{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T17:22:12Z","timestamp":1790184132485,"version":"4.1.0"},"reference-count":51,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2019,5,21]],"date-time":"2019-05-21T00:00:00Z","timestamp":1558396800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61761166008, 61562082"],"award-info":[{"award-number":["61761166008, 61562082"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Key R8D Program of China","award":["2017YFB0202204"],"award-info":[{"award-number":["2017YFB0202204"]}]},{"DOI":"10.13039\/501100012424","name":"Advanced Innovation Center for Language Resources","doi-asserted-by":"crossref","award":["TYR17002"],"award-info":[{"award-number":["TYR17002"]}],"id":[{"id":"10.13039\/501100012424","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Research Foundation, Prime Ministers Office, Singapore under its IRC@Singapore Funding Initiative"},{"name":"NExT++ project"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Asian Low-Resour. Lang. Inf. Process."],"published-print":{"date-parts":[[2019,12,31]]},"abstract":"<jats:p>Neural machine translation (NMT) has made remarkable progress in recent years, but the performance of NMT suffers from a data sparsity problem since large-scale parallel corpora are only readily available for high-resource languages (HRLs). In recent days, transfer learning (TL) has been used widely in low-resource languages (LRLs) machine translation, while TL is becoming one of the vital directions for addressing the data sparsity problem in low-resource NMT. As a solution, a transfer learning method in NMT is generally obtained via initializing the low-resource model (child) with the high-resource model (parent). However, leveraging the original TL to low-resource models is neither able to make full use of highly related multiple HRLs nor to receive different parameters from the same parents. In order to exploit multiple HRLs effectively, we present a language-independent and straightforward multi-round transfer learning (MRTL) approach to low-resource NMT. Besides, with the intention of reducing the differences between high-resource and low-resource languages at the character level, we introduce a unified transliteration method for various language families, which are both semantically and syntactically highly analogous with each other. Experiments on low-resource datasets show that our approaches are effective, significantly outperform the state-of-the-art methods, and yield improvements of up to 5.63 BLEU points.<\/jats:p>","DOI":"10.1145\/3314945","type":"journal-article","created":{"date-parts":[[2019,5,23]],"date-time":"2019-05-23T18:01:38Z","timestamp":1558634498000},"page":"1-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["Multi-Round Transfer Learning for Low-Resource NMT Using Multiple High-Resource Languages"],"prefix":"10.1145","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4231-6519","authenticated-orcid":false,"given":"Mieradilijiang","family":"Maimaiti","sequence":"first","affiliation":[{"name":"State Key Laboratory of Intelligent Technology and Systems, Institute for Artificial Intelligence, Tsinghua University, Beijing National Research Center for Information Science and Technology (BNRist), Department of Computer Science and Technology, Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Intelligent Technology and Systems, Institute for Artificial Intelligence, Tsinghua University, Beijing National Research Center for Information Science and Technology (BNRist), Department of Computer Science and Technology, Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huanbo","family":"Luan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Intelligent Technology and Systems, Institute for Artificial Intelligence, Tsinghua University, Beijing National Research Center for Information Science and Technology (BNRist), Department of Computer Science and Technology, Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maosong","family":"Sun","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Intelligent Technology and Systems, Institute for Artificial Intelligence, Tsinghua University, Beijing National Research Center for Information Science and Technology (BNRist), Department of Computer Science and Technology, Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2019,5,21]]},"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":"Proceedings of ICLR.","author":"Bahdanau Dzmitry","year":"2015"},{"key":"e_1_2_1_3_1","unstructured":"Antonio Valerio Miceli Barone and Giuseppe Attardi. 2013. Pre-reordering for machine translation using transition-based walks on dependency parse trees. In WMT@ACL.  Antonio Valerio Miceli Barone and Giuseppe Attardi. 2013. Pre-reordering for machine translation using transition-based walks on dependency parse trees. In WMT@ACL."},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/972470.972474"},{"key":"e_1_2_1_5_1","volume-title":"Proceedings of ACL.","author":"Carpuat Marine","year":"2013"},{"key":"e_1_2_1_6_1","volume-title":"Li","author":"Chen Yun","year":"2017"},{"key":"e_1_2_1_7_1","volume-title":"Li","author":"Chen Yun","year":"2018"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1185"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/3171837.3171841"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.3115\/1219840.1219873"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_2_1_12_1","unstructured":"Chenhui Chu Raj Dabre and Sadao Kurohashi. 2017. An empirical comparison of simple domain adaptation methods for neural machine translation. CoRR abs\/1701.03214.  Chenhui Chu Raj Dabre and Sadao Kurohashi. 2017. An empirical comparison of simple domain adaptation methods for neural machine translation. CoRR abs\/1701.03214."},{"key":"e_1_2_1_13_1","first-page":"17","volume-title":"Proceedings of the 31st Pacific Asia Conference on Language, Information, and Computation. The National University (Phillippines), 282--286","author":"Dabre Raj","year":"2017"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1166"},{"key":"e_1_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Marzieh Fadaee Arianna Bisazza and Christof Monz. 2017. Data augmentation for low-resource neural machine translation. In ACL.  Marzieh Fadaee Arianna Bisazza and Christof Monz. 2017. Data augmentation for low-resource neural machine translation. In ACL.","DOI":"10.18653\/v1\/P17-2090"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1101"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1026"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.3115\/1220575.1220660"},{"key":"e_1_2_1_19_1","unstructured":"Kazi Saidul Hasan Altaf Rahman and Vincent Ng. 2009. Learning-based named entity recognition for morphologically-rich resource-scarce languages. In EACL.  Kazi Saidul Hasan Altaf Rahman and Vincent Ng. 2009. Learning-based named entity recognition for morphologically-rich resource-scarce languages. In EACL."},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural Comput. (1997).  Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural Comput. (1997).","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.349"},{"key":"e_1_2_1_23_1","volume-title":"Google\u2019s multilingual neural machine translation system: Enabling zero-shot translation. Trans. ACL","author":"Johnson Melvin","year":"2017"},{"key":"e_1_2_1_24_1","unstructured":"Marcin Junczys-Dowmunt Tomasz Dwojak and Hieu Hoang. 2016. Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions. arXiv:1610.01108v2.  Marcin Junczys-Dowmunt Tomasz Dwojak and Hieu Hoang. 2016. Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions. arXiv:1610.01108v2."},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10590-017-9203-5"},{"key":"e_1_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Philipp Koehn and Rebecca Knowles. 2017. Six challenges for neural machine translation. In NMT@ACL.  Philipp Koehn and Rebecca Knowles. 2017. Six challenges for neural machine translation. In NMT@ACL.","DOI":"10.18653\/v1\/W17-3204"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073445.1073462"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1162\/coli.2009.35.4.35403"},{"key":"e_1_2_1_29_1","volume-title":"Jordan","author":"Long Mingsheng","year":"2015"},{"key":"e_1_2_1_30_1","volume-title":"Manning","author":"Luong Minh-Thang","year":"2015"},{"key":"e_1_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Thang Luong Ilya Sutskever Quoc V. Le Oriol Vinyals and Wojciech Zaremba. 2015. Addressing the rare word problem in neural machine translation. In ACL.  Thang Luong Ilya Sutskever Quoc V. Le Oriol Vinyals and Wojciech Zaremba. 2015. Addressing the rare word problem in neural machine translation. In ACL.","DOI":"10.3115\/v1\/P15-1002"},{"key":"e_1_2_1_32_1","volume-title":"ICIS2018","author":"Mieradilijiang Maimaiti","year":"2018"},{"key":"e_1_2_1_33_1","volume-title":"Nguyen and David Chiang","author":"Toan","year":"2017"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.222"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2010.2091281"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3099556"},{"key":"e_1_2_1_39_1","volume-title":"Neural machine translation of rare words with subword units. CoRR abs\/1508.07909","author":"Sennrich Rico","year":"2016"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10590-017-9206-2"},{"key":"e_1_2_1_41_1","volume-title":"Le","author":"Sutskever Ilya","year":"2014"},{"key":"e_1_2_1_42_1","volume-title":"Sinno Jialin Pan, and Qiang Yang","author":"Tan Ben","year":"2017"},{"key":"e_1_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Clara Vania and Adam Lopez. 2017. From characters to words to in between: Do we capture morphology? In ACL.  Clara Vania and Adam Lopez. 2017. From characters to words to in between: Do we capture morphology? In ACL.","DOI":"10.18653\/v1\/P17-1184"},{"key":"e_1_2_1_44_1","volume-title":"Proceedings of NIPS.","author":"Vaswani Ashish","year":"2017"},{"key":"e_1_2_1_45_1","volume-title":"Proceedings of MT Summit XIII","author":"Wang Zhiyang","year":"2011"},{"key":"e_1_2_1_46_1","unstructured":"Yonghui Wu Mike Schuster Zhifeng Chen Quoc V. Le Mohammad Norouzi Wolfgang Macherey Maxim Krikun Yuan Cao Qin Gao Klaus Macherey Jeff Klingner Apurva Shah Melvin Johnson Xiaobing Liu Lukasz Kaiser Stephan Gouws Yoshikiyo Kato Taku Kudo Hideto Kazawa Keith Stevens George Kurian Nishant Patil Wei Wang Cliff Young Jason Smith Jason Riesa Alex Rudnick Oriol Vinyals Gregory S. Corrado Macduff Hughes and Jeffrey Dean 2016. Google\u2019s neural machine translation system: Bridging the gap between human and machine translation. CoRR abs\/1609.08144.  Yonghui Wu Mike Schuster Zhifeng Chen Quoc V. Le Mohammad Norouzi Wolfgang Macherey Maxim Krikun Yuan Cao Qin Gao Klaus Macherey Jeff Klingner Apurva Shah Melvin Johnson Xiaobing Liu Lukasz Kaiser Stephan Gouws Yoshikiyo Kato Taku Kudo Hideto Kazawa Keith Stevens George Kurian Nishant Patil Wei Wang Cliff Young Jason Smith Jason Riesa Alex Rudnick Oriol Vinyals Gregory S. Corrado Macduff Hughes and Jeffrey Dean 2016. Google\u2019s neural machine translation system: Bridging the gap between human and machine translation. CoRR abs\/1609.08144."},{"key":"e_1_2_1_47_1","volume-title":"THUMT: An open source toolkit for neural machine translation. arXiv preprint arXiv:1706.06415.","author":"Zhang Jiacheng","year":"2017"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.5555\/3171837.3171880"},{"key":"e_1_2_1_49_1","doi-asserted-by":"crossref","unstructured":"Barret Zoph and Kevin Knight. 2016. Multi-source neural translation. In HLT-NAACL.  Barret Zoph and Kevin Knight. 2016. Multi-source neural translation. In HLT-NAACL.","DOI":"10.18653\/v1\/N16-1004"},{"key":"e_1_2_1_50_1","volume-title":"Le","author":"Zoph Barret","year":"2017"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1163"}],"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\/3314945","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3314945","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:02:03Z","timestamp":1750208523000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3314945"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5,21]]},"references-count":51,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2019,12,31]]}},"alternative-id":["10.1145\/3314945"],"URL":"https:\/\/doi.org\/10.1145\/3314945","relation":{},"ISSN":["2375-4699","2375-4702"],"issn-type":[{"value":"2375-4699","type":"print"},{"value":"2375-4702","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,5,21]]},"assertion":[{"value":"2018-06-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-01-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-05-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}