{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T14:25:51Z","timestamp":1774880751402,"version":"3.50.1"},"reference-count":27,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011,9]]},"DOI":"10.1109\/icdim.2011.6093324","type":"proceedings-article","created":{"date-parts":[[2011,12,6]],"date-time":"2011-12-06T15:59:24Z","timestamp":1323187164000},"page":"73-78","source":"Crossref","is-referenced-by-count":4,"title":["Index-based n-gram extraction from large document collections"],"prefix":"10.1109","author":[{"given":"Michal","family":"Kratky","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Radim","family":"Baca","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Bednar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiri","family":"Walder","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiri","family":"Dvorsky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Chovanec","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","author":"garcia-molina","year":"2008","journal-title":"Database Systems The Complete Book"},{"key":"ref11","author":"lightstone","year":"2007","journal-title":"Physical Database Design the Database Professional's Guide"},{"key":"ref12","first-page":"223","article-title":"The Virtual Corpus Approach to Deriving Ngram Statistics from Large Scale Corpora","author":"kit","year":"0","journal-title":"Proceedings of 1998 International Conference on Chinese Information Processing (1998)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/089120101300346787"},{"key":"ref14","article-title":"TREC Web Corpus","year":"2009","journal-title":"GOV"},{"key":"ref15","year":"2010","journal-title":"The British National Corpus (BNC)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BF00288683"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/356770.356776"},{"key":"ref18","author":"knuth","year":"1998","journal-title":"The Art of Computer Programming' 3 Sorting and Searching"},{"key":"ref19","author":"manolopoulos","year":"2001","journal-title":"Advanced Database Indexing"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-00958-7_69"},{"key":"ref27","author":"samet","year":"2006","journal-title":"Foundations of Multidimensional and Metric Data Structures"},{"key":"ref3","first-page":"132","article-title":"Detecting Co-Derivative Documents in Large Text Collections","author":"pomik\u00e1lek","year":"0","journal-title":"Proceedings of the Sixth International Language Resources and Evaluation (LREC'08)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30213-1_6"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"277","DOI":"10.4156\/jcit.vol6.issue3.31","article-title":"A copy detection method for chinese text by character based n-gram","volume":"6","author":"zhang","year":"2011","journal-title":"JCIT Journal of Convergence Information Technology"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/772755.772759"},{"key":"ref7","article-title":"Language identification from text using n-gram based cumulative frequency addition","author":"ahmed","year":"0","journal-title":"Proceedings of CSIS 2004"},{"key":"ref2","first-page":"209","article-title":"Teraman: A tool for n-gram extraction from large datasets","author":"ce\u0161ka","year":"0","journal-title":"Intelligent Computer Communication and Processing 2007 IEEE International Conference on"},{"key":"ref9","author":"baeza-yates","year":"1999","journal-title":"Modern Information Retrieval"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/223784.223855"},{"key":"ref20","author":"ceska","year":"2009","journal-title":"Teraman Tool"},{"key":"ref22","author":"le","year":"2010","journal-title":"NGram Extraction Tool"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/991886.991994"},{"key":"ref24","first-page":"121","article-title":"A comparison of two algorithms for discovering repeated word sequences","author":"tesar","year":"2005","journal-title":"In Data mining VI Southampton"},{"key":"ref23","author":"fletcher","year":"2010","journal-title":"kfNgram Tool"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1075\/ijcl.10.3.02dav"},{"key":"ref25","author":"berkeley","year":"2011","journal-title":"Berkeley DB"}],"event":{"name":"2011 Sixth International Conference on Digital Information Management (ICDIM)","location":"Melbourne, Australia","start":{"date-parts":[[2011,9,26]]},"end":{"date-parts":[[2011,9,28]]}},"container-title":["2011 Sixth International Conference on Digital Information Management"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6082065\/6093313\/06093324.pdf?arnumber=6093324","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,20]],"date-time":"2017-06-20T06:53:10Z","timestamp":1497941590000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6093324\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,9]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icdim.2011.6093324","relation":{},"subject":[],"published":{"date-parts":[[2011,9]]}}}