{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T22:22:33Z","timestamp":1742941353800,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030811990"},{"type":"electronic","value":"9783030812003"}],"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\/978-3-030-81200-3_16","type":"book-chapter","created":{"date-parts":[[2021,7,15]],"date-time":"2021-07-15T17:04:55Z","timestamp":1626368695000},"page":"216-229","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Comparison of Cross-Lingual Similar Documents Retrieval Methods"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9687-6650","authenticated-orcid":false,"given":"Denis","family":"Zubarev","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3113-3765","authenticated-orcid":false,"given":"Ilya","family":"Sochenkov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,7,16]]},"reference":[{"key":"16_CR1","unstructured":"Antonova, A., Misyurev, A.: Building a web-based parallel corpus and filtering out machine-translated text. In: Proceedings of the 4th Workshop on Building and Using Comparable Corpora: Comparable Corpora and the Web, pp. 136\u2013144 (2011)"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Artetxe, M., Labaka, G., Agirre, E.: Generalizing and improving bilingual word embedding mappings with a multi-step framework of linear transformations. In: AAAI, pp. 5012\u20135019 (2018)","DOI":"10.1609\/aaai.v32i1.11992"},{"key":"16_CR3","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1162\/tacl_a_00288","volume":"7","author":"M Artetxe","year":"2019","unstructured":"Artetxe, M., Schwenk, H.: Massively multilingual sentence embeddings for zero-shot cross-lingual transfer and beyond. Trans. Assoc. Comput. Linguist. 7, 597\u2013610 (2019)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"16_CR4","unstructured":"Bakhteev, O., Ogaltsov, A., Khazov, A., Safin, K., Kuznetsova, R.: Crosslang: the system of cross-lingual plagiarism detection. In: Workshop on Document Intelligence at NeurIPS 2019 (2019)"},{"key":"16_CR5","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1016\/j.knosys.2013.06.018","volume":"50","author":"A Barr\u00f3n-Cede\u00f1o","year":"2013","unstructured":"Barr\u00f3n-Cede\u00f1o, A., Gupta, P., Rosso, P.: Methods for cross-language plagiarism detection. Knowl.-Based Syst. 50, 211\u2013217 (2013)","journal-title":"Knowl.-Based Syst."},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. Trans. Assoc. Comput. Linguist. 5, 135\u2013146 (2017)","DOI":"10.1162\/tacl_a_00051"},{"key":"16_CR7","unstructured":"Conneau, A., Lample, G., Ranzato, M., Denoyer, L., J\u00e9gou, H.: Word translation without parallel data. arXiv preprint arXiv:1710.04087 (2017)"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Ferrero, J., Agnes, F., Besacier, L., Schwab, D.: Usingword embedding for cross-language plagiarism detection. arXiv preprint arXiv:1702.03082 (2017)","DOI":"10.18653\/v1\/W17-2502"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Franco-Salvador, M., Gupta, P., Rosso, P., Banchs, R.E.: Cross-language plagiarism detection over continuous-space-and knowledge graph-based representations of language. Knowl.-based Syst. 111, 87\u201399 (2016)","DOI":"10.1016\/j.knosys.2016.08.004"},{"key":"16_CR10","unstructured":"Gabrilovich, E., Markovitch, S., et al.: Computing semantic relatedness using wikipedia-based explicit semantic analysis. IJcAI. 7, 1606\u20131611 (2007)"},{"key":"16_CR11","unstructured":"Gillick, D., Presta, A., Tomar, G.S.: End-to-end retrieval in continuous space. arXiv preprint arXiv:1811.08008 (2018)"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Jiang, J.Y., Zhang, M., Li, C., Bendersky, M., Golbandi, N., Najork, M.: Semantic text matching for long-form documents. In: The World Wide Web Conference, pp. 795\u2013806 (2019)","DOI":"10.1145\/3308558.3313707"},{"key":"16_CR13","unstructured":"Johnson, J., Douze, M., J\u00e9gou, H.: Billion-scale similarity search with gpus. IEEE Trans. Big Data (2019)"},{"key":"16_CR14","unstructured":"Kutuzov, A., Kopotev, M., Sviridenko, T., Ivanova, L.: Clustering comparable corpora of russian and ukrainian academic texts: Word embeddings and semantic fingerprints. arXiv preprint arXiv:1604.05372 (2016)"},{"key":"16_CR15","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111\u20133119 (2013)"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Potthast, M., Barr\u00f3n-Cede\u00f1o, A., Stein, B., Rosso, P.: Cross-language plagiarism detection. Lang. Res. Eval. 45(1), 45\u201362 (2011)","DOI":"10.1007\/s10579-009-9114-z"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Rekabsaz, N., Lupu, M., Hanbury, A., Zuccon, G.: Generalizing translation models in the probabilistic relevance framework. In: Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, pp. 711\u2013720 (2016)","DOI":"10.1145\/2983323.2983833"},{"key":"16_CR18","unstructured":"Romanov, A., Kuznetsova, R., Bakhteev, O., Khritankov, A.: Machine-translated text detection in a collection of russian scientific papers. Dialogue, p. 2 (2016)"},{"key":"16_CR19","unstructured":"Schwenk, H., Chaudhary, V., Sun, S., Gong, H., Guzm\u00e1n, F.: Wikimatrix: Mining 135m parallel sentences in 1620 language pairs from wikipedia. arXiv preprint arXiv:1907.05791 (2019)"},{"key":"16_CR20","unstructured":"Sochenkov, I.V., Zubarev, D.V., Tikhomirov, I.A.: Exploratory patent search. Inf. its Appl. 12(1), 89\u201394 (2018)"},{"key":"16_CR21","unstructured":"Sochenkov, I., Zubarev, D., Smirnov, I.: The paraplag: Russian dataset for paraphrased plagiarism detection. In: Computational Linguistics and Intellectual Technologies: Papers from the Annual International Conference Dialogue, vol. 1, pp. 284\u2013297 (2017)"},{"key":"16_CR22","unstructured":"Straka, M., Hajic, J., Strakov\u00e1, J.: Udpipe: trainable pipeline for processing conll-u files performing tokenization, morphological analysis, pos tagging and parsing. In: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), pp. 4290\u20134297 (2016)"},{"key":"16_CR23","unstructured":"Tang, S., Mousavi, M., de Sa, V.R.: An empirical study on post-processing methods for word embeddings. arXiv preprint arXiv:1905.10971 (2019)"},{"key":"16_CR24","unstructured":"Tiedemann, J.: Parallel data, tools and interfaces in opus. Lrec 2012, 2214\u20132218 (2012)"},{"key":"16_CR25","unstructured":"Vuli\u0107, I., et al.: Multi-simlex: A large-scale evaluation of multilingual and cross-lingual lexical semantic similarity. arXiv preprint arXiv:2003.04866 (2020)"},{"key":"16_CR26","doi-asserted-by":"crossref","unstructured":"Vulic, I., Moens, M.F.: Bilingual word embeddings from non-parallel document-aligned data applied to bilingual lexicon induction. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics (ACL 2015), vol. 2, pp. 719\u2013725. ACL; East Stroudsburg, PA (2015)","DOI":"10.3115\/v1\/P15-2118"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Vuli\u0107, I., Moens, M.F.: Monolingual and cross-lingual information retrieval models based on (bilingual) word embeddings. In: Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 363\u2013372 (2015)","DOI":"10.1145\/2766462.2767752"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Zubarev, D.V., Sochenkov, I.V.: Cross-lingual similar document retrieval methods. In: Proceedings of the ISP RAS, 31(5) (2019)","DOI":"10.15514\/ISPRAS-2019-31(5)-9"},{"key":"16_CR29","unstructured":"Zubarev, D., Sochenkov, I.: Cross-language text alignment for plagiarism detection based on contextual and context-free models. In: Proceedings of the Annual International Conference Dialogue, vol. 1, pp. 799\u2013810 (2019)"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Zweigenbaum, P., Sharoff, S., Rapp, R.: Overview of the third bucc shared task: spotting parallel sentences in comparable corpora. In: Proceedings of 11th Workshop on Building and Using Comparable Corpora, pp. 39\u201342 (2018)","DOI":"10.18653\/v1\/W17-2512"}],"container-title":["Communications in Computer and Information Science","Data Analytics and Management in Data Intensive Domains"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-81200-3_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,4]],"date-time":"2023-01-04T13:10:59Z","timestamp":1672837859000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-81200-3_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030811990","9783030812003"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-81200-3_16","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"16 July 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DAMDID\/RCDL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Data Analytics and Management in Data Intensive Domains","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Voronezh","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russia","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":"13 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"damdid2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/damdid2020.cs.vsu.ru\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"60","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":"16","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":"27% - 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":"3.8","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)"}}]}}