{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:09:56Z","timestamp":1750219796368,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,19]]},"DOI":"10.1145\/3539618.3591942","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:59Z","timestamp":1689726179000},"page":"1776-1780","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Unified Formulation for the Frequency Distribution of Word Frequencies using the Inverse Zipf's Law"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8432-9413","authenticated-orcid":false,"given":"Can","family":"\u00d6zbey","sequence":"first","affiliation":[{"name":"Huawei Turkey R&amp;D Center, Istanbul, Turkey"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4524-862X","authenticated-orcid":false,"given":"Talha","family":"\u00c7olako\u011flu","sequence":"additional","affiliation":[{"name":"Huawei Turkey R&amp;D Center, Istanbul, Turkey"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4456-5163","authenticated-orcid":false,"given":"M. \u015eafak","family":"Bilici","sequence":"additional","affiliation":[{"name":"Huawei Turkey R&amp;D Center, Istanbul, Turkey"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2445-5929","authenticated-orcid":false,"given":"Ekin Can","family":"Erku\u015f;","sequence":"additional","affiliation":[{"name":"Huawei Turkey R&amp;D Center, Istanbul, Turkey"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"volume-title":"Word Frequency Distributions (1 ed.)","author":"Baayen R. Harald","key":"e_1_3_2_2_1_1","unstructured":"R. Harald Baayen. 2001. Word Frequency Distributions (1 ed.). Springer Dordrecht."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0019-9958(67)90201-X"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-4571(199007)41:5<387::AID-ASI10>3.0.CO;2-I"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080821"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1526709.1526770"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-014-9287-y"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0218348X97000103"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.102.052113"},{"volume-title":"Unsupervised morpheme segmentation and morphology induction from text corpora using Morfessor 1.0","author":"Creutz Mathias","key":"e_1_3_2_2_9_1","unstructured":"Mathias Creutz and Krista Lagus. 2005. Unsupervised morpheme segmentation and morphology induction from text corpora using Morfessor 1.0. Helsinki University of Technology."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/12047.13675"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1140\/epjb"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1076\/jqul.8.3.165"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1574-0080(04)80010-5"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1140\/epjb"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-009-9135-4"},{"volume-title":"Information retrieval, computational and theoretical aspects","author":"Heaps Harold Stanley","key":"e_1_3_2_2_16_1","unstructured":"Harold Stanley Heaps. 1978. Information retrieval, computational and theoretical aspects. Academic Press."},{"key":"e_1_3_2_2_17_1","first-page":"14","article-title":"Zipf's Law everywhere","volume":"5","author":"Li Wentian","year":"2002","unstructured":"Wentian Li. 2002. Zipf's Law everywhere. Glottometrics 5 (2002), 14--21.","journal-title":"Glottometrics"},{"key":"e_1_3_2_2_18_1","unstructured":"Edward Ma. 2019. NLP Augmentation. https:\/\/github.com\/makcedward\/nlpaug."},{"key":"e_1_3_2_2_19_1","first-page":"486","article-title":"An informational theory of the statistical structure of language","volume":"84","author":"Mandelbrot Benoit","year":"1953","unstructured":"Benoit Mandelbrot. 1953. An informational theory of the statistical structure of language. Communication Theory 84 (1953), 486--502.","journal-title":"Communication Theory"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.3.013084"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1177\/016555159301900401"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.physleta.2017.05.061"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2021.110679"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0147073"},{"key":"e_1_3_2_2_25_1","first-page":"261","article-title":"Information theoretic models in statistical linguistics-Part I: A model for word frequencies","volume":"63","author":"Naranan Sundaresan","year":"1992","unstructured":"Sundaresan Naranan and Vriddhachalam K. Balasubrahmanyan. 1992. Information theoretic models in statistical linguistics-Part I: A model for word frequencies. Current Science 63, 5 (1992), 261--269. http:\/\/www.jstor.org\/stable\/24095491","journal-title":"Current Science"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1080\/09296179808590110"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1002\/asi.4630360502"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1002\/asi.4630290303"},{"key":"e_1_3_2_2_29_1","first-page":"68","article-title":"Strong","volume":"20","author":"Perline Richard","year":"2005","unstructured":"Richard Perline. 2005. Strong, Weak and False Inverse Power Laws. Statist. Sci. 20, 1 (2005), 68--88.","journal-title":"Weak and False Inverse Power Laws. Statist. Sci."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/11671299_55"},{"volume-title":"chaos, power laws: Minutes from an infinite paradise","author":"Schroeder Manfred R.","key":"e_1_3_2_2_31_1","unstructured":"Manfred R. Schroeder. 1991. Fractals, chaos, power laws: Minutes from an infinite paradise. W. H. Freeman and Company, New York, NY, USA."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/0306-4573(76)90035-2"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLC.2005.1527331"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1975.10482469"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/636669.636684"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1080\/09296179608590062"},{"volume-title":"Selected studies of the principle of relative frequency in language","author":"Zipf George Kingsley","key":"e_1_3_2_2_37_1","unstructured":"George Kingsley Zipf. 1932. Selected studies of the principle of relative frequency in language. Harvard University Press."},{"volume-title":"Human Behavior and the Principle of Least Effort","author":"Zipf George Kingsley","key":"e_1_3_2_2_38_1","unstructured":"George Kingsley Zipf. 1949. Human Behavior and the Principle of Least Effort. Addison-Wesley, Cambridge, MA."}],"event":{"name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Taipei Taiwan","acronym":"SIGIR '23"},"container-title":["Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591942","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3591942","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:38:07Z","timestamp":1750178287000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591942"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":38,"alternative-id":["10.1145\/3539618.3591942","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3591942","relation":{},"subject":[],"published":{"date-parts":[[2023,7,18]]},"assertion":[{"value":"2023-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}