{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T14:47:37Z","timestamp":1775054857924,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":17,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642332463","type":"print"},{"value":"9783642332470","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-33247-0_8","type":"book-chapter","created":{"date-parts":[[2012,9,11]],"date-time":"2012-09-11T22:41:12Z","timestamp":1347403272000},"page":"67-75","source":"Crossref","is-referenced-by-count":15,"title":["Cross-Language High Similarity Search Using a Conceptual Thesaurus"],"prefix":"10.1007","author":[{"given":"Parth","family":"Gupta","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alberto","family":"Barr\u00f3n-Cede\u00f1o","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paolo","family":"Rosso","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"8_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/3-540-45123-4_1","volume-title":"Combinatorial Pattern Matching","author":"A.Z. Broder","year":"2000","unstructured":"Broder, A.Z.: Identifying and Filtering Near-Duplicate Documents. In: Giancarlo, R., Sankoff, D. (eds.) CPM 2000. LNCS, vol.\u00a01848, pp. 1\u201310. Springer, Heidelberg (2000)"},{"key":"8_CR2","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1145\/506309.506311","volume":"20","author":"A. Chowdhury","year":"2002","unstructured":"Chowdhury, A., Frieder, O., Grossman, D., McCabe, M.C.: Collection Statistics for Fast Duplicate Document Detection. ACM Trans. Inf. Syst.\u00a020, 171\u2013191 (2002)","journal-title":"ACM Trans. Inf. Syst."},{"key":"8_CR3","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1145\/509907.509965","volume-title":"Proceedings of the Thiry-fourth Annual ACM Symposium on Theory of Computing, STOC 2002","author":"M.S. Charikar","year":"2002","unstructured":"Charikar, M.S.: Similarity Estimation Techniques from Rounding Algorithms. In: Proceedings of the Thiry-fourth Annual ACM Symposium on Theory of Computing, STOC 2002, pp. 380\u2013388. ACM, New York (2002)"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Kolcz, A., Chowdhury, A., Alspector, J.: Improved Robustness of Signature-based Near-Replica Detection via Lexicon Randomization. In: Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2004, pp. 605\u2013610 (2004)","DOI":"10.1145\/1014052.1014127"},{"key":"8_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1007\/978-3-642-12275-0_66","volume-title":"Advances in Information Retrieval","author":"M. Anderka","year":"2010","unstructured":"Anderka, M., Stein, B., Potthast, M.: Cross-Language High Similarity Search: Why No Sub-linear Time Bound Can Be Expected. In: Gurrin, C., He, Y., Kazai, G., Kruschwitz, U., Little, S., Roelleke, T., R\u00fcger, S., van Rijsbergen, K. (eds.) ECIR 2010. LNCS, vol.\u00a05993, pp. 640\u2013644. Springer, Heidelberg (2010)"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Ture, F., Elsayed, T., Lin, J.J.: No Free Lunch: Brute Force vs. Locality-Sensitive Hashing for Cross-Lingual Pairwise Similarity. In: Proceeding of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2011, pp. 943\u2013952 (2011)","DOI":"10.1145\/2009916.2010042"},{"issue":"1","key":"8_CR7","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/1327452.1327492","volume":"51","author":"J. Dean","year":"2008","unstructured":"Dean, J., Ghemawat, S.: MapReduce: Simplified Data Processing on Large Clusters. Commun. ACM\u00a051(1), 107\u2013113 (2008)","journal-title":"Commun. ACM"},{"key":"8_CR8","unstructured":"Platt, J., Toutanova, K., tau Yih, W.: Translingual Document Representations from Discriminative Projections. In: Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing. EMNLP 2010, pp. 251\u2013261 (2010)"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Pouliquen, B., Steinberger, R., Ignat, C.: Automatic Linking of Similar Texts Across Languages. In: Recent Advances in Natural Language Processing III. Selected Papers from RANLP 2003, pp. 307\u2013316 (2003)","DOI":"10.1075\/cilt.260.34pou"},{"key":"8_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/3-540-45715-1_44","volume-title":"Computational Linguistics and Intelligent Text Processing","author":"R. Steinberger","year":"2002","unstructured":"Steinberger, R., Pouliquen, B., Hagman, J.: Cross-Lingual Document Similarity Calculation Using the Multilingual Thesaurus EUROVOC. In: Gelbukh, A. (ed.) CICLing 2002. LNCS, vol.\u00a02276, pp. 415\u2013424. Springer, Heidelberg (2002)"},{"key":"8_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1007\/978-3-540-78646-7_51","volume-title":"Advances in Information Retrieval","author":"M. Potthast","year":"2008","unstructured":"Potthast, M., Stein, B., Anderka, M.: A Wikipedia-Based Multilingual Retrieval Model. In: Macdonald, C., Ounis, I., Plachouras, V., Ruthven, I., White, R.W. (eds.) ECIR 2008. LNCS, vol.\u00a04956, pp. 522\u2013530. Springer, Heidelberg (2008)"},{"key":"8_CR12","first-page":"263","volume":"19","author":"P.F. Brown","year":"1993","unstructured":"Brown, P.F., Pietra, V.J.D., Pietra, S.A.D., Mercer, R.L.: The Mathematics of Statistical Machine Translation: Parameter Estimation. Comput. Linguist.\u00a019, 263\u2013311 (1993)","journal-title":"Comput. Linguist."},{"key":"8_CR13","unstructured":"Barr\u00f3n-Cede\u00f1o, A., Rosso, P., Pinto, D., Juan, A.: On Cross-lingual Plagiarism Analysis using a Statistical Model. In: Proceedings of the ECAI 2008 Workshop on Uncovering Plagiarism, Authorship and Social Software Misuse, PAN 2008 (2008)"},{"key":"8_CR14","doi-asserted-by":"publisher","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.: A Statistical Approach to Crosslingual Natural Language Tasks. J. Algorithms\u00a064, 51\u201360 (2009)","journal-title":"J. Algorithms"},{"issue":"1-2","key":"8_CR15","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. Inf. Retr.\u00a07(1-2), 73\u201397 (2004)","journal-title":"Inf. Retr."},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Potthast, M., Barr\u00f3n-Cede\u00f1o, A., Stein, B., Rosso, P.: Cross-Language Plagiarism Detection. Language Resources and Evaluation, Special Issue on Plagiarism and Authorship Analysis\u00a045(1) (2011)","DOI":"10.1007\/s10579-009-9114-z"},{"key":"8_CR17","unstructured":"Pouliquen, B., Steinberger, R., Ignat, C.: Automatic Annotation of Multilingual Text Collections with a Conceptual Thesaurus. CoRR abs\/cs\/0609059 (2006)"}],"container-title":["Lecture Notes in Computer Science","Information Access Evaluation. Multilinguality, Multimodality, and Visual Analytics"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-33247-0_8.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T12:00:10Z","timestamp":1620129610000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-33247-0_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642332463","9783642332470"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-33247-0_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012]]}}}