{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T11:03:40Z","timestamp":1759230220618,"version":"3.37.3"},"publisher-location":"Cham","reference-count":11,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030474355"},{"type":"electronic","value":"9783030474362"}],"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"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-47436-2_63","type":"book-chapter","created":{"date-parts":[[2020,5,8]],"date-time":"2020-05-08T07:02:47Z","timestamp":1588921367000},"page":"840-851","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["An Empirical Model for n-gram Frequency Distribution in Large Corpora"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5223-1180","authenticated-orcid":false,"given":"Joaquim F.","family":"Silva","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6729-8348","authenticated-orcid":false,"given":"Jose C.","family":"Cunha","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,5,6]]},"reference":[{"key":"63_CR1","doi-asserted-by":"publisher","unstructured":"Ausloos, M., Cerqueti, R.: A universal rank-size law. PLoS ONE 11(11) (2016). \nhttps:\/\/doi.org\/10.1371\/journal.pone.0166011","DOI":"10.1371\/journal.pone.0166011"},{"key":"63_CR2","first-page":"1","volume":"4","author":"VK Balasubrahmanyan","year":"2002","unstructured":"Balasubrahmanyan, V.K., Naranan, S.: Algorithmic information, complexity and Zipf\u2019s law. Glottometrics 4, 1\u201326 (2002)","journal-title":"Glottometrics"},{"key":"63_CR3","unstructured":"Brants, T., Popat, A.C., Xu, P., Och, F.J., Dean, J.: Large language models in machine translation. In: Joint Conference on Empirical Methods in NLP and Computational Natural Language Learning, pp. 858\u2013867. ACL (2007)"},{"key":"63_CR4","doi-asserted-by":"publisher","unstructured":"Dias, G.: Multiword unit hybrid extraction. In: ACL Workshop on Multiword Expressions, vol. 18, pp. 41\u201348. ACL (2003). \nhttps:\/\/doi.org\/10.3115\/1119282.1119288","DOI":"10.3115\/1119282.1119288"},{"key":"63_CR5","doi-asserted-by":"publisher","unstructured":"L\u00fc, L., Zhang, Z.K., Zhou, T.: Deviation of Zipf\u2019s and heaps\u2019 laws in human languages with limited dictionary sizes. Sci. Rep. 3(1082) (2013). \nhttps:\/\/doi.org\/10.1038\/srep01082","DOI":"10.1038\/srep01082"},{"key":"63_CR6","unstructured":"Mandelbrot, B.: On the theory of word frequencies and on related Markovian models of discourse. In: Structure of Language and its Mathematical Aspects (1953)"},{"issue":"2","key":"63_CR7","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1080\/15427951.2004.10129088","volume":"1","author":"M Mitzenmacher","year":"2003","unstructured":"Mitzenmacher, M.: A brief history of generative models for power law and lognormal distributions. Internet Math. 1(2), 226\u2013251 (2003)","journal-title":"Internet Math."},{"issue":"5","key":"63_CR8","doi-asserted-by":"publisher","first-page":"1112","DOI":"10.3758\/s13423-014-0585-6","volume":"21","author":"ST Piantadosi","year":"2014","unstructured":"Piantadosi, S.T.: Zipf\u2019s word frequency law in natural language: a critical review and future directions. Psychon. Bull. Rev. 21(5), 1112\u20131130 (2014). \nhttps:\/\/doi.org\/10.3758\/s13423-014-0585-6","journal-title":"Psychon. Bull. Rev."},{"key":"63_CR9","doi-asserted-by":"publisher","unstructured":"Silva, J.F., Gon\u00e7alves, C., Cunha, J.C.: A theoretical model for n-gram distribution in big data corpora. In: 2016 IEEE International Conference on Big Data, pp. 134\u2013141 (2016). \nhttps:\/\/doi.org\/10.1109\/BigData.2016.7840598","DOI":"10.1109\/BigData.2016.7840598"},{"issue":"3\/4","key":"63_CR10","doi-asserted-by":"publisher","first-page":"425","DOI":"10.2307\/2333389","volume":"42","author":"H Simon","year":"1955","unstructured":"Simon, H.: On a class of skew distribution functions. Biometrika 42(3\/4), 425\u2013440 (1955). \nhttps:\/\/doi.org\/10.2307\/2333389","journal-title":"Biometrika"},{"key":"63_CR11","volume-title":"Human Behavior and the Principle of Least-Effort","author":"GK Zipf","year":"1949","unstructured":"Zipf, G.K.: Human Behavior and the Principle of Least-Effort. Addison-Wesley, Cambridge (1949)"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-47436-2_63","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,8]],"date-time":"2020-05-08T09:11:24Z","timestamp":1588929084000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-47436-2_63"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030474355","9783030474362"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-47436-2_63","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":"6 May 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","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":"11 May 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 May 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pakdd2020.org\/","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":"CMT System","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"628","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":"135","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":"21% - 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":"3-4","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":"6-8","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","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)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}