{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T11:04:26Z","timestamp":1759230266019,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030227401"},{"type":"electronic","value":"9783030227418"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-22741-8_6","type":"book-chapter","created":{"date-parts":[[2019,6,7]],"date-time":"2019-06-07T15:02:45Z","timestamp":1559919765000},"page":"75-88","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["n-gram Cache Performance in Statistical Extraction of Relevant Terms in Large Corpora"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9113-6269","authenticated-orcid":false,"given":"Carlos","family":"Goncalves","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5223-1180","authenticated-orcid":false,"given":"Joaquim F.","family":"Silva","sequence":"additional","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":[[2019,6,8]]},"reference":[{"unstructured":"Google Ngram Viewer. https:\/\/books.google.com\/ngrams","key":"6_CR1"},{"unstructured":"Lin, D., et al.: New tools for web-scale n-grams. In: LREC (2010)","key":"6_CR2"},{"key":"6_CR3","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/3-540-48159-1_9","volume-title":"Progress in Artificial Intelligence","author":"JF da Silva","year":"1999","unstructured":"da Silva, J.F., Dias, G., Guillor\u00e9, S., Pereira Lopes, J.G.: Using LocalMaxs algorithm for the extraction of contiguous and non-contiguous multiword lexical units. In: Barahona, P., Alferes, J.J. (eds.) EPIA 1999. LNCS (LNAI), vol. 1695, pp. 113\u2013132. Springer, Heidelberg (1999). https:\/\/doi.org\/10.1007\/3-540-48159-1_9"},{"unstructured":"da Silva, J.F., et al.: A local maxima method and a fair dispersion normalization for extracting multiword units. In: Proceedings of the 6th Meeting on the Mathematics of Language, pp. 369\u2013381 (1999)","key":"6_CR4"},{"doi-asserted-by":"crossref","unstructured":"da Silva, J.F., et al.: A theoretical model for n-gram distribution in big data corpora. In: IEEE International Conference on Big Data, pp. 134\u2013141 (2016)","key":"6_CR5","DOI":"10.1109\/BigData.2016.7840598"},{"unstructured":"Parallel LocalMaxs. http:\/\/cjsg.ddns.net\/~cajo\/phd\/","key":"6_CR6"},{"issue":"9","key":"6_CR7","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1016\/j.parco.2014.06.007","volume":"40","author":"D Arroyuelo","year":"2014","unstructured":"Arroyuelo, D., et al.: Distributed text search using suffix arrays. Parallel Comput. 40(9), 471\u2013495 (2014)","journal-title":"Parallel Comput."},{"doi-asserted-by":"crossref","unstructured":"Goncalves, C., et al.: A parallel algorithm for statistical multiword term extraction from very large corpora. In: IEEE 17th International Conference on High Performance Computing and Communications, pp. 219\u2013224 (2015)","key":"6_CR8","DOI":"10.1109\/HPCC-CSS-ICESS.2015.72"},{"doi-asserted-by":"crossref","unstructured":"Goncalves, C., et al.: An n-gram cache for large-scale parallel extraction of multiword relevant expressions with LocalMaxs. In: IEEE 12th International Conference on e-Science, pp. 120\u2013129. IEEE Computer Society (2016)","key":"6_CR9","DOI":"10.1109\/eScience.2016.7870892"},{"issue":"7","key":"6_CR10","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1145\/362686.362692","volume":"13","author":"BH Bloom","year":"1970","unstructured":"Bloom, B.H.: Space\/Time trade-offs in hash coding with allowable errors. Commun. ACM 13(7), 422\u2013426 (1970)","journal-title":"Commun. ACM"},{"unstructured":"Daille, B.: Study and implementation of combined techniques for automatic extraction of terminology. In: The Balancing Act: Combining Symbolic and Statistical Approaches to Language. MIT Press (1996)","key":"6_CR11"},{"issue":"5","key":"6_CR12","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/MIS.2008.88","volume":"23","author":"P Velardi","year":"2008","unstructured":"Velardi, P., et al.: Mining the web to create specialized glossaries. IEEE Intell. Syst. 23(5), 18\u201325 (2008)","journal-title":"IEEE Intell. Syst."},{"unstructured":"Pearce, D.: A comparative evaluation of collocation extraction techniques. In: 3rd International Conference on Language Resources and Evaluation (2002)","key":"6_CR13"},{"key":"6_CR14","first-page":"22","volume":"16","author":"KW Church","year":"1990","unstructured":"Church, K.W., et al.: Word association norms, mutual information, and lexicography. Comput. Linguist. 16, 22\u201329 (1990)","journal-title":"Comput. Linguist."},{"key":"6_CR15","first-page":"61","volume":"19","author":"T Dunning","year":"1993","unstructured":"Dunning, T.: Accurate methods for the statistics of surprise and coincidence. Comput. Linguist. 19, 61\u201374 (1993)","journal-title":"Comput. Linguist."},{"unstructured":"Church, K.W., et al.: Concordance for parallel texts. In: 7th Annual Conference for the new OED and Text Research, pp. 40\u201362 (1991)","key":"6_CR16"},{"unstructured":"Goncalves, C.: Parallel and distributed statistical-based extraction of relevant multiwords from large corpora. Ph.D. dissertation, FCT\/UNL (2017)","key":"6_CR17"},{"key":"6_CR18","volume-title":"The Psychobiology of Language: An Introduction to Dynamic Philology","author":"GK Zipf","year":"1935","unstructured":"Zipf, G.K.: The Psychobiology of Language: An Introduction to Dynamic Philology. MIT Press, Cambridge (1935)"},{"doi-asserted-by":"crossref","unstructured":"Mandelbrot, B.B.: On the theory of word frequencies and on related Markovian models of discourse. In: Structures of Language and its Mathematical Aspects, vol. 12, pp. 134\u2013141. American Mathematical Society (1961)","key":"6_CR19","DOI":"10.1090\/psapm\/012\/9970"},{"doi-asserted-by":"crossref","unstructured":"Kuhn, R.: Speech recognition and the frequency of recently used words: a modified Markov model for natural language. In: Proceedings of the 12th Conference on Computational Linguistics, COLING 1988, vol. 1, pp. 348\u2013350. ACM (1988)","key":"6_CR20","DOI":"10.3115\/991635.991706"},{"unstructured":"Breslau, L., et al.: Web caching and Zipf-like distributions: evidence and implications. In: Eighteenth Annual Joint Conference of the IEEE Computer and Communications Societies, INFOCOM 1999, vol. 1, pp. 126\u2013134, March 1999","key":"6_CR21"},{"doi-asserted-by":"crossref","unstructured":"Baeza-Yates, R., et al.: The impact of caching on search engines. In: Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2007, pp. 183\u2013190. ACM (2007)","key":"6_CR22","DOI":"10.1145\/1277741.1277775"},{"issue":"4","key":"6_CR23","doi-asserted-by":"publisher","first-page":"1050","DOI":"10.1109\/TKDE.2003.1209022","volume":"15","author":"Q Yang","year":"2003","unstructured":"Yang, Q., et al.: Web-log mining for predictive web caching. IEEE Trans. Knowl. Data Eng. 15(4), 1050\u20131053 (2003)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"doi-asserted-by":"crossref","unstructured":"Balkir, A.S., et al.: A distributed look-up architecture for text mining applications using MapReduce. In: International Conference for High Performance Computing, Networking, Storage and Analysis (SC), pp. 1\u201311 (2011)","key":"6_CR24","DOI":"10.1145\/2063384.2063463"},{"unstructured":"Luna Cloud. http:\/\/www.lunacloud.com","key":"6_CR25"},{"unstructured":"Brants, T., et al.: Large language models in machine translation. In: Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pp. 858\u2013867 (2007)","key":"6_CR26"}],"container-title":["Lecture Notes in Computer Science","Computational Science \u2013 ICCS 2019"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-22741-8_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,7]],"date-time":"2023-06-07T03:27:26Z","timestamp":1686108446000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-22741-8_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030227401","9783030227418"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-22741-8_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"8 June 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Faro","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 June 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 June 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccs-computsci2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iccs-meeting.org\/iccs2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}