{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,24]],"date-time":"2025-01-24T05:09:36Z","timestamp":1737695376080,"version":"3.33.0"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"3-4","license":[{"start":{"date-parts":[[2007,12,1]],"date-time":"2007-12-01T00:00:00Z","timestamp":1196467200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJDAR"],"published-print":{"date-parts":[[2007,12]]},"DOI":"10.1007\/s10032-007-0057-x","type":"journal-article","created":{"date-parts":[[2007,12,4]],"date-time":"2007-12-04T07:32:49Z","timestamp":1196753569000},"page":"187-198","source":"Crossref","is-referenced-by-count":5,"title":["Finding structure in noisy text: topic classification and unsupervised clustering"],"prefix":"10.1007","volume":"10","author":[{"given":"Prem","family":"Natarajan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rohit","family":"Prasad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Krishna","family":"Subramanian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shirin","family":"Saleem","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fred","family":"Choi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rich","family":"Schwartz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2007,12,5]]},"reference":[{"key":"57_CR1","doi-asserted-by":"crossref","unstructured":"Schwartz, R., Imai, T., Kubala, F., Nguyen, L., Makhoul, J.: A Maximum Likelihood Model for Topic Classification of Broadcast News. In: Proceedings of EUROSPEECH. ISCA, Rhodes (1997)","DOI":"10.21437\/Eurospeech.1997-422"},{"key":"57_CR2","doi-asserted-by":"crossref","unstructured":"Joachims, T.: Text Categorization with support vector machines. In: Proceedings of ECML-98, 10th European Conference on Machine Learning. Springer, Chemnitz, pp. 137\u2013142 (1998)","DOI":"10.1007\/BFb0026683"},{"key":"57_CR3","doi-asserted-by":"crossref","unstructured":"Baker, L.D., McCallum A.: Distributional clustering of words for text classification. In: Proceedings of ACM SIGIR. ACM, Melbourne, pp. 96\u2013103 (1998)","DOI":"10.1145\/290941.290970"},{"key":"57_CR4","first-page":"616","volume-title":"Proceedings of the Twentieth International Conference on Machine Learning (ICML-2003)","author":"J.D.M. Rennie","year":"2003","unstructured":"Rennie J.D.M., Shih L., Teevan J. and Karger D. (2003). Tackling the poor assumptions of Naive\u2013Bayes text classifiers. In: Fawcett, T. and Mishra, N. (eds) Proceedings of the Twentieth International Conference on Machine Learning (ICML-2003), pp 616\u2013623. AAAI Press, Washington, DC"},{"key":"57_CR5","doi-asserted-by":"crossref","unstructured":"Eick, S., Lockwood, J., Loui, R., Moscola, J., Kastner, C., Levine, A., Weishar, D.: Transformation algorithms for data streams. In: Proceedings of IEEE Aerospace Conference, March 2005","DOI":"10.1109\/AERO.2005.1559611"},{"key":"57_CR6","doi-asserted-by":"crossref","unstructured":"Wright, J. H., Carey, J. M., Parris, E. S.: Improved topic spotting through statistical modeling of keyword dependencies. In: Proceedings IEEE ICASSP. IEEE, Detroit, pp. 313\u2013316 (1995)","DOI":"10.1109\/ICASSP.1995.479536"},{"key":"57_CR7","doi-asserted-by":"crossref","unstructured":"Peskin, B., Connolly, S., Gillick, L., Lowe, S., McAllaster, D., Nagesha, V.: Improvements in switchboard recognition and topic identification. In: Proceedings of IEEE ICASSP. IEEE, Atlanta, pp. 303\u2013306 (1996)","DOI":"10.1109\/ICASSP.1996.540418"},{"key":"57_CR8","doi-asserted-by":"crossref","unstructured":"Subramanian, K., Prasad, R., Natarajan, P., Schwartz, R.: Optimal estimation of rejection thresholds for topic spotting. In: Proceedings of IEEE ICASSP. IEEE, Honolulu (2007)","DOI":"10.1109\/ICASSP.2007.367168"},{"key":"57_CR9","volume-title":"Proceedings of ACM HLT","author":"S. Sista","year":"2002","unstructured":"Sista S., Schwartz R., Leek T. and Makhoul J. (2002). An algorithm for unsupervised topic discovery from broadcast news stories. In: Marcus, M. (eds) Proceedings of ACM HLT. ACM, San Diego"},{"key":"57_CR10","unstructured":"The 20 Newsgroup (20 NG) Corpus, http:\/\/www.people.csail.mit.edu\/jrennie\/20Newsgroups\/"},{"key":"57_CR11","unstructured":"Differentiable Nonlinear Optimization, http:\/\/www.sai.msu.su\/sal\/B\/3\/DONLP2.html"},{"key":"57_CR12","doi-asserted-by":"crossref","unstructured":"Li, H., Abe, N.: Word clustering and disambiguation based on co-occurrence data. In: Proceedings of COLING-ACL, pp. 749\u2013755 (1998)","DOI":"10.3115\/980691.980693"},{"key":"57_CR13","doi-asserted-by":"crossref","unstructured":"Biswas, G., Weinberg, J., Fisher, D.: ITERATE: A conceptual clustering algorithm for data mining. IEEE Trans. Syst. Man Cybernet. Rev. 28(2) (1998)","DOI":"10.1109\/5326.669556"},{"key":"57_CR14","unstructured":"Hofmann, T.: The cluster-abstraction model: unsupervised learning of topic hierarchies from text data. In: Proceedings of IJCAI. IJCAI, Stockholm, pp. 682\u2013687 (1999)"},{"issue":"5","key":"57_CR15","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1016\/0306-4573(88)90027-1","volume":"24","author":"P. Willet","year":"1998","unstructured":"Willet P. (1998). Recent trends in hierarchical document clustering: a critical review. Inform. Process. Manage. 24(5): 577\u2013597","journal-title":"Inform. Process. Manage."},{"key":"57_CR16","doi-asserted-by":"crossref","unstructured":"Sista, S., Srivastava A., Kubala, F., Schwartz R.: Unsupervised topic discovery applied to segmentation of news transcriptions. In: Proceedings of Eurospeech. ISCA, Geneva, pp. 2833\u20132836 (2003)","DOI":"10.21437\/Eurospeech.2003-754"},{"key":"57_CR17","unstructured":"Marcken, C.: The unsupervised acquisition of lexicon from continuous speech. In: MIT Artificial Intelligence Laboratory, A.I. Memo No. 1558 (1995)"},{"key":"57_CR18","unstructured":"Leek, T.R.: Minimum Description Length (MDL) phrases. BBN Technologies, Technical Report 010405TRL (2001)"},{"issue":"1\u20133","key":"57_CR19","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1023\/A:1007558221122","volume":"34","author":"D. Bikel","year":"1999","unstructured":"Bikel D., Schwartz R. and Weischedel R. (1999). An Algorithm that learns what\u2019s in a name. Machine Learning 34(1\u20133): 211\u2013231","journal-title":"Machine Learning"},{"key":"57_CR20","volume-title":"The SMART Retrieval System: Experiments in Automatic Document Processing","author":"G. Salton","year":"1971","unstructured":"Salton G. (1971). The SMART Retrieval System: Experiments in Automatic Document Processing. Prentice Hall, Englewood Cliffs"},{"key":"57_CR21","volume-title":"Probability, Random Variables, and Stochastic Processes","author":"P. Papoulis","year":"1984","unstructured":"Papoulis P. (1984). Probability, Random Variables and Stochastic Processes, 2nd edn. McGraw-Hill, New York","edition":"2"},{"key":"57_CR22","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1214\/aoms\/1177729694","volume":"22","author":"S. Kullback","year":"1951","unstructured":"Kullback S. and Leibler R.A. (1951). On information and sufficiency. Ann. Mathe. Stat. 22: 79\u201386","journal-title":"Ann. Mathe. Stat."},{"key":"57_CR23","unstructured":"Johnson, D., Sinanovic, S.: Symmetrizing the Kullback\u2013Leibler distance. Rice University Working Paper (2001)"}],"container-title":["International Journal of Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-007-0057-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10032-007-0057-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-007-0057-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T06:01:16Z","timestamp":1737612076000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10032-007-0057-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007,12]]},"references-count":23,"journal-issue":{"issue":"3-4","published-print":{"date-parts":[[2007,12]]}},"alternative-id":["57"],"URL":"https:\/\/doi.org\/10.1007\/s10032-007-0057-x","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"type":"print","value":"1433-2833"},{"type":"electronic","value":"1433-2825"}],"subject":[],"published":{"date-parts":[[2007,12]]}}}