{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:55:12Z","timestamp":1780588512867,"version":"3.54.1"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2010,1,30]],"date-time":"2010-01-30T00:00:00Z","timestamp":1264809600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Lang Resources & Evaluation"],"published-print":{"date-parts":[[2011,3]]},"DOI":"10.1007\/s10579-009-9114-z","type":"journal-article","created":{"date-parts":[[2010,1,29]],"date-time":"2010-01-29T03:58:04Z","timestamp":1264737484000},"page":"45-62","source":"Crossref","is-referenced-by-count":135,"title":["Cross-language plagiarism detection"],"prefix":"10.1007","volume":"45","author":[{"given":"Martin","family":"Potthast","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alberto","family":"Barr\u00f3n-Cede\u00f1o","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benno","family":"Stein","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paolo","family":"Rosso","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2010,1,30]]},"reference":[{"key":"9114_CR1","unstructured":"Ballesteros, L. A. (2001). Resolving ambiguity for cross-language information retrieval: A dictionary approach. PhD thesis, University of Massachusetts Amherst, USA, Bruce Croft."},{"key":"9114_CR2","unstructured":"Barr\u00f3n-Cede\u00f1o, A., Rosso, P., Pinto, D., & Juan A. (2008). On cross-lingual plagiarism analysis using a statistical model. In S. Benno, S. Efstathios, & K. Moshe (Eds.), ECAI 2008 workshop on uncovering plagiarism, authorship, and social software misuse (PAN 08) (pp. 9\u201313). Patras, Greece."},{"key":"9114_CR3","first-page":"1","volume":"3","author":"L. E. Baum","year":"1972","unstructured":"Baum, L. E. (1972). An inequality and associated maximization technique in statistical estimation of probabilistic functions of a Markov process. Inequalities, 3, 1\u20138.","journal-title":"Inequalities"},{"key":"9114_CR4","unstructured":"Berger, A., & Lafferty, J. (1999). Information retrieval as statistical translation. In SIGIR\u201999: Proceedings of the 22nd annual international ACM SIGIR conference on research and development in information retrieval (vol. 4629, pp. 222\u2013229). Berkeley, California, United States: ACM."},{"key":"9114_CR5","unstructured":"Brin, S., Davis, J., & Garcia-Molina, H. (1995). Copy detection mechanisms for digital documents. In SIGMOD \u201995 (pp. 398\u2013409). New York, NY, USA: ACM Press."},{"issue":"2","key":"9114_CR6","first-page":"263","volume":"19","author":"P. F. Brown","year":"1993","unstructured":"Brown, P. F., Della Pietra, S. A., Della Pietra, V. J., & Mercer R. L. (1993). The mathematics of statistical machine translation: Parameter estimation. Computational Linguistics, 19(2), 263\u2013311.","journal-title":"Computational Linguistics"},{"key":"9114_CR7","unstructured":"Ceska, Z., Toman, M., & Jezek, K. (2008). Multilingual plagiarism detection. In AIMSA\u201908: Proceedings of the 13th international conference on artificial intelligence (pp. 83\u201392). Berlin, Heidelberg: Springer."},{"key":"9114_CR8","unstructured":"Clough, P. (2003). Old and new challenges in automatic plagiarism detection. National UK Plagiarism Advisory Service, http:\/\/www.ir.shef.ac.uk\/cloughie\/papers\/pas_plagiarism.pdf ."},{"issue":"1","key":"9114_CR9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"A. P. Dempster","year":"1977","unstructured":"Dempster A. P., Laird N. M., Rubin D. B. (1977). Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society. Series B (Methodological), 39(1), 1\u201338.","journal-title":"Journal of the Royal Statistical Society. Series B (Methodological)"},{"key":"9114_CR11","unstructured":"Dumais, S. T., Letsche, T. A., Littman, M. L., & Landauer, T. K. (1997). Automatic cross-language retrieval using latent semantic indexing. In D. Hull & D. Oard (Eds.), AAAI-97 spring symposium series: Cross-language text and speech retrieval (pp. 18\u201324). Stanford University, American Association for Artificial Intelligence."},{"key":"9114_CR12","unstructured":"Gabrilovich, E., & Markovitch, S. (2007). Computing semantic relatedness using Wikipedia-based explicit semantic analysis. In Proceedings of the 20th international joint conference for artificial intelligence, Hyderabad, India."},{"issue":"3","key":"9114_CR13","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1002\/asi.10170","volume":"54","author":"T. C. Hoad","year":"2003","unstructured":"Hoad T. C., & Zobel, J. (2003). Methods for identifying versioned and plagiarised documents. American Society for Information Science and Technology, 54(3), 203\u2013215.","journal-title":"American Society for Information Science and Technology"},{"issue":"3","key":"9114_CR14","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1016\/j.ipm.2004.06.012","volume":"41","author":"G.-A. Levow","year":"2005","unstructured":"Levow, G.-A., Oard, D. W., & Resnik, P. (2005). Dictionary-based techniques for cross-language information retrieval. Information Processing & Management, 41(3), 523\u2013547.","journal-title":"Information Processing & Management"},{"key":"9114_CR15","doi-asserted-by":"crossref","unstructured":"Littman, M., Dumais, S. T., & Landauer, T. K. (1998). Automatic cross-language information retrieval using latent semantic indexing. In Cross-language information retrieval, chap. 5 (pp. 51\u201362). Kluwer.","DOI":"10.1007\/978-1-4615-5661-9_5"},{"issue":"8","key":"9114_CR16","first-page":"1050","volume":"12","author":"H. Maurer","year":"2006","unstructured":"Maurer, H., Kappe, F., & Zaka, B. (2006). Plagiarism\u2014a survey. Journal of Universal Computer Science, 12(8), 1050\u20131084.","journal-title":"Journal of Universal Computer Science"},{"key":"9114_CR10","unstructured":"McCabe, D. (2005). Research report of the Center for Academic Integrity. http:\/\/www.academicintegrity.org ."},{"issue":"1-2","key":"9114_CR17","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1023\/B:INRT.0000009441.78971.be","volume":"7","author":"P. Mcnamee","year":"2004","unstructured":"Mcnamee, P., & Mayfield, J. (2004). Character N-gram tokenization for European language text retrieval. Information Retrieval, 7(1\u20132), 73\u201397.","journal-title":"Information Retrieval"},{"key":"9114_CR18","doi-asserted-by":"crossref","unstructured":"Meyer zu Eissen, S., & Stein, B. (2006). Intrinsic plagiarism detection. In M. Lalmas, A. MacFarlane, S. M. R\u00fcger, A. Tombros, T. Tsikrika, & A. Yavlinsky (Eds.), Proceedings of the European conference on information retrieval (ECIR 2006), volume 3936 of Lecture Notes in Computer Science (pp. 565\u2013569). Springer.","DOI":"10.1007\/11735106_66"},{"key":"9114_CR19","doi-asserted-by":"crossref","unstructured":"Meyer zu Eissen, S., Stein, B., & Kulig, M. (2007). Plagiarism detection without reference collections. In R. Decker & H. J. Lenz (Eds.), Advances in data analysis (pp. 359\u2013366), Springer.","DOI":"10.1007\/978-3-540-70981-7_40"},{"issue":"1","key":"9114_CR20","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1162\/089120103321337421","volume":"29","author":"F. J. Och","year":"2003","unstructured":"Och, F. J., & Ney, H. (2003). A systematic comparison of various statistical alignment models. Computational Linguistics, 29(1), 19\u201351.","journal-title":"Computational Linguistics"},{"key":"9114_CR21","doi-asserted-by":"crossref","unstructured":"Pinto, D., Juan, A., & Rosso, P. (2007). Using query-relevant documents pairs for cross-lingual information retrieval. In V. Matousek & P. Mautner (Eds.), Lecture Notes in Artificial Intelligence (pp. 630\u2013637). Pilsen, Czech Republic.","DOI":"10.1007\/978-3-540-74628-7_81"},{"issue":"1","key":"9114_CR22","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.jalgor.2009.02.005","volume":"64","author":"D. Pinto","year":"2009","unstructured":"Pinto, D., Civera, J., Barr\u00f3n-Cede\u00f1o, A., Juan, A., & Rosso, P. (2009). A statistical approach to cross-lingual natural language tasks. Journal of Algorithms, 64(1), 51\u201360.","journal-title":"Journal of Algorithms"},{"key":"9114_CR23","unstructured":"Potthast, M. (2007). Wikipedia in the pocket-indexing technology for near-duplicate detection and high similarity search. In C. Clarke, N. Fuhr, N. Kando, W. Kraaij, & A. de Vries (Eds.), 30th Annual international ACM SIGIR conference (pp. 909\u2013909). ACM."},{"key":"9114_CR24","unstructured":"Potthast, M., Stein, B., & Anderka, M. (2008). A Wikipedia-based multilingual retrieval model. In C. Macdonald, I. Ounis, V. Plachouras, I. Ruthven, & R. W. White (Eds.), 30th European conference on IR research, ECIR 2008, Glasgow , volume 4956 LNCS of Lecture Notes in Computer Science (pp. 522\u2013530). Berlin: Springer."},{"key":"9114_CR25","unstructured":"Pouliquen, B., Steinberger, R., & Ignat, C. (2003a). Automatic annotation of multilingual text collections with a conceptual thesaurus. In Proceedings of the workshop \u2019ontologies and information extraction\u2019 at the Summer School \u2019The Semantic Web and Language Technology\u2014its potential and practicalities\u2019 (EUROLAN\u20192003) (pp. 9\u201328), Bucharest, Romania."},{"key":"9114_CR26","unstructured":"Pouliquen, B., Steinberger, R., & Ignat, C. (2003b). Automatic identification of document translations in large multilingual document collections. In Proceedings of the international conference recent advances in natural language processing (RANLP\u20192003) (pp. 401\u2013408). Borovets, Bulgaria."},{"key":"9114_CR27","doi-asserted-by":"crossref","unstructured":"Stein, B. (2007). Principles of hash-based text retrieval. In C. Clarke, N. Fuhr, N. Kando, W. Kraaij, & A. de Vries (Eds.), 30th Annual international ACM SIGIR conference (pp. 527\u2013534). ACM.","DOI":"10.1145\/1277741.1277832"},{"key":"9114_CR28","unstructured":"Stein, B. (2005). Fuzzy-fingerprints for text-based information retrieval. In K. Tochtermann & H. Maurer (Eds.), Proceedings of the 5th international conference on knowledge management (I-KNOW 05), Graz, Journal of Universal Computer Science. (pp. 572\u2013579). Know-Center."},{"key":"9114_CR29","doi-asserted-by":"crossref","unstructured":"Stein, B., & Anderka, M. (2009). Collection-relative representations: A unifying view to retrieval models. In A. M. Tjoa & R. R. Wagner (Eds.), 20th International conference on database and expert systems applications (DEXA 09) (pp. 383\u2013387). IEEE.","DOI":"10.1109\/DEXA.2009.50"},{"key":"9114_CR30","unstructured":"Stein, B., & Meyer zu Eissen, S. (2007). Intrinsic plagiarism analysis with meta learning. In B. Stein, M. Koppel, & E. Stamatatos (Eds.), SIGIR workshop on plagiarism analysis, authorship identification, and near-duplicate detection (PAN 07) (pp. 45\u201350). CEUR-WS.org."},{"key":"9114_CR31","unstructured":"Stein, B., & Potthast, M. (2007). Construction of compact retrieval models. In S. Dominich & F. Kiss (Eds.), Studies in theory of information retrieval (pp. 85\u201393). Foundation for Information Society."},{"key":"9114_CR32","doi-asserted-by":"crossref","unstructured":"Stein, B., Meyer zu Eissen, S., & Potthast, M. (2007). Strategies for retrieving plagiarized documents. In C. Clarke, N. Fuhr, N. Kando, W. Kraaij, & A. de Vries (Eds.), 30th Annual international ACM SIGIR conference (pp. 825\u2013826). ACM.","DOI":"10.1145\/1277741.1277928"},{"key":"9114_CR33","unstructured":"Steinberger, R., Pouliquen, B., Widiger, A., Ignat, C., Erjavec, T., Tufis, D., & Varga, D. (2006). The JRC-Acquis: A multilingual aligned parallel corpus with 20+ languages. In Proceedings of the 5th international conference on language resources and evaluation (LREC\u20192006)."},{"key":"9114_CR34","unstructured":"Steinberger, R., Pouliquen, B., & Ignat, C. (2004). Exploiting multilingual nomenclatures and language-independent text features as an interlingua for cross-lingual text analysis applications. In Proceedings of the 4th Slovenian language technology conference. Information Society 2004 (IS\u20192004)."},{"key":"9114_CR35","unstructured":"Vinokourov, A., Shawe-Taylor, J., & Cristianini, N. (2003). Inferring a semantic representation of text via cross-language correlation analysis. In S. Becker, S. Thrun, & K. Obermayer (Eds.), NIPS-02: Advances in neural information processing systems (pp. 1473\u20131480). MIT Press."},{"issue":"1-2","key":"9114_CR36","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1016\/S0004-3702(98)00063-0","volume":"103","author":"Y. Yang","year":"1998","unstructured":"Yang, Y., Carbonell, J. G., Brown, R. D., & Frederking, R. E. (1998). Translingual information retrieval: Learning from bilingual corpora. Artificial Intelligence, 103(1\u20132), 323\u2013345.","journal-title":"Artificial Intelligence"}],"container-title":["Language Resources and Evaluation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-009-9114-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10579-009-9114-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-009-9114-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,30]],"date-time":"2019-05-30T14:21:15Z","timestamp":1559226075000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10579-009-9114-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,1,30]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2011,3]]}},"alternative-id":["9114"],"URL":"https:\/\/doi.org\/10.1007\/s10579-009-9114-z","relation":{},"ISSN":["1574-020X","1574-0218"],"issn-type":[{"value":"1574-020X","type":"print"},{"value":"1574-0218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,1,30]]}}}