{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T11:33:08Z","timestamp":1777635188885,"version":"3.51.4"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030721121","type":"print"},{"value":"9783030721138","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-72113-8_44","type":"book-chapter","created":{"date-parts":[[2021,3,26]],"date-time":"2021-03-26T12:03:02Z","timestamp":1616760182000},"page":"666-679","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Machine Translation Customization via Automatic Training Data Selection from the Web"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1056-6975","authenticated-orcid":false,"given":"Thuy","family":"Vu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2216-8034","authenticated-orcid":false,"given":"Alessandro","family":"Moschitti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,3,27]]},"reference":[{"key":"44_CR1","first-page":"88","volume":"2016","author":"F Ahmed","year":"2016","unstructured":"Ahmed, F., Shafiq, M.Z., Liu, A.X.: The internet is for porn: measurement and analysis of online adult traffic. ICDCS 2016, 88\u201397 (2016)","journal-title":"ICDCS"},{"key":"44_CR2","first-page":"355","volume":"2011","author":"A Axelrod","year":"2011","unstructured":"Axelrod, A., He, X., Gao, J.: Domain adaptation via pseudo in-domain data selection. EMNLP 2011, 355\u2013362 (2011)","journal-title":"EMNLP"},{"key":"44_CR3","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: ICLR 2015 (2015)"},{"key":"44_CR4","first-page":"4555","volume":"2020","author":"M Ba\u00f1\u00f3n","year":"2020","unstructured":"Ba\u00f1\u00f3n, M., et al.: ParaCrawl: web-scale acquisition of parallel corpora. ACL 2020, 4555\u20134567 (2020)","journal-title":"ACL"},{"key":"44_CR5","unstructured":"Biesinger, R.: Is your software racist? Politico (2018). https:\/\/www.politico.com\/agenda\/story\/2018\/02\/07\/algorithmic-bias-software-recommendations-000631"},{"key":"44_CR6","doi-asserted-by":"crossref","unstructured":"Bojar, O., et al.: Findings of the 2018 Conference on Machine Translation (WMT 2018), Belgium, Brussels, pp. 272\u2013307 (2018)","DOI":"10.18653\/v1\/W18-6401"},{"key":"44_CR7","doi-asserted-by":"crossref","unstructured":"Buck, C., Koehn, P.: Quick and reliable document alignment via TF\/IDF-weighted cosine distance. In: WMT 2016, Berlin, Germany, pp. 672\u2013678 (2016)","DOI":"10.18653\/v1\/W16-2365"},{"key":"44_CR8","doi-asserted-by":"crossref","unstructured":"Chen, B., Huang, F.: Semi-supervised convolutional networks for translation adaptation with tiny amount of in-domain data. In: Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning. Association for Computational Linguistics, Berlin (2016)","DOI":"10.18653\/v1\/K16-1031"},{"key":"44_CR9","doi-asserted-by":"crossref","unstructured":"Dinu, G., Mathur, P., Federico, M., Al-Onaizan, Y.: Training neural machine translation to apply terminology constraints. In: ACL 2019, Florence, Italy, pp. 3063\u20133068 (2019)","DOI":"10.18653\/v1\/P19-1294"},{"key":"44_CR10","doi-asserted-by":"crossref","unstructured":"Gao, J., Goodman, J., Li, M., Lee, K.F.: Toward a unified approach to statistical language modeling for chinese. In: ACM TALIP (2002)","DOI":"10.1145\/509900.509903"},{"key":"44_CR11","unstructured":"Hieber, F., et al.: Sockeye: a toolkit for neural machine translation. CoRR (2017)"},{"key":"44_CR12","doi-asserted-by":"crossref","unstructured":"Junczys-Dowmunt, M., et al.: Marian: fast neural machine translation in C++. CoRR (2018)","DOI":"10.18653\/v1\/P18-4020"},{"key":"44_CR13","doi-asserted-by":"crossref","unstructured":"Liu, L., Hong, Y., Liu, H., Wang, X., Yao, J.: Effective selection of translation model training data. In: ACL 2014, Baltimore, Maryland (2014)","DOI":"10.3115\/v1\/P14-2093"},{"key":"44_CR14","doi-asserted-by":"crossref","unstructured":"Luong, T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. In: EMNLP 2015, Lisbon, Portugal (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"44_CR15","unstructured":"McCulloch, G.: Covid-19 is history\u2019s biggest translation challenge. wired.com (2020). https:\/\/www.wired.com\/story\/covid-language-translation-problem\/"},{"key":"44_CR16","unstructured":"Moore, R.C., Lewis, W.: Intelligent selection of language model training data. In: ACL 2010, Uppsala, Sweden, pp. 220\u2013224 (2010)"},{"key":"44_CR17","doi-asserted-by":"crossref","unstructured":"Post, M.: A call for clarity in reporting BLEU scores. In: WMT 2018 (2018)","DOI":"10.18653\/v1\/W18-6319"},{"key":"44_CR18","unstructured":"Smith, J.R., Saint-Amand, H., Plamada, M., Koehn, P., Callison-Burch, C., Lopez, A.: Dirt cheap web-scale parallel text from the common crawl. In: ACL 2013, Sofia, Bulgaria, pp. 1374\u20131383 (2013)"},{"key":"44_CR19","unstructured":"Uszkoreit, J., Ponte, J., Popat, A., Dubiner, M.: Large scale parallel document mining for machine translation. In: COLING 2010, Beijing, China (2010)"},{"key":"44_CR20","unstructured":"Vaswani, A., et al..: Attention is all you need. In: NIPS 2017, pp. 5998\u20136008 (2017)"},{"key":"44_CR21","doi-asserted-by":"crossref","unstructured":"Vu, T., Moschitti, A.: CDA: a cost efficient content-based multilingual web document aligner. In: EACL 2021 (2021)","DOI":"10.18653\/v1\/2021.eacl-main.266"},{"key":"44_CR22","unstructured":"Yasuda, K., Zhang, R., Yamamoto, H., Sumita, E.: Method of selecting training data to build a compact and efficient translation model. In: IJCNLP 2008 (2008)"}],"updated-by":[{"DOI":"10.1007\/978-3-030-72113-8_51","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2021,6,10]],"date-time":"2021-06-10T00:00:00Z","timestamp":1623283200000}}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-72113-8_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T11:06:55Z","timestamp":1710241615000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-72113-8_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030721121","9783030721138"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-72113-8_44","relation":{"correction":[{"id-type":"doi","id":"10.1007\/978-3-030-72113-8_51","asserted-by":"object"}]},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"27 March 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"10 June 2021","order":2,"name":"change_date","label":"Change Date","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Correction","order":3,"name":"change_type","label":"Change Type","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The original version of this chapter the table 3 was not correct. This has been corrected.","order":4,"name":"change_details","label":"Change Details","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 March 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 April 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"43","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.ecir2021.eu\/","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":"436","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":"50","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":"39","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":"11% - 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)"}}]}}