{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,14]],"date-time":"2026-11-14T17:54:18Z","timestamp":1794678858898,"version":"4.9.1"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"1-2","license":[{"start":{"date-parts":[[2001,1,1]],"date-time":"2001-01-01T00:00:00Z","timestamp":978307200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2001,1,1]],"date-time":"2001-01-01T00:00:00Z","timestamp":978307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Learning"],"published-print":{"date-parts":[[2001,1]]},"DOI":"10.1023\/a:1007617005950","type":"journal-article","created":{"date-parts":[[2002,12,22]],"date-time":"2002-12-22T05:54:50Z","timestamp":1040536490000},"page":"177-196","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1788,"title":["Unsupervised Learning by Probabilistic Latent Semantic Analysis"],"prefix":"10.1007","volume":"42","author":[{"given":"Thomas","family":"Hofmann","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"279327_CR1","doi-asserted-by":"crossref","unstructured":"Baker, L. D. & McCallum, A. K. (1998). Distributional clustering ofwords for text classification. In Proceedings of the 21st ACM-SIGIR International Conference on Research and Development in Information Retrieval (SIGIR).","DOI":"10.1145\/290941.290970"},{"key":"279327_CR2","doi-asserted-by":"crossref","unstructured":"Bellegarda, J. R. (1998). Exploiting both local and global constraints for multi-span statistical language modeling. In Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP'98, pp. 677\u2013680.","DOI":"10.1109\/ICASSP.1998.675355"},{"issue":"4","key":"279327_CR3","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1137\/1037127","volume":"37","author":"M. W. Berry","year":"1995","unstructured":"Berry, M. W. Dumais, S. T., & O'Brien, G. W. (1995). Using linear algebra for intelligent information retrieval. SIAM Review, 37(4), 573\u2013595.","journal-title":"SIAM Review"},{"key":"279327_CR4","unstructured":"Cheeseman, P. & Stutz, J. (1996). Bayesian classification (AutoClass): Theory and results. In Usama M. Fayyad, Gregory Piatetsky-Shapiro, Padhraic Smyth, & Ramasamy Uthurusamy, (Eds.), Advances in Knowledge Discovery and Data Mining. AAAI Press\/MIT Press."},{"key":"279327_CR5","doi-asserted-by":"crossref","unstructured":"Coccaro, N. & Jurafsky, D. (1998). Towards better integration of semantic predictors in statistical language modeling. In Proceedings of the 5th International Conference on Spoken Language Processing (ICSLP).","DOI":"10.21437\/ICSLP.1998-642"},{"key":"279327_CR6","doi-asserted-by":"crossref","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":"Deerwester, S., Dumais, G. W., Furnas, S. T., Landauer, T. K., & Harshman, R. (1990). Indexing by latent semantic analysis. Journal of the American Society for Information Science, 41, 391\u2013407.","journal-title":"Journal of the American Society for Information Science"},{"key":"279327_CR7","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. J. Royal Statist. Soc. B, 39, 1\u201338.","journal-title":"J. Royal Statist. Soc. B"},{"key":"279327_CR8","doi-asserted-by":"crossref","unstructured":"Dumais, S. T. (1995). Latent semantic indexing (LSI): TREC-3 report. In D.K Harman, (Ed.), Proceedings of the Text REtrieval Conference (TREC-3), pp. 219\u2013230.","DOI":"10.6028\/NIST.SP.500-225.adhoc-lsi"},{"issue":"12","key":"279327_CR9","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1145\/138859.138866","volume":"35","author":"P. W. Foltz","year":"1992","unstructured":"Foltz, P. W. & Dumais, S. T. (1992). An analysis of information filtering methods. Communications of the ACM, 35(12), 51\u201360.","journal-title":"Communications of the ACM"},{"issue":"395","key":"279327_CR10","doi-asserted-by":"crossref","first-page":"780","DOI":"10.1080\/01621459.1986.10478335","volume":"81","author":"Z. Gilula","year":"1986","unstructured":"Gilula, Z., & Haberman, S. J. (1986). Canonical analysis of contingency tables by maximum likelihood. Journal of the American Statistical Association, 81(395), 780\u2013788.","journal-title":"Journal of the American Statistical Association"},{"key":"279327_CR11","unstructured":"Golub, G. H. & Van Loan, C. F. (1996). Matrix Computations. Johns Hopkins University Press, 3rd (ed.)."},{"key":"279327_CR12","unstructured":"Hofmann, T., Puzicha, J., & Jordan, M. I. (1999). Unsupervised learning from dyadic data. In Advances in Neural Information Processing Systems, Vol. 11, MIT Press."},{"issue":"3","key":"279327_CR13","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1109\/TASSP.1987.1165125","volume":"35","author":"S. M. Katz","year":"1987","unstructured":"Katz, S. M. (1987). Estimation of probabilities for sparse data for the language model component of a speech recogniser. IEEE Transactions on Acoustics, Speech and Signal Processing, 35(3), 400\u2013401.","journal-title":"IEEE Transactions on Acoustics, Speech and Signal Processing"},{"key":"279327_CR14","doi-asserted-by":"crossref","unstructured":"Landauer, T. K. & Dumais, S. T. (1997). A solution to Plato's problem: The latent semantic analysis theory of acquisition, induction, and representation of knowledge. Psychological Review.","DOI":"10.1037\/\/0033-295X.104.2.211"},{"key":"279327_CR15","unstructured":"LDC. Linguistic Data Consortium: TDT pilot study corpus documentation. http:\/\/www.ldc.upenn.edu\/TDT, 1997."},{"issue":"675","key":"279327_CR16","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1038\/44565","volume":"401","author":"D. D. Lee","year":"1999","unstructured":"Lee, D. D. & Seung, H. S. (1999). Learning the parts of objects by non-negative matrix factorization. Nature, 401(675), 788\u2013791.","journal-title":"Nature"},{"key":"279327_CR17","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1007\/978-94-011-5014-9_12","volume-title":"Learning in Graphical Models","author":"R. M. Neal","year":"1998","unstructured":"Neal, R. M. & Hinton, G. E. (1998). A view of the EM algorithm that justifies incremental and other variants. In M.I. Jordan, (Ed.), Learning in Graphical Models, Dordrecht, MA: Kluwer Academic Publishers, pp. 355\u2013368."},{"key":"279327_CR18","doi-asserted-by":"crossref","unstructured":"Pereira, F. C. N., Tishby, N. Z., & Lee, L. (1983). Distributional clustering of english words. In Proceedings of the ACL, pp. 183\u2013190.","DOI":"10.3115\/981574.981598"},{"issue":"11","key":"279327_CR19","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1016\/0167-8655(90)90010-Y","volume":"11","author":"K. Rose","year":"1990","unstructured":"Rose, K., Gurewitz, E., & Fox, G. (1990). A deterministic annealing approach to clustering. Pattern Recognition Letters, 11(11), 589\u2013594.","journal-title":"Pattern Recognition Letters"},{"key":"279327_CR20","volume-title":"Introduction to Modern Information Retrieval","author":"G. Salton","year":"1983","unstructured":"Salton, G. & McGill, M. J. (1983). Introduction to Modern Information Retrieval. New York: McGraw-Hill."},{"key":"279327_CR21","unstructured":"Saul, L. & Pereira, F. (1997). Aggregate and mixed-order Markov models for statistical language processing. In Proceedings of the 2nd International Conference on Empirical Methods in Natural Language Processing, pp. 81\u201389."},{"issue":"2","key":"279327_CR22","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1016\/S0893-6080(97)00133-0","volume":"11","author":"N. Ueda","year":"1988","unstructured":"Ueda, N. & Nakano, R. (1988). Deterministic annealing EM algorithm. Neural Networks, 11(2), 271\u2013282.","journal-title":"Neural Networks"},{"issue":"4","key":"279327_CR23","doi-asserted-by":"crossref","first-page":"1085","DOI":"10.1109\/18.87000","volume":"37","author":"I. H. Witten","year":"1991","unstructured":"Witten, I. H. & Bell, T. C. (1991). The zero-frequency problem\u2014estimating the probabilities of novel events in adaptive text compression. IEEE Transactions on Information Theory, 37(4); 1085\u20131094.","journal-title":"IEEE Transactions on Information Theory"},{"issue":"2\/3","key":"279327_CR24","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1080\/01638539809545030","volume":"25","author":"M. B. W. Wolfe","year":"1998","unstructured":"Wolfe, M. B. W., Schreiner, M. E., Rehder, B., Laham, D., Foltz, P. W., Kintsch, W. & Landauer, T. K. (1998). Learning from text: Matching readers and texts by latent semantic analysis. Discourse Processes, 25(2\/3), 309\u2013336.","journal-title":"Discourse Processes"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1007617005950.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1007617005950\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1007617005950.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T11:46:38Z","timestamp":1752147998000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1007617005950"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2001,1]]},"references-count":24,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[2001,1]]}},"alternative-id":["279327"],"URL":"https:\/\/doi.org\/10.1023\/a:1007617005950","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2001,1]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}