{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T04:07:27Z","timestamp":1729051647369},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031243363"},{"type":"electronic","value":"9783031243370"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-24337-0_38","type":"book-chapter","created":{"date-parts":[[2023,2,25]],"date-time":"2023-02-25T12:02:40Z","timestamp":1677326560000},"page":"545-554","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["How Much Does Tokenization Affect Neural Machine Translation?"],"prefix":"10.1007","author":[{"given":"Miguel","family":"Domingo","sequence":"first","affiliation":[]},{"given":"Mercedes","family":"Garc\u00eda-Mart\u00ednez","sequence":"additional","affiliation":[]},{"given":"Alexandre","family":"Helle","sequence":"additional","affiliation":[]},{"given":"Francisco","family":"Casacuberta","sequence":"additional","affiliation":[]},{"given":"Manuel","family":"Herranz","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,2,26]]},"reference":[{"key":"38_CR1","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2015)"},{"key":"38_CR2","doi-asserted-by":"crossref","unstructured":"Britz, D., Goldie, A., Luong, T., Le, Q.: Massive exploration of neural machine translation architectures. arXiv preprint arXiv:1703.03906 (2017)","DOI":"10.18653\/v1\/D17-1151"},{"key":"38_CR3","doi-asserted-by":"crossref","unstructured":"Dyer, C.: Using a maximum entropy model to build segmentation lattices for MT. In: Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics, pp. 406\u2013414 (2009)","DOI":"10.3115\/1620754.1620814"},{"key":"38_CR4","doi-asserted-by":"crossref","unstructured":"Goldwater, S., McClosky, D.: Improving statistical MT through morphological analysis. In: Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing, pp. 676\u2013683 (2005)","DOI":"10.3115\/1220575.1220660"},{"issue":"8","key":"38_CR5","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"38_CR6","doi-asserted-by":"crossref","unstructured":"Huck, M., Riess, S., Fraser, A.: Target-side word segmentation strategies for neural machine translation. In: Proceedings of the Conference on Machine Translation, pp. 56\u201367 (2017)","DOI":"10.18653\/v1\/W17-4706"},{"key":"38_CR7","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"38_CR8","doi-asserted-by":"crossref","unstructured":"Klein, G., Kim, Y., Deng, Y., Senellart, J., Rush, A.M.: OpenNMT: open-source toolkit for neural machine translation. arXiv preprint arXiv:1701.02810 (2017)","DOI":"10.18653\/v1\/P17-4012"},{"key":"38_CR9","unstructured":"Koehn, P.: Statistical significance tests for machine translation evaluation. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 388\u2013395 (2004)"},{"key":"38_CR10","doi-asserted-by":"crossref","unstructured":"Koehn, P., et al.: Moses: open source toolkit for statistical machine translation. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics, pp. 177\u2013180 (2007)","DOI":"10.3115\/1557769.1557821"},{"key":"38_CR11","unstructured":"Kudo, T.: Sentencepiece experiments (2018). https:\/\/github.com\/google\/sentencepiece\/blob\/master\/doc\/experiments.md"},{"key":"38_CR12","doi-asserted-by":"crossref","unstructured":"Kudo, T.: Subword regularization: improving neural network translation models with multiple subword candidates. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics, pp. 66\u201375 (2018)","DOI":"10.18653\/v1\/P18-1007"},{"key":"38_CR13","unstructured":"Nguyen, T., Vogel, S., Smith, N.A.: Nonparametric word segmentation for machine translation. In: Proceedings of the International Conference on Computational Linguistics, pp. 815\u2013823 (2010)"},{"issue":"2","key":"38_CR14","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1162\/089120104323093285","volume":"30","author":"S Nie\u00dfen","year":"2004","unstructured":"Nie\u00dfen, S., Ney, H.: Statistical machine translation with scarce resources using morpho-syntactic information. Comput. Linguist. 30(2), 181\u2013204 (2004)","journal-title":"Comput. Linguist."},{"key":"38_CR15","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 Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"38_CR16","unstructured":"Pascanu, R., Gulcehre, C., Cho, K., Bengio, Y.: How to construct deep recurrent neural networks. arXiv preprint arXiv:1312.6026 (2013)"},{"key":"38_CR17","doi-asserted-by":"crossref","unstructured":"Pinnis, M., Kri\u0161lauks, R., Deksne, D., Miks, T.: Neural machine translation for morphologically rich languages with improved sub-word units and synthetic data. In: Proceedings of the International Conference on Text, Speech, and Dialogue, pp. 237\u2013245 (2017)","DOI":"10.1007\/978-3-319-64206-2_27"},{"issue":"11","key":"38_CR18","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Trans. Signal Process. 45(11), 2673\u20132681 (1997)","journal-title":"IEEE Trans. Signal Process."},{"key":"38_CR19","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics, pp. 1715\u20131725 (2016)","DOI":"10.18653\/v1\/P16-1162"},{"key":"38_CR20","unstructured":"Snover, M., Dorr, B., Schwartz, R., Micciulla, L., Makhoul, J.: A study of translation edit rate with targeted human annotation. In: Proceedings of the Association for Machine Translation in the Americas, pp. 223\u2013231 (2006)"},{"key":"38_CR21","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 3104\u20133112 (2014)"},{"key":"38_CR22","unstructured":"Tseng, H., Chang, P., Andrew, G., Jurafsky, D., Manning, C.: A conditional random field word segmenter. In: Proceedings of the Special Interest Group of the Association for Computational Linguistics Workshop on Chinese Language Processing, pp. 168\u2013171 (2005)"},{"key":"38_CR23","unstructured":"Wu, Y., et al.: Google\u2019s neural machine translation system: bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144 (2016)"},{"key":"38_CR24","doi-asserted-by":"crossref","unstructured":"Zhao, H., Utiyama, M., Sumita, E., Lu, B.L.: An empirical study on word segmentation for Chinese machine translation. In: Proceedings of the Computational Linguistics and Intelligent Text Processing, pp. 248\u2013263 (2013)","DOI":"10.1007\/978-3-642-37256-8_21"}],"container-title":["Lecture Notes in Computer Science","Computational Linguistics and Intelligent Text Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-24337-0_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,15]],"date-time":"2024-10-15T04:55:53Z","timestamp":1728968153000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-24337-0_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031243363","9783031243370"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-24337-0_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"26 February 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CICLing","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Linguistics and Intelligent Text Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"La Rochelle","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","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":"7 April 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 April 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cicling2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.cicling.org\/2019\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"335","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":"95","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":"28% - 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":"2.3","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":"3.4","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)"}}]}}