{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T13:47:05Z","timestamp":1725544025328},"publisher-location":"Berlin, Heidelberg","reference-count":14,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540346166"},{"type":"electronic","value":"9783540346173"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11765448_14","type":"book-chapter","created":{"date-parts":[[2006,7,3]],"date-time":"2006-07-03T20:38:56Z","timestamp":1151959136000},"page":"153-163","source":"Crossref","is-referenced-by-count":8,"title":["Language Identification in Multi-lingual Web-Documents"],"prefix":"10.1007","author":[{"given":"Thomas","family":"Mandl","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Margaryta","family":"Shramko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Olga","family":"Tartakovski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christa","family":"Womser-Hacker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"14_CR1","unstructured":"Artemenko, O., Shramko, M.: Entwicklung eines Werkzeugs zur Sprachidentifikation in mono- und multilingualen Texten. Master thesis. University of Hildesheim (2005), http:\/\/web1.bib.uni-hildesheim.de\/2005\/artemenko_shramko.pdf"},{"key":"14_CR2","unstructured":"Cavnar, W.B., Trenkle, J.M.: N-Gram-Based Text Categorization. Symposion on Document Analysis and Information Retrieval, pp. 161\u2013176. Univ. of Nevada, Las Vegas"},{"key":"14_CR3","unstructured":"Cowie, J., Ludovik, E., Zacharski, R.: An Autonomous, Web-based, Multilingual Corpus Collection Tool. In: Proc. Intl. Conference on Natural Language Processing and Industrial Applications, Moncton, pp. 142\u2013148 (1998)"},{"key":"14_CR4","unstructured":"Grefenstette, G.: Comparing two language identification schemes. In: JADT 1995. 3rd International conference on Statistical Analysis of Textual Data, Rome (1995)"},{"issue":"1-2","key":"14_CR5","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1023\/B:INRT.0000009439.19151.4c","volume":"7","author":"V. Hollink","year":"2004","unstructured":"Hollink, V., Kamps, J., Monz, C., de Rijke, M.: Monolingual Document Retrieval for European Languages. Information Retrieval\u00a07(1-2), 33\u201352 (2004)","journal-title":"Information Retrieval"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Kikui, G.: Identifying the Coding System and Language of On-line Documents on the Internet. In: Proc 16th Conf. on Computational linguistics, Denmark, vol.\u00a02, pp. 652\u2013657 (1996)","DOI":"10.3115\/993268.993282"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Kralisch, A., Mandl T.: Barriers of Information Access across Languages on the Internet: Network and Language Effects. In: Proc. Hawaii International Conference on System Sciences (HICSS-39) (2006)","DOI":"10.1109\/HICSS.2006.71"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Lins, R., Gon\u00e7alves, P.: Automatic Language Identification of Written Texts. In: Proc. ACM SAC Symposium on Applied Computing, Nicosia, Cyprus, pp. 1128\u20131133 (March 2004)","DOI":"10.1145\/967900.968129"},{"key":"14_CR9","unstructured":"Martino, M., Paulsen, R.: Natural language determination using partial words, U.S. Patent No. 6216102 B1 (April 2001)"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Martins, B., Silva, M.: Language Identification in Web Pages. In: Proc. ACM SAC Symposium on Applied Computing, Santa Fe, New Mexico, USA, March 13-17, 2005, pp. 764\u2013768 (2005)","DOI":"10.1145\/1066677.1066852"},{"issue":"1\/2","key":"14_CR11","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1023\/B:INRT.0000009441.78971.be","volume":"7","author":"P. McNamee","year":"2004","unstructured":"McNamee, P., Mayfield, J.: Character N-Gram Tokenization for European Language Text Retrieval. Information Retrieval\u00a07(1\/2), 73\u201398 (2004)","journal-title":"Information Retrieval"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Prager, J.: Linguini: Language Identification for Multilingual Documents. In: Proc. 32nd Hawaii International Conf. on System Sciences (1999)","DOI":"10.1109\/HICSS.1999.772689"},{"key":"14_CR13","unstructured":"Sigurbj\u00f6rnsson, B., Kamps, J., de Rijke, M.: Blueprint of a cross-lingual web retrieval collection. Journal on Digital Information Management\u00a03(9-13) (2005)"},{"key":"14_CR14","first-page":"183","volume":"13","author":"C. Souter","year":"1994","unstructured":"Souter, C., Churcher, G., Hayes, J., Hughes, J., Johnson, S.: Natural Language Identification Using Corpus-Based Models. Hermes J. Linguistics\u00a013, 183\u2013203 (1994)","journal-title":"Hermes J. Linguistics"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Information Systems"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11765448_14.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T03:11:02Z","timestamp":1619493062000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11765448_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540346166","9783540346173"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/11765448_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2006]]}}}