Le Mohammad Norouzi Wolfgang Macherey Maxim Krikun Yuan Cao Qin Gao Klaus Macherey et al. 2016. Google\u2019s neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144 (2016)."},{"key":"e_1_2_1_27_1","volume-title":"Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL\u201918)","author":"Yang Liu","year":"2018"},{"key":"e_1_2_1_28_1","volume-title":"Automatic transferring between ancient Chinese and contemporary Chinese. arXiv preprint arXiv:1803.01557","author":"Zhang Zhiyuan","year":"2018"}],"container-title":["ACM Transactions on Asian and Low-Resource Language Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3325887","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3325887","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:53:08Z","timestamp":1750204388000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3325887"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5,31]]},"references-count":28,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,1,31]]}},"alternative-id":["10.1145\/3325887"],"URL":"https:\/\/doi.org\/10.1145\/3325887","relation":{},"ISSN":["2375-4699","2375-4702"],"issn-type":[{"value":"2375-4699","type":"print"},{"value":"2375-4702","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,5,31]]},"assertion":[{"value":"2018-08-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-04-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-05-31","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}