{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T18:27:30Z","timestamp":1787509650660,"version":"build-2736575974"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030323806","type":"print"},{"value":"9783030323813","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-32381-3_26","type":"book-chapter","created":{"date-parts":[[2019,10,14]],"date-time":"2019-10-14T07:17:59Z","timestamp":1571037479000},"page":"321-333","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Character-Aware Low-Resource Neural Machine Translation with Weight Sharing and Pre-training"],"prefix":"10.1007","author":[{"given":"Yichao","family":"Cao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rujing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,10,13]]},"reference":[{"key":"26_CR1","unstructured":"Vaswani, A., Shazeer, N.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"26_CR2","unstructured":"Hassan, H., Aue, A., et al.: Achieving human parity on automatic Chinese to English news translation. arXiv preprint arXiv:1803.05567 (2018)"},{"key":"26_CR3","doi-asserted-by":"crossref","unstructured":"Zoph, B., Yuret, D.: Transfer learning for low-resource neural machine translation. arXiv preprint arXiv:1604.02201 (2016)","DOI":"10.18653\/v1\/D16-1163"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Koehn, P., Knowles, R.: Six challenges for neural machine translation. arXiv preprint arXiv:1706.03872 (2017)","DOI":"10.18653\/v1\/W17-3204"},{"key":"26_CR5","unstructured":"Santos, C.N.D., Guimaraes, V.: Boosting named entity recognition with neural character embeddings. arXiv preprint arXiv:1505.05008 (2015)"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Yang, Z., Chen, W.: Unsupervised neural machine translation with weight sharing. arXiv preprint arXiv:1804.09057 (2018)","DOI":"10.18653\/v1\/P18-1005"},{"key":"26_CR7","unstructured":"Devlin, J., Chang, M.W.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Vincent, P., Larochelle, H.: Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th International Conference on Machine learning, pp. 1096\u20131103. ACM (2008)","DOI":"10.1145\/1390156.1390294"},{"key":"26_CR9","unstructured":"Bahdanau, D., Cho, K.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Gu, J., Wang, Y.: Meta-learning for low-resource neural machine translation. arXiv preprint arXiv:1808.08437 (2018)","DOI":"10.18653\/v1\/D18-1398"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B.: Improving neural machine translation models with monolingual data. arXiv preprint arXiv:1511.06709 (2015)","DOI":"10.18653\/v1\/P16-1009"},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Currey, A., Barone, A.V.M.: Copied monolingual data improves low-resource neural machine translation. In: Proceedings of the Second Conference on Machine Translation, pp. 148\u2013156 (2017)","DOI":"10.18653\/v1\/W17-4715"},{"key":"26_CR13","unstructured":"Ling, W., Trancoso, I.: Character-based neural machine translation. arXiv preprint arXiv:1511.04586 (2015)"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Ruiz Costa-Juss\u00e0, M., Rodr\u00edguez Fonollosa, J.A.: Character-based neural machine translation. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pp. 357\u2013361 (2016)","DOI":"10.18653\/v1\/P16-2058"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Luong, M.T., Manning, C.D.: Achieving open vocabulary neural machine translation with hybrid word-character models. arXiv preprint arXiv:1604.00788 (2016)","DOI":"10.18653\/v1\/P16-1100"},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"Passban, P., Liu, Q., Way, A.: Improving character-based decoding using targetside morphological information for neural machine translation. arXiv preprint arXiv:1804.06506 (2018)","DOI":"10.18653\/v1\/N18-1006"},{"key":"26_CR17","unstructured":"Radford, A., Narasimhan, K.: Improving language understanding with unsupervised learning. Technical report, OpenAI (2018)"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Lample, G., Ott, M.: Phrase-based & neural unsupervised machine translation. arXiv preprint arXiv:1804.07755 (2018)","DOI":"10.18653\/v1\/D18-1549"},{"key":"26_CR19","doi-asserted-by":"crossref","unstructured":"Firat, O., Cho, K.: Multi-way, multilingual neural machine translation with a shared attention mechanism. arXiv preprint arXiv:1601.01073 (2016)","DOI":"10.18653\/v1\/N16-1101"},{"key":"26_CR20","unstructured":"Renduchintala, A., Shapiro, P.: Character-aware decoder for neural machine translation. arXiv preprint arXiv:1809.02223 (2018)"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Kim, Y., Jernite, Y.: Character-aware neural language models. In: Thirtieth AAAI Conference on Artificial Intelligence (2016)","DOI":"10.1609\/aaai.v30i1.10362"},{"key":"26_CR22","unstructured":"Srivastava, R.K., Greff, K.: Training very deep networks. In: Advances in Neural Information Processing Systems, pp. 2377\u20132385 (2015)"},{"key":"26_CR23","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1162\/tacl_a_00067","volume":"5","author":"J Lee","year":"2017","unstructured":"Lee, J., Cho, K.: Fully character-level neural machine translation without explicit segmentation. Trans. Assoc. Comput. Linguist. 5, 365\u2013378 (2017)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"26_CR24","unstructured":"Lample, G., Conneau, A.: Cross-lingual language model pretraining (2019)"},{"key":"26_CR25","unstructured":"Sun, M., Chen, X.: THULAC: an efficient lexical analyzer for Chinese. Technical report (2016)"},{"key":"26_CR26","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"issue":"1","key":"26_CR27","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."}],"container-title":["Lecture Notes in Computer Science","Chinese Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-32381-3_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T14:36:43Z","timestamp":1710254203000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-32381-3_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030323806","9783030323813"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-32381-3_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"13 October 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China National Conference on Chinese Computational Linguistics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kunming","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":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cncl2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.cips-cl.org\/static\/CCL2019\/en\/callfor.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}