{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T07:42:54Z","timestamp":1773301374307,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":72,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2006,8,20]]},"DOI":"10.1145\/1150402.1150455","type":"proceedings-article","created":{"date-parts":[[2006,10,18]],"date-time":"2006-10-18T22:04:00Z","timestamp":1161209040000},"page":"474-483","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":28,"title":["Extracting key-substring-group features for text classification"],"prefix":"10.1145","author":[{"given":"Dell","family":"Zhang","sequence":"first","affiliation":[{"name":"University of London, London, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wee Sun","family":"Lee","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2006,8,20]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"307","volume-title":"Proceedings of the 6th Natural Language Processing Pacific Rim Symposim (NLPRS)","author":"Aizawa A. N.","year":"2001","unstructured":"A. N. Aizawa . Linguistic techniques to improve the performance of automatic text categorization . In Proceedings of the 6th Natural Language Processing Pacific Rim Symposim (NLPRS) , pages 307 -- 314 , Tokyo, Japan , 2001 .]] A. N. Aizawa. Linguistic techniques to improve the performance of automatic text categorization. In Proceedings of the 6th Natural Language Processing Pacific Rim Symposim (NLPRS), pages 307--314, Tokyo, Japan, 2001.]]"},{"key":"e_1_3_2_1_2_1","volume-title":"Modern Information Retrieval","author":"Baeza-Yates R.","year":"1999","unstructured":"R. Baeza-Yates and B. Ribeiro-Neto . Modern Information Retrieval . Addison-Wesley , 1999 .]] R. Baeza-Yates and B. Ribeiro-Neto. Modern Information Retrieval. Addison-Wesley, 1999.]]"},{"key":"e_1_3_2_1_3_1","volume-title":"Text Compression","author":"Bell T. C.","year":"1990","unstructured":"T. C. Bell , J. G. Cleary , and I. H. Witten . Text Compression . Prentice-Hall , 1990 .]] T. C. Bell, J. G. Cleary, and I. H. Witten. Text Compression. Prentice-Hall, 1990.]]"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/646388.690192"},{"key":"e_1_3_2_1_6_1","volume-title":"Word-sequence kernels. Journal of Machine Learning Research, 3(Feb):1059--1082","author":"Cancedda N.","year":"2003","unstructured":"N. Cancedda , E. Gaussier , C. Goutte , and J.-M. Renders . Word-sequence kernels. Journal of Machine Learning Research, 3(Feb):1059--1082 , 2003 .]] N. Cancedda, E. Gaussier, C. Goutte, and J.-M. Renders. Word-sequence kernels. Journal of Machine Learning Research, 3(Feb):1059--1082, 2003.]]"},{"key":"e_1_3_2_1_7_1","volume-title":"LIBSVM: a library for support vector machines","author":"Chang C.-C.","year":"2001","unstructured":"C.-C. Chang and C.-J. Lin . LIBSVM: a library for support vector machines , 2001 .]] C.-C. Chang and C.-J. Lin. LIBSVM: a library for support vector machines, 2001.]]"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/371920.372182"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01185431"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.3115\/981863.981904"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/258525.258534"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.3115\/981623.981633"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/40.2_and_3.67"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1984.1096090"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/345662"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/133160.133214"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/288627.288651"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/789087.789742"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015388"},{"key":"e_1_3_2_1_20_1","volume-title":"Microsoft Research","author":"Goodman J.","year":"2001","unstructured":"J. Goodman . A bit of progress in language modeling, extended version. Technical report , Microsoft Research , 2001 .]] J. Goodman. A bit of progress in language modeling, extended version. Technical report, Microsoft Research, 2001.]]"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/262228"},{"key":"e_1_3_2_1_22_1","first-page":"24","volume-title":"PRICAI'2000 International Workshop on Text and Web Mining","author":"He J.","year":"2000","unstructured":"J. He , A.-H. Tan , and C.-L. Tan . A comparative study on Chinese text categorization methods . In PRICAI'2000 International Workshop on Text and Web Mining , pages 24 -- 35 , Melbourne, Australia , 2000 .]] J. He, A.-H. Tan, and C.-L. Tan. A comparative study on Chinese text categorization methods. In PRICAI'2000 International Workshop on Text and Web Mining, pages 24--35, Melbourne, Australia, 2000.]]"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1023202221875"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/515834"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1093\/llc\/10.2.111"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/72.991427"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1075\/nlp.5(1st)"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/1005332.1016786"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/645326.649721"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/383952.383974"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.5555\/572351"},{"key":"e_1_3_2_1_32_1","volume-title":"Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics and Speech Recognition","author":"Jurafsky D.","year":"2000","unstructured":"D. Jurafsky and J. H. Martin . Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics and Speech Recognition . Prentice Hall , 2000 .]] D. Jurafsky and J. H. Martin. Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics and Speech Recognition. Prentice Hall, 2000.]]"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.3115\/976909.979622"},{"key":"e_1_3_2_1_34_1","volume-title":"The Art of Computer Programming","author":"Knuth D.","year":"1997","unstructured":"D. Knuth . The Art of Computer Programming . Addison-Wesley , 3 rd edition, 1997 .]] D. Knuth. The Art of Computer Programming. Addison-Wesley, 3rd edition, 1997.]]","edition":"3"},{"key":"e_1_3_2_1_35_1","volume-title":"Diffusion kernels on statistical manifolds. Journal of Machine Learning Research, 6(Jan):129--163","author":"Lafferty J. D.","year":"2005","unstructured":"J. D. Lafferty and G. Lebanon . Diffusion kernels on statistical manifolds. Journal of Machine Learning Research, 6(Jan):129--163 , 2005 .]] J. D. Lafferty and G. Lebanon. Diffusion kernels on statistical manifolds. Journal of Machine Learning Research, 6(Jan):129--163, 2005.]]"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/383952.383970"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/290941.291041"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/564376.564403"},{"key":"e_1_3_2_1_39_1","first-page":"566","volume-title":"Proceedings of the 7th Pacific Symposium on Biocomputing (PSB)","author":"Leslie C. S.","year":"2002","unstructured":"C. S. Leslie , E. Eskin , and W. S. Noble . The spectrum kernel: A string kernel for SVM protein classification . In Proceedings of the 7th Pacific Symposium on Biocomputing (PSB) , pages 566 -- 575 , Lihue, HI , 2002 .]] C. S. Leslie, E. Eskin, and W. S. Noble. The spectrum kernel: A string kernel for SVM protein classification. In Proceedings of the 7th Pacific Symposium on Biocomputing (PSB), pages 566--575, Lihue, HI, 2002.]]"},{"key":"e_1_3_2_1_40_1","first-page":"4","volume-title":"Proceedings of the 10th European Conference on Machine Learning (ECML)","author":"Lewis D. D.","year":"1998","unstructured":"D. D. Lewis . Naive (Bayes) at forty : The independence assumption in information retrieval . In Proceedings of the 10th European Conference on Machine Learning (ECML) , pages 4 -- 15 , Chemnitz, Germany , 1998 .]] D. D. Lewis. Naive (Bayes) at forty: The independence assumption in information retrieval. In Proceedings of the 10th European Conference on Machine Learning (ECML), pages 4--15, Chemnitz, Germany, 1998.]]"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1162\/153244302760200687"},{"key":"e_1_3_2_1_42_1","volume-title":"Foundations of Statistical Natural Language Processing","author":"Manning C.","year":"1999","unstructured":"C. Manning and H. Schutze . Foundations of Statistical Natural Language Processing . MIT Press , Cambridge, MA , 1999 .]] C. Manning and H. Schutze. Foundations of Statistical Natural Language Processing. MIT Press, Cambridge, MA, 1999.]]"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-31865-1_22"},{"key":"e_1_3_2_1_44_1","volume-title":"Machine Learning","author":"Mitchell T.","year":"1997","unstructured":"T. Mitchell . Machine Learning . McGraw Hill , international edition, 1997 .]] T. Mitchell. Machine Learning. McGraw Hill, international edition, 1997.]]"},{"key":"e_1_3_2_1_45_1","volume-title":"A suffix tree approach to email filtering","author":"Pampapathi R. M.","year":"2005","unstructured":"R. M. Pampapathi , B. Mirkin , and M. Levene . A suffix tree approach to email filtering , 2005 .]] R. M. Pampapathi, B. Mirkin, and M. Levene. A suffix tree approach to email filtering, 2005.]]"},{"key":"e_1_3_2_1_46_1","volume-title":"Random Variables, and Stochastic Processes","author":"Papoulis A.","year":"1984","unstructured":"A. Papoulis . Probability , Random Variables, and Stochastic Processes . McGraw Hill , New York , 2 nd edition, 1984 .]] A. Papoulis. Probability, Random Variables, and Stochastic Processes. McGraw Hill, New York, 2nd edition, 1984.]]","edition":"2"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:INRT.0000011209.19643.e2"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/290941.291008"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114008"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.880083"},{"key":"e_1_3_2_1_51_1","volume-title":"MSRI Workshop on Nonlinear Estimation and Classification","author":"Schapire R. E.","year":"2002","unstructured":"R. E. Schapire . The boosting approach to machine learning: An overview . In MSRI Workshop on Nonlinear Estimation and Classification , Berkeley, CA , 2002 .]] R. E. Schapire. The boosting approach to machine learning: An overview. In MSRI Workshop on Nonlinear Estimation and Classification, Berkeley, CA, 2002.]]"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007649029923"},{"key":"e_1_3_2_1_53_1","volume-title":"Learning with Kernels","author":"Scholkopf B.","year":"2002","unstructured":"B. Scholkopf and A. J. Smola . Learning with Kernels . MIT Press , Cambridge, MA , 2002 .]] B. Scholkopf and A. J. Smola. Learning with Kernels. MIT Press, Cambridge, MA, 2002.]]"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/505282.505283"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.5555\/975545"},{"key":"e_1_3_2_1_56_1","first-page":"578","volume-title":"Proceedings of the 19th International Conference on Machine Learning (ICML)","author":"Slonim N.","year":"2002","unstructured":"N. Slonim , G. Bejerano , S. Fine , and N. Tishby . Discriminative feature selection via multiclass variable memory Markov model . In Proceedings of the 19th International Conference on Machine Learning (ICML) , pages 578 -- 585 , Sydney, Australia , 2002 .]] N. Slonim, G. Bejerano, S. Fine, and N. Tishby. Discriminative feature selection via multiclass variable memory Markov model. In Proceedings of the 19th International Conference on Machine Learning (ICML), pages 578--585, Sydney, Australia, 2002.]]"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1162\/089120100750105920"},{"key":"e_1_3_2_1_58_1","first-page":"83","volume-title":"Workshop on Language Modeling and Information Retrieval","author":"Teahan W. J.","year":"2001","unstructured":"W. J. Teahan and D. J. Harper . Using compression based language models for text categorization. In J. Callan, B. Croft, and J. Lafferty, editors , Workshop on Language Modeling and Information Retrieval , pages 83 -- 88 , Carnegie Mellon University , 2001 .]] W. J. Teahan and D. J. Harper. Using compression based language models for text categorization. In J. Callan, B. Croft, and J. Lafferty, editors, Workshop on Language Modeling and Information Retrieval, pages 83--88, Carnegie Mellon University, 2001.]]"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01206331"},{"key":"e_1_3_2_1_60_1","volume-title":"UK","author":"van Rijsbergen C.","year":"1979","unstructured":"C. van Rijsbergen . Information Retrieval . Butterworths, London , UK , 2 nd edition, 1979 .]] C. van Rijsbergen. Information Retrieval. Butterworths, London, UK, 2nd edition, 1979.]]","edition":"2"},{"key":"e_1_3_2_1_61_1","volume-title":"Springer-Verlag","author":"Vapnik V. N.","year":"2000","unstructured":"V. N. Vapnik . The Nature of Statistical Learning Theory . Springer-Verlag , 2 nd edition, 2000 .]] V. N. Vapnik. The Nature of Statistical Learning Theory. Springer-Verlag, 2nd edition, 2000.]]","edition":"2"},{"key":"e_1_3_2_1_62_1","volume-title":"Kernels and Bioinformatics","author":"Vishwanathan S.","year":"2004","unstructured":"S. Vishwanathan and A. Smola . Fast kernels for string and tree matching . In K. Tsuda, B. Scholkopf, and J. Vert, editors, Kernels and Bioinformatics . MIT Press , Cambridge, MA , 2004 .]] S. Vishwanathan and A. Smola. Fast kernels for string and tree matching. In K. Tsuda, B. Scholkopf, and J. Vert, editors, Kernels and Bioinformatics. MIT Press, Cambridge, MA, 2004.]]"},{"key":"e_1_3_2_1_63_1","volume-title":"Proceedings of the 34th Annual Conference on Information Sciences and Systems (CISS)","author":"Witten I. H.","year":"2000","unstructured":"I. H. Witten . Applications of lossless compression in adaptive text mining . In Proceedings of the 34th Annual Conference on Information Sciences and Systems (CISS) , Princeton University, New Jersey , 2000 .]] I. H. Witten. Applications of lossless compression in adaptive text mining. In Proceedings of the 34th Annual Conference on Information Sciences and Systems (CISS), Princeton University, New Jersey, 2000.]]"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.5555\/789086.789617"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1162\/089120101300346787"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2003.1260785"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/312624.312647"},{"key":"e_1_3_2_1_68_1","first-page":"412","volume-title":"Proceedings of the 14th International Conference on Machine Learning (ICML)","author":"Yang Y.","year":"1997","unstructured":"Y. Yang and J. O. Pedersen . A comparative study on feature selection in text categorization . In Proceedings of the 14th International Conference on Machine Learning (ICML) , pages 412 -- 420 , Nashville, TN , 1997 .]] Y. Yang and J. O. Pedersen. A comparative study on feature selection in text categorization. In Proceedings of the 14th International Conference on Machine Learning (ICML), pages 412--420, Nashville, TN, 1997.]]"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1389-1286(99)00054-7"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/984321.984322"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/1076034.1076081"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24655-8_8"},{"key":"e_1_3_2_1_74_1","volume-title":"Human Behaviour and the Principle of Least Effort","author":"Zipf G. K.","year":"1949","unstructured":"G. K. Zipf . Human Behaviour and the Principle of Least Effort . Addison-Wesley , Cambridge, MA , 1949 .]] G. K. Zipf. Human Behaviour and the Principle of Least Effort. Addison-Wesley, Cambridge, MA, 1949.]]"}],"event":{"name":"KDD06: The 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","location":"Philadelphia PA USA","acronym":"KDD06","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","ACM Association for Computing Machinery"]},"container-title":["Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1150402.1150455","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,8]],"date-time":"2023-01-08T09:26:40Z","timestamp":1673170000000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1150402.1150455"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006,8,20]]},"references-count":72,"alternative-id":["10.1145\/1150402.1150455","10.1145\/1150402"],"URL":"https:\/\/doi.org\/10.1145\/1150402.1150455","relation":{},"subject":[],"published":{"date-parts":[[2006,8,20]]},"assertion":[{"value":"2006-08-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}