{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:37:21Z","timestamp":1765546641222,"version":"3.40.3"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030630300"},{"type":"electronic","value":"9783030630317"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","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":[[2020]]},"DOI":"10.1007\/978-3-030-63031-7_16","type":"book-chapter","created":{"date-parts":[[2020,11,12]],"date-time":"2020-11-12T00:05:35Z","timestamp":1605139535000},"page":"214-227","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Multi-reward Based Reinforcement Learning for Neural Machine Translation"],"prefix":"10.1007","author":[{"given":"Shuo","family":"Sun","sequence":"first","affiliation":[]},{"given":"Hongxu","family":"Hou","sequence":"additional","affiliation":[]},{"given":"Nier","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Ziyue","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Chaowei","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,12]]},"reference":[{"key":"16_CR1","unstructured":"Bahdanau, D., et al.: An actor-critic algorithm for sequence prediction. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, 24\u201326 April 2017, Conference Track Proceedings (2017). https:\/\/openreview.net\/forum?id=SJDaqqveg"},{"key":"16_CR2","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7\u20139 May 2015, Conference Track Proceedings (2015). http:\/\/arxiv.org\/abs\/1409.0473"},{"issue":"3","key":"16_CR3","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1080\/09296179508590051","volume":"2","author":"WA Gale","year":"1995","unstructured":"Gale, W.A., Sampson, G.: Good-turing frequency estimation without tears. J. Quant. Linguistics 2(3), 217\u2013237 (1995). https:\/\/doi.org\/10.1080\/09296179508590051","journal-title":"J. Quant. Linguistics"},{"key":"16_CR4","doi-asserted-by":"publisher","unstructured":"Harris, C.M., Mandelbaum, J.: A note on convergence requirements for nonlinear maximum-likelihood estimation of parameters from mixture models. Comput. OR 12(2), 237\u2013240 (1985). https:\/\/doi.org\/10.1016\/0305-0548(85)90048-6","DOI":"10.1016\/0305-0548(85)90048-6"},{"key":"16_CR5","unstructured":"Kool, W., van Hoof, H., Welling, M.: Stochastic beams and where to find them: the gumbel-top-k trick for sampling sequences without replacement. In: Proceedings of the 36th International Conference on Machine Learning, ICML 2019, Long Beach, California, USA, 9\u201315 June 2019, pp. 3499\u20133508 (2019). http:\/\/proceedings.mlr.press\/v97\/kool19a.html"},{"key":"16_CR6","unstructured":"Maddison, C.J., Tarlow, D., Minka, T.: A* sampling. In: Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, Montreal, Quebec, Canada, 8\u201313 December 2014, pp. 3086\u20133094 (2014). http:\/\/papers.nips.cc\/paper\/5449-a-sampling"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, Philadelphia, PA, USA, 6\u201312 July 2002, pp. 311\u2013318 (2002). https:\/\/www.aclweb.org\/anthology\/P02-1040\/","DOI":"10.3115\/1073083.1073135"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Peters, M.E., et al.: Deep contextualized word representations. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2018, New Orleans, Louisiana, USA, 1\u20136 June 2018, vol. 1 (Long Papers), pp. 2227\u20132237 (2018). https:\/\/www.aclweb.org\/anthology\/N18-1202\/","DOI":"10.18653\/v1\/N18-1202"},{"key":"16_CR9","doi-asserted-by":"publisher","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016, Berlin, Germany, 7\u201312 August 2016, vol. 1: Long Papers (2016). https:\/\/doi.org\/10.18653\/v1\/p16-1162","DOI":"10.18653\/v1\/p16-1162"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Shen, S., et al.: Minimum risk training for neural machine translation. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016, Berlin, Germany, 7\u201312 August 2016, vol. 1: Long Papers (2016). https:\/\/www.aclweb.org\/anthology\/P16-1159\/","DOI":"10.18653\/v1\/P16-1159"},{"key":"16_CR11","doi-asserted-by":"publisher","unstructured":"Sutton, R.S.: Learning to predict by the methods of temporal differences. Mach. Learn. 3, 9\u201344 (1988). https:\/\/doi.org\/10.1007\/BF00115009","DOI":"10.1007\/BF00115009"},{"key":"16_CR12","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, Long Beach, CA, USA, 4\u20139 December 2017, pp. 5998\u20136008 (2017). http:\/\/papers.nips.cc\/paper\/7181-attention-is-all-you-need"},{"key":"16_CR13","unstructured":"Wang, Z., Schaul, T., Hessel, M., van Hasselt, H., Lanctot, M., de Freitas, N.: Dueling network architectures for deep reinforcement learning. In: Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, 19\u201324 June 2016, pp. 1995\u20132003 (2016). http:\/\/proceedings.mlr.press\/v48\/wangf16.html"},{"key":"16_CR14","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8, 229\u2013256 (1992). https:\/\/doi.org\/10.1007\/BF00992696","journal-title":"Mach. Learn."},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Wu, L., Tian, F., Qin, T., Lai, J., Liu, T.: A study of reinforcement learning for neural machine translation. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, 31 October \u20134 November 2018, pp. 3612\u20133621 (2018). https:\/\/www.aclweb.org\/anthology\/D18-1397\/","DOI":"10.18653\/v1\/D18-1397"},{"key":"16_CR16","unstructured":"Wu, L., et al.: Adversarial neural machine translation. In: Proceedings of The 10th Asian Conference on Machine Learning, ACML 2018, Beijing, China, 14\u201316 November 2018, pp. 534\u2013549 (2018). http:\/\/proceedings.mlr.press\/v95\/wu18a.html"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Yang, Z., Chen, W., Wang, F., Xu, B.: Improving neural machine translation with conditional sequence generative adversarial nets. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2018, New Orleans, Louisiana, USA, 1\u20136 June 2018, vol. 1 (Long Papers), pp. 1346\u20131355 (2018). https:\/\/www.aclweb.org\/anthology\/N18-1122\/","DOI":"10.18653\/v1\/N18-1122"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Yin, W., Sch\u00fctze, H., Xiang, B., Zhou, B.: ABCNN: attention-based convolutional neural network for modeling sentence pairs. TACL 4, 259\u2013272 (2016). https:\/\/tacl2013.cs.columbia.edu\/ojs\/index.php\/tacl\/article\/view\/831","DOI":"10.1162\/tacl_a_00097"},{"key":"16_CR19","unstructured":"Yu, L., Zhang, W., Wang, J., Yu, Y.: Seqgan: sequence generative adversarial nets with policy gradient. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, San Francisco, California, USA, 4\u20139 February 2017, pp. 2852\u20132858 (2017). http:\/\/aaai.org\/ocs\/index.php\/AAAI\/AAAI17\/paper\/view\/14344"}],"container-title":["Lecture Notes in Computer Science","Chinese Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-63031-7_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T19:02:59Z","timestamp":1710270179000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-63031-7_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030630300","9783030630317"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-63031-7_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"12 November 2020","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":"Hainan","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":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 November 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cncl2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.cips-cl.org\/static\/CCL2020\/index.html","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":"www.softconf.com","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"99","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":"32","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":"2","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":"32% - 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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}