{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T02:39:54Z","timestamp":1743129594103,"version":"3.40.3"},"publisher-location":"Cham","reference-count":11,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030983048"},{"type":"electronic","value":"9783030983055"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-030-98305-5_38","type":"book-chapter","created":{"date-parts":[[2022,3,17]],"date-time":"2022-03-17T08:05:37Z","timestamp":1647504337000},"page":"407-412","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Revisiting CCNet for\u00a0Quality Measurements in\u00a0Galician"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2328-3205","authenticated-orcid":false,"given":"John E.","family":"Ortega","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5941-1707","authenticated-orcid":false,"given":"Iria","family":"de-Dios-Flores","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5172-6803","authenticated-orcid":false,"given":"Jos\u00e9 Ramom","family":"Pichel","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5819-2469","authenticated-orcid":false,"given":"Pablo","family":"Gamallo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,3,16]]},"reference":[{"key":"38_CR1","doi-asserted-by":"publisher","unstructured":"Conneau, A., et al.: Unsupervised cross-lingual representation learning at scale. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 8440\u20138451. Association for Computational Linguistics, July 2020. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.747, https:\/\/aclanthology.org\/2020.acl-main.747","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"38_CR2","unstructured":"Gamallo, P., Alegria, I., Pichel, J.R., Agirrezabal, M.: Comparing two basic methods for discriminating between similar languages and varieties. In: COLING Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial3) (2016)"},{"key":"38_CR3","doi-asserted-by":"publisher","unstructured":"Gamallo, P., Pichel, J.R., Alegria, I.: Measuring language distance of isolated european languages. Information 11(4), 181 (2020). https:\/\/doi.org\/10.3390\/info11040181, https:\/\/www.mdpi.com\/2078-2489\/11\/4\/181","DOI":"10.3390\/info11040181"},{"key":"38_CR4","unstructured":"Heafield, K.: Kenlm: faster and smaller language model queries. In: Proceedings of the sixth workshop on statistical machine translation, pp. 187\u2013197 (2011)"},{"key":"38_CR5","unstructured":"Kida, T., Fukamachi, S., Takeda, M., Shinohara, A., Shinohara, T., Arikawa, S.: Byte pair encoding: a text compression scheme that accelerates pattern matching (1999)"},{"key":"38_CR6","doi-asserted-by":"crossref","unstructured":"Kudo, T., Richardson, J.: Sentencepiece: A simple and language independent subword tokenizer and detokenizer for neural text processing. arXiv preprint arXiv:1808.06226 (2018)","DOI":"10.18653\/v1\/D18-2012"},{"key":"38_CR7","unstructured":"Lankford, S., Afli, H., Way, A.: Machine translation in the covid domain: an english-irish case study for loresmt 2021. In: Proceedings of the 4th Workshop on Technologies for MT of Low Resource Languages (LoResMT2021), pp. 144\u2013150 (2021)"},{"issue":"8","key":"38_CR8","first-page":"707","volume":"10","author":"V Levenshtein","year":"1966","unstructured":"Levenshtein, V.: Binary codes capable of correcting deletions, insertions and reversals. Soviet Phys. Doklady. 10(8), 707\u2013710 (1966)","journal-title":"Soviet Phys. Doklady."},{"key":"38_CR9","unstructured":"Ortega, J.E., Castro-Mamani, R.A., Samame, J.R.M.: Love thy neighbor: combining two neighboring low-resource languages for translation. In: Proceedings of the 4th Workshop on Technologies for MT of Low Resource Languages (LoResMT2021). pp. 44\u201351 (2021)"},{"issue":"4","key":"38_CR10","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1007\/s10590-020-09255-9","volume":"34","author":"JE Ortega","year":"2020","unstructured":"Ortega, J.E., Mamani, R.C., Cho, K.: Neural machine translation with a polysynthetic low resource language. Mach. Trans. 34(4), 325\u2013346 (2020)","journal-title":"Mach. Trans."},{"key":"38_CR11","unstructured":"Wenzek, G., et al.: CCNet: extracting high quality monolingual datasets from web crawl data. In: Proceedings of the 12th Language Resources and Evaluation Conference, pp. 4003\u20134012. European Language Resources Association, Marseille, France, May 2020. https:\/\/aclanthology.org\/2020.lrec-1.494"}],"container-title":["Lecture Notes in Computer Science","Computational Processing of the Portuguese Language"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-98305-5_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,17]],"date-time":"2022-03-17T08:16:25Z","timestamp":1647504985000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-98305-5_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030983048","9783030983055"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-98305-5_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"16 March 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PROPOR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Processing of the Portuguese Language","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Fortaleza","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazil","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 March 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 March 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"propor2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/sites.universidadedefortaleza.com\/propor2022\/","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":"88","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":"36","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":"4","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":"41% - 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":"3.16","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":"2.87","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)"}},{"value":"A Scientific Review Committee of 97 researchers reviewed all papers. Conference was held online due to COVID-19.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}