{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T09:09:20Z","timestamp":1747818560232},"publisher-location":"Berlin, Heidelberg","reference-count":13,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642405846"},{"type":"electronic","value":"9783642405853"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-40585-3_60","type":"book-chapter","created":{"date-parts":[[2013,8,17]],"date-time":"2013-08-17T06:15:02Z","timestamp":1376720102000},"page":"475-483","source":"Crossref","is-referenced-by-count":16,"title":["Selecting and Weighting N-Grams to Identify 1100 Languages"],"prefix":"10.1007","author":[{"given":"Ralf D.","family":"Brown","sequence":"first","affiliation":[]}],"member":"297","reference":[{"key":"60_CR1","doi-asserted-by":"crossref","unstructured":"Brown, R.D.: Finding and Identifying Text in 900+ Languages. Digital Investigation\u00a09, S34\u2013S43 (2012)","DOI":"10.1016\/j.diin.2012.05.004"},{"key":"60_CR2","unstructured":"Cavnar, W.B., Trenkle, J.M.: N-Gram-Based Text Categorization. In: Proceedings of SDAIR 1994, 3rd Annual Symposium on Document Analysis and Information Retrieval, UNLV Publications\/Reprographics, pp. 161\u2013175 (April 1994)"},{"key":"60_CR3","doi-asserted-by":"crossref","unstructured":"Ljube\u0161i\u0107, N., Mikeli\u0107, N., Boras, D.: Language identification: How to distinguish similar languages. In: Lu\u017ear-Stifter, V., Hljuz Dobri\u0107, V. (eds.) Proceedings of the 29th International Conference on Information Technology Interfaces, Zagreb, pp. 541\u2013546. SRCE University Computing Centre (2007)","DOI":"10.1109\/ITI.2007.4283829"},{"key":"60_CR4","unstructured":"Ahmed, B., Cha, S.H., Tappert, C.: Language Identification from Text Using N-gram Based Cumulative Frequency Addition. In: Proceedings of Student\/Faculty Research Day, CSIS, Pace University (May 2004)"},{"key":"60_CR5","unstructured":"Carter, S., Tsagkias, M., Weerkamp, W.: Semi-Supervised Priors for Microblog Language Identification. In: Proceedings of the Dutch-Belgian Information Retrieval Workshop (DIR 2011), Amsterdam (February 2011)"},{"issue":"5199","key":"60_CR6","doi-asserted-by":"publisher","first-page":"843","DOI":"10.1126\/science.267.5199.843","volume":"267","author":"M. Damashek","year":"1995","unstructured":"Damashek, M.: Gauging Similarity with n-grams: Language Independent Categorization of Text. Science\u00a0267(5199), 843\u2013848 (1995)","journal-title":"Science"},{"key":"60_CR7","unstructured":"Shuyo, N.: Language Detection Library - 99% over precision for 49 languages (December 2010), \n                    \n                      http:\/\/www.slideshare.net\/shuyo\/language-detection-library-for-java\n                    \n                    \n                   (accessed May 30, 2013)"},{"key":"60_CR8","doi-asserted-by":"crossref","unstructured":"Xia, F., Lewis, W.D., Poon, H.: Language ID in the Context of Harvesting Language Data off the Web. In: Proceedings of EACL 2009, pp. 870\u2013878 (2009)","DOI":"10.3115\/1609067.1609164"},{"key":"60_CR9","unstructured":"Likasoft: Polyglot 3000, \n                    \n                      http:\/\/polyglot3000.com\n                    \n                    \n                   (accessed May 30, 2013)"},{"key":"60_CR10","unstructured":"United Bible Societies: Scripture Language Report 2011 (2011), \n                    \n                      http:\/\/www.unitedbiblesocieties.org\/wp-content\/uploads\/2012\/04\/-report-TABLE-I-2011-Rec-March-28.doc\n                    \n                    \n                   (accessed May 30, 2013)"},{"key":"60_CR11","unstructured":"Hugueney, B.: libtextcat 2.2-9: Faster Unicode-focused C++ reimplementation of libtextcat (2011), \n                    \n                      https:\/\/github.com\/scientific-coder\/libtextcat\n                    \n                    \n                   (accessed May 30, 2013)"},{"key":"60_CR12","unstructured":"Barkov, A.: mguesser version 0.4 (2008), \n                    \n                      http:\/\/www.mnogosearch.org\/guesser\/mguesser-0.4.tar.gz\n                    \n                    \n                   (accessed May 30, 2013)"},{"key":"60_CR13","unstructured":"Shuyo, N.: Language Detection Library for Java, \n                    \n                      http:\/\/code.google.com\/p\/language-detection\/\n                    \n                    \n                   (accessed May 30, 2013)"}],"container-title":["Lecture Notes in Computer Science","Text, Speech, and Dialogue"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-40585-3_60","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,16]],"date-time":"2019-05-16T14:04:02Z","timestamp":1558015442000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-40585-3_60"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642405846","9783642405853"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-40585-3_60","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}