{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T05:21:17Z","timestamp":1737091277082,"version":"3.33.0"},"publisher-location":"Berlin, Heidelberg","reference-count":24,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540433439"},{"type":"electronic","value":"9783540458869"}],"license":[{"start":{"date-parts":[[2002,1,1]],"date-time":"2002-01-01T00:00:00Z","timestamp":1009843200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2002]]},"DOI":"10.1007\/3-540-45886-7_16","type":"book-chapter","created":{"date-parts":[[2007,5,27]],"date-time":"2007-05-27T00:11:04Z","timestamp":1180224664000},"page":"229-247","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["A Hierarchical Model for Clustering and Categorising Documents"],"prefix":"10.1007","author":[{"given":"E.","family":"Gaussier","sequence":"first","affiliation":[]},{"given":"C.","family":"Goutte","sequence":"additional","affiliation":[]},{"given":"K.","family":"Popat","sequence":"additional","affiliation":[]},{"given":"F.","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2002,3,14]]},"reference":[{"unstructured":"L. Douglas Baker, Thomas Hofmann, Andrew McCallum, and Yiming Yang. A hierarchical probabilistic model for novelty detection in text. http:\/\/www-2.cs.cmu.edu\/ mccallum\/papers\/tdt-nips99s.ps.gz .","key":"16_CR1"},{"key":"16_CR2","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1016\/0167-9473(92)90042-E","volume":"14","author":"G. Celeux","year":"1992","unstructured":"Gilles Celeux and G\u00e9rard Govaert. A Classification EM algorithm for clustering and two stochastic versions. Computational Statistics and Data Analysis, 14:315\u2013332, 1992.","journal-title":"Computational Statistics and Data Analysis"},{"issue":"6","key":"16_CR3","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9","volume":"41","author":"S. Deerwester","year":"1990","unstructured":"S. Deerwester, S. T. Dumais, G. W. Furnas, T. K. Landauer, and R. Harshman. Indexing by latent semantic analysis. Journal of the American Society for Information Science, 41(6):391\u2013407, 1990.","journal-title":"Journal of the American Society for Information Science"},{"issue":"1","key":"16_CR4","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":"A. P. Dempster, N. M. Laird, and D. B. Rubin. Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society, Series B, 39(1):1\u201338, 1977.","journal-title":"Journal of the Royal Statistical Society"},{"unstructured":"E. Gaussier and N. Cancedda. Probabilistic models for terminology extraction and knowleddge structuring from documents. In Proceedings of the 2001IEEE International Conference on Systems, Man & Cybernetics, 2001.","key":"16_CR5"},{"doi-asserted-by":"crossref","unstructured":"G. Grefenstette. Explorations in Automatic Thesaurus Construction. Kluwer Academic Publishers, 1994.","key":"16_CR6","DOI":"10.1007\/978-1-4615-2710-7"},{"key":"16_CR7","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1080\/00437956.1954.11659520","volume":"10","author":"Z. S. Harris","year":"1954","unstructured":"Z. S. Harris. Distributional structure. Word, 10:146\u2013162, 1954.","journal-title":"Word"},{"doi-asserted-by":"crossref","unstructured":"Thomas Hofmann. Probabilistic latent semantic analysis. In Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligence, pages 289\u2013296. Morgan Kaufmann, 1999. http:\/\/www2.sis.pitt.edu\/ dsl\/UAI\/uai99.html .","key":"16_CR8","DOI":"10.1145\/312624.312649"},{"key":"16_CR9","first-page":"914","volume":"12","author":"T. Hofmann","year":"2000","unstructured":"Thomas Hofmann. Learning the similarity of documents: An information-geometric approach to document retrieval and categorization. In Advances in Neural Information Processing Systems 12, page 914. MIT Press, 2000.","journal-title":"Advances in Neural Information Processing Systems"},{"unstructured":"Thomas Hofmann and Jan Puzicha. Statistical models for co-occurence data. A.I. Memo 1625, A.I. Laboratory, February 1998.","key":"16_CR10"},{"key":"16_CR11","first-page":"487","volume":"11","author":"T. S. Jaakkola","year":"1999","unstructured":"Tommi S. Jaakkola and David Haussler. Exploiting generative models in discriminative classifiers. In Advances in Neural Information Processing Systems 11, pages 487\u2013493, 1999.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"16_CR12","series-title":"Lect Notes Comput Sci","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1007\/BFb0026683","volume-title":"Text categorization with support vector machines: Learning with many relevant features","author":"T. Joachims","year":"1998","unstructured":"Thorsten Joachims. Text categorization with support vector machines: Learning with many relevant features. In Proceedings of the European Conference on Machine Learning (ECML98), number 1398 in Lecture Notes in Computer Science, pages 137\u2013142. Springer Verlag, 1998."},{"key":"16_CR13","volume-title":"Foundations of Statistical Natural Language Processing","author":"C. D. Manning","year":"1999","unstructured":"Christopher D. Manning and Hinrich Sch\u00fctze. Foundations of Statistical Natural Language Processing. MIT Press, Cambridge, MA, 1999."},{"unstructured":"Andrew McCallum, Ronald Rosenfeld, Tom Mitchell, and Andrew Y. Ng. Improving text classification by shrinkage in a hierarchy of classes. In Proceedings of the Fifteenth International Conference on Machine Learning, pages 359\u2013367, 1998.","key":"16_CR14"},{"doi-asserted-by":"crossref","unstructured":"Fernando Pereira, Naftali Tishby, and Lillian Lee. Distributional clustering of english words. In Proceedings of the International Conference of the Association for Computational Linguistics, 1993.","key":"16_CR15","DOI":"10.3115\/981574.981598"},{"issue":"8","key":"16_CR16","doi-asserted-by":"publisher","first-page":"945","DOI":"10.1103\/PhysRevLett.65.945","volume":"65","author":"K. Rose","year":"1990","unstructured":"K. Rose, E. Gurewitz, and G. Fox. Statistical mechanics and phase transitions in clustering. Physical Review Letters, 65(8):945\u2013848, 1990.","journal-title":"Physical Review Letters"},{"unstructured":"G. Salton. Automatic Thesaurus Construction for Information Retrieval. North Holland Publishing, 1972.","key":"16_CR17"},{"key":"16_CR18","volume-title":"Statistical Analysis of Finite Mixture Distribution","author":"D. M. Titterington","year":"1985","unstructured":"D. M. Titterington, A. F. Smith, and U. E. Makov. Statistical Analysis of Finite Mixture Distribution. John Wiley & Sons, San Diego, 1985."},{"doi-asserted-by":"crossref","unstructured":"Kristina Toutanova, Francine Chen, Kris Popat, and Thomas Hofmann. Text classification in a hierarchical mixture model for small training sets. In Proceedings of the ACM Conference on Information and Knowledge Management, 2001.","key":"16_CR19","DOI":"10.1145\/502602.502604"},{"unstructured":"Naonori Ueda and Ryohei Nakano. Deterministic annealing variant of the EM algorithm. In Gerry Tesauro, David Touretzky, and Todd Leen, editors, Advances in Neural Information Processing Systems 7, pages 545\u2013552. MIT Press, 1995.","key":"16_CR20"},{"doi-asserted-by":"crossref","unstructured":"C. J. van Rijsbergen. Information Retrieval. Butterworth, 2nd edition edition, 1979.","key":"16_CR21","DOI":"10.1007\/978-3-642-23318-0_2"},{"issue":"2\u20133","key":"16_CR22","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1023\/A:1013677411002","volume":"18","author":"A. Vinokourov","year":"2002","unstructured":"Alexei Vinokourov and Mark Girolami. A probabilistic framework for the hierarchic organisation and classification of document collections. Journal of Intelligent Information Systems, 18(2\u20133):153\u2013172, 2002.","journal-title":"Journal of Intelligent Information Systems"},{"issue":"5","key":"16_CR23","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1016\/0306-4573(88)90027-1","volume":"24","author":"P. Willett","year":"1988","unstructured":"Peter Willett. Recent trends in hierarchical document clustering: A critical review. Information Processing & Management, 24(5):577\u2013597, 1988.","journal-title":"Information Processing & Management"},{"doi-asserted-by":"crossref","unstructured":"Yiming Yang and Xin Liu. A re-examination of text categorization methods. In Proceedings of the 22nd ACM SIGIR Conference on Research and Development in Information Retrieval, pages 42\u201349, 1999.","key":"16_CR24","DOI":"10.1145\/312624.312647"}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/3-540-45886-7_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:25:18Z","timestamp":1737051918000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/3-540-45886-7_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2002]]},"ISBN":["9783540433439","9783540458869"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/3-540-45886-7_16","relation":{},"ISSN":["0302-9743"],"issn-type":[{"type":"print","value":"0302-9743"}],"subject":[],"published":{"date-parts":[[2002]]},"assertion":[{"value":"14 March 2002","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}