{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T02:44:31Z","timestamp":1743129871894,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":27,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540709381"},{"type":"electronic","value":"9783540709398"}],"license":[{"start":{"date-parts":[[2007,1,1]],"date-time":"2007-01-01T00:00:00Z","timestamp":1167609600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2007]]},"DOI":"10.1007\/978-3-540-70939-8_54","type":"book-chapter","created":{"date-parts":[[2007,5,19]],"date-time":"2007-05-19T07:15:01Z","timestamp":1179558901000},"page":"611-622","source":"Crossref","is-referenced-by-count":21,"title":["Clustering Narrow-Domain Short Texts by Using the Kullback-Leibler Distance"],"prefix":"10.1007","author":[{"given":"David","family":"Pinto","sequence":"first","affiliation":[]},{"given":"Jos\u00e9-Miguel","family":"Bened\u00ed","sequence":"additional","affiliation":[]},{"given":"Paolo","family":"Rosso","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"54_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1007\/11428817_25","volume-title":"Natural Language Processing and Information Systems","author":"M. Alexandrov","year":"2005","unstructured":"Alexandrov, M., Gelbukh, A., Rosso, P.: An Approach to Clustering Abstracts. In: Montoyo, A., Mu\u0144oz, R., M\u00e9tais, E. (eds.) NLDB 2005. LNCS, vol.\u00a03513, pp. 275\u2013285. Springer, Heidelberg (2005)"},{"issue":"4","key":"54_CR2","doi-asserted-by":"publisher","first-page":"1407","DOI":"10.1109\/18.681318","volume":"44","author":"C.H. Bennett","year":"1998","unstructured":"Bennett, C.H., G\u00e1cs, P., Li, M., Vit\u00e1nyi, P., Zurek, W.: Information Distance. IEEE Trans. Inform. Theory\u00a044(4), 1407\u20131423 (1998)","journal-title":"IEEE Trans. Inform. Theory"},{"key":"54_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1007\/3-540-36618-0_22","volume-title":"Advances in Information Retrieval","author":"B. Bigi","year":"2003","unstructured":"Bigi, B., Huang, Y., Mori, R.d.: Vocabulary and Language Model Adaptation using Information Retrieval. In: Sebastiani, F. (ed.) ECIR 2003. LNCS, vol.\u00a02633, pp. 305\u2013319. Springer, Heidelberg (2003)"},{"key":"54_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1007\/3-540-36618-0_22","volume-title":"Advances in Information Retrieval","author":"B. Bigi","year":"2003","unstructured":"Bigi, B.: Using Kullback-Leibler Distance for Text Categorization. In: Sebastiani, F. (ed.) ECIR 2003. LNCS, vol.\u00a02633, pp. 305\u2013319. Springer, Heidelberg (2003)"},{"issue":"6","key":"54_CR5","first-page":"1085","volume":"80","author":"B. Bigi","year":"2000","unstructured":"Bigi, B., Mori, R.d., El-B\u00e8ze, M., Spriet, T.: A fuzzy decision strategy for topic identification and dynamic selection of language models. Signal Processing Journal, Special Issue on Fuzzy Logic in Signal Processing\u00a080(6), 1085\u20131097 (2000)","journal-title":"Signal Processing Journal, Special Issue on Fuzzy Logic in Signal Processing"},{"issue":"4","key":"54_CR6","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1016\/S0019-9958(67)90201-X","volume":"10","author":"A.D. Booth","year":"1967","unstructured":"Booth, A.D.: A Law of Occurrences for Words of Low Frequency. Information and control\u00a010(4), 386\u2013393 (1967)","journal-title":"Information and control"},{"issue":"3","key":"54_CR7","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1093\/biomet\/76.3.503","volume":"76","author":"P. Burman","year":"1989","unstructured":"Burman, P.: A comparative study of ordinary cross-validation, v-fold cross-validation and the repeated learning-testing methods. Biometrika\u00a076(3), 503\u2013514 (1989)","journal-title":"Biometrika"},{"issue":"1","key":"54_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/366836.366860","volume":"19","author":"C. Carpineto","year":"2001","unstructured":"Carpineto, C., Mori, R.d., Romano, G., Bigi, B.: An information-theoretic approach to automatic query expansion. ACM Transactions on Information Systems\u00a019(1), 1\u201327 (2001)","journal-title":"ACM Transactions on Information Systems"},{"issue":"1\u20133","key":"54_CR9","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1023\/A:1007537716579","volume":"34","author":"I. Dagan","year":"1999","unstructured":"Dagan, I., Lee, L., Pereira, F.: Similarity-based models of word cooccurrence probabilities. Machine Learning\u00a034(1\u20133), 43\u201369 (1999)","journal-title":"Machine Learning"},{"key":"54_CR10","unstructured":"Fuglede, B., Topse, F.: Jensen-Shannon Divergence and Hilbert space embedding. IEEE Int. Sym. Information Theory (2004)"},{"issue":"1","key":"54_CR11","first-page":"114","volume":"35","author":"H. Jim\u00e9nez","year":"2005","unstructured":"Jim\u00e9nez, H., Pinto, D., Rosso, P.: Uso del punto de transici\u00f3n en la selecci\u00f3n de t\u00e9rminos \u00edndice para agrupamiento de textos cortos. Procesamiento del Lenguaje Natural\u00a035(1), 114\u2013118 (2005)","journal-title":"Procesamiento del Lenguaje Natural"},{"key":"54_CR12","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/BF02289588","volume":"2","author":"S.C. Johnson","year":"1967","unstructured":"Johnson, S.C.: Hierarchical Clustering Schemes. Psychometrika\u00a02, 241\u2013254 (1967)","journal-title":"Psychometrika"},{"issue":"1","key":"54_CR13","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1214\/aoms\/1177729694","volume":"22","author":"S. Kullback","year":"1951","unstructured":"Kullback, S., Leibler, R.A.: On information and sufficiency. Annals of Mathematical Statistics\u00a022(1), 79\u201386 (1951)","journal-title":"Annals of Mathematical Statistics"},{"key":"54_CR14","first-page":"488","volume-title":"ICML","author":"T. Liu","year":"2003","unstructured":"Liu, T., Liu, S., Chen, Z., Ma, W.: An evaluation on feature selection for text clustering. In: Fawcett, T., Mishra, N. (eds.) ICML, pp. 488\u2013495. AAAI Press, Menlo Park (2003)"},{"key":"54_CR15","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1007\/978-3-540-30120-2_17","volume-title":"Text, Speech and Dialogue","author":"P. Makagonov","year":"2004","unstructured":"Makagonov, P., Alexandrov, M., Gelbukh, A.: Clustering Abstracts instead of Full Texts. In: Sojka, P., Kope\u010dek, I., Pala, K. (eds.) TSD 2004. LNCS (LNAI), vol.\u00a03206, pp. 129\u2013135. Springer, Heidelberg (2004)"},{"issue":"1","key":"54_CR16","first-page":"119","volume":"35","author":"A. Montejo-R\u00e1ez","year":"2005","unstructured":"Montejo-R\u00e1ez, A., Ure\u00f1a-Lopez, L.A., Steinberger, R.: Categorization using bibliographic records: beyond document content. Procesamiento del Lenguaje Natural\u00a035(1), 119\u2013126 (2005)","journal-title":"Procesamiento del Lenguaje Natural"},{"volume-title":"Spoken Dialogues with Computers","year":"1998","key":"54_CR17","unstructured":"Mori, R.d. (ed.): Spoken Dialogues with Computers. Academic Press, London (1998)"},{"key":"54_CR18","doi-asserted-by":"crossref","unstructured":"Pekar, V., Krkoska, M., Staab, S.: Feature Weighting for Co-occurrence-based Classification of Words. In: Proceedings of the 20th Conference on Computational Linguistics, COLING-2004 (2004)","DOI":"10.3115\/1220355.1220470"},{"key":"54_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1007\/11671299_55","volume-title":"Computational Linguistics and Intelligent Text Processing","author":"D. Pinto","year":"2006","unstructured":"Pinto, D., Jim\u00e9nez-Salazar, H., Rosso, P.: Clustering abstracts of scientific texts using the transition point technique. In: Gelbukh, A. (ed.) CICLing 2006. LNCS, vol.\u00a03878, pp. 536\u2013546. Springer, Heidelberg (2006)"},{"issue":"1","key":"54_CR20","first-page":"43","volume":"37","author":"D. Pinto","year":"2006","unstructured":"Pinto, D., Rosso, P., Juan, A., Jim\u00e9nez, H.: A Comparative Study of Clustering Algorithms on Narrow-Domain Abstracts. Procesamiento del Lenguaje Natural\u00a037(1), 43\u201349 (2006)","journal-title":"Procesamiento del Lenguaje Natural"},{"key":"54_CR21","unstructured":"Pinto, D., Rosso, P.: KnCr: A Short-Text Narrow-Domain Sub-Corpus of Medline. In: Proceedings of TLH-ENC06, pp. 266\u2013269 (2006)"},{"key":"54_CR22","doi-asserted-by":"crossref","unstructured":"Porter, M.F.: An algorithm for suffix stripping. In Program\u00a014(3) (1980)","DOI":"10.1108\/eb046814"},{"key":"54_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1007\/3-540-36456-0_69","volume-title":"Computational Linguistics and Intelligent Text Processing","author":"K. Shin","year":"2003","unstructured":"Shin, K., Han, S.Y.: Fast clustering algorithm for information organization. In: Gelbukh, A. (ed.) CICLing 2003. LNCS, vol.\u00a02588, pp. 619\u2013622. Springer, Heidelberg (2003)"},{"key":"54_CR24","unstructured":"Van Rijsbergen, C.J.: Information Retrieval, 2nd edn. Dept. of Computer Science, University of Glasgow (1979)"},{"key":"54_CR25","first-page":"256","volume-title":"Proceedings of SIGIR-ACM","author":"Y. Yang","year":"1995","unstructured":"Yang, Y.: Noise reduction in a statistical approach to text categorization. In: Proceedings of SIGIR-ACM, pp. 256\u2013263. ACM Press, New York (1995)"},{"key":"54_CR26","unstructured":"Yang, Y., Pedersen, J.O.: A comparative study on feature selection in text categorization. In: Proc. ICML, pp. 412\u2013420 (1997)"},{"issue":"4","key":"54_CR27","doi-asserted-by":"publisher","first-page":"1270","DOI":"10.1109\/18.243444","volume":"39","author":"J. Ziv","year":"1993","unstructured":"Ziv, J., Merhav, N.: A measure of relative entropy between individual sequences with application to universal classification. IEEE Transactions on Information Theory\u00a039(4), 1270\u20131279 (1993)","journal-title":"IEEE Transactions on Information Theory"}],"container-title":["Lecture Notes in Computer Science","Computational Linguistics and Intelligent Text Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-70939-8_54","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,19]],"date-time":"2019-05-19T11:57:03Z","timestamp":1558267023000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-70939-8_54"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007]]},"ISBN":["9783540709381","9783540709398"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-70939-8_54","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2007]]}}}