@Article{Belkin06, title = "Manifold Regularization: {A} Geometric Framework for Learning from Labeled and Unlabeled Examples", author = "Mikhail Belkin and Partha Niyogi and Vikas Sindhwani", journal = "Journal of Machine Learning Research", year = "2006", volume = "7", bibdate = "2007-02-21", bibsource = "DBLP, http://dblp.uni-trier.de/db/journals/jmlr/jmlr7.html#BelkinNS06", pages = "2399--2434", URL = "http://www.jmlr.org/papers/v7/belkin06a.html", } @InCollection{Burges98, author = "Christopher J. C. Burges", year = "1998", booktitle = "Knowledge Discovery and Data Mining", number = "4", pages = "121--167", volume = "2", title = "A Tutorial on Support Vector Machines for Pattern Recognition", } @Manual{Chang01, author = {Chih-Chung Chang and Chih-Jen Lin}, title = {{LIBSVM}: a library for support vector machines}, year = {2001}, note = {Software available at {\tt http://www.csie.ntu.edu.tw/$\sim$cjlin/libsvm}} } @Book{Scholkopf02, author = "B. Sch{\"o}lkopf and A. J. Smola", title = "Learning with Kernels", publisher = "The MIT Press", year = "2002", address = "Cambridge, MA", } @Book{Chapelle06, title = "Semi-Supervised Learning", author = "Olivier Chapelle and Bernhard Sch{\"o}lkopf and Alexander Zien", publisher = "MIT Press", year = "2006", month = sep, abstract = "In the field of machine learning, semi-supervised learning (SSL) occupies the middle ground, between supervised learning (in which all training examples are labeled) and unsupervised learning (in which no label data are given). Interest in SSL has increased in recent years, particularly because of application domains in which unlabeled data are plentiful, such as images, text, and bioinformatics. This first comprehensive overview of SSL presents state-of-the-art algorithms, a taxonomy of the field, selected applications, benchmark experiments, and perspectives on ongoing and future research. Semi-Supervised Learning first presents the key assumptions and ideas underlying the field: smoothness, cluster or low-density separation, manifold structure, and transduction. The core of the book is the presentation of SSL methods, organized according to algorithmic strategies. After an examination of generative models, the book describes algorithms that implement the low-density separation assumption, graph-based methods, and algorithms that perform two-step learning. The book then discusses SSL applications and offers guidelines for SSL practitioners by analyzing the results of extensive benchmark experiments. Finally, the book looks at interesting directions for SSL research. The book closes with a discussion of the relationship between semi-supervised learning and transduction.", bibsource = "OAI-PMH server at eprints.pascal-network.org", oai = "oai:eprints.pascal-network.org:3092", subject = "Computational, Information-Theoretic Learning with Statistics; Learning/Statistics \& Optimisation; Theory \& Algorithms", type = "NonPeerReviewed", URL = "http://www.kyb.tuebingen.mpg.de/ssl-book/", note = "Web page: http://www.kyb.tuebingen.mpg.de/ssl-book/", } @techreport{Zhu07, author = "Xiaojin Zhu", title = "Semi-Supervised Learning Literature Survey", institution = "Computer Sciences, University of Wisconsin-Madison", number = "1530", year = 2007, URL = "http://www.cs.wisc.edu/$\sim$jerryzhu/pub/ssl\_survey.pdf" } @Article{Tenenbaum00, author = "J. B. Tenenbaum and V. de Silva and J. C. Langford", title = "A Global Geometric Framework for Nonlinear Dimensionality Reduction", journal = "Science", volume = "290", year = "2000", number = "5500", month = dec, pages = "2319--2323", URL = "http://isomap.stanford.edu/", bibsource = "http://www.visionbib.com/bibliography/pattern601.html#TT43941", } @Misc{Bernstein00, author = "Mira Bernstein and Vin de Silva and John C. Langford and Joshua B. Tenenbaum", title = "Graph approximations to geodesics on embedded manifolds", year = "2000", URL = "http://isomap.stanford.edu/BdSLT.pdf", } @Article{Quan05, author = "QUAN Yong and YANG Jie", title = "Geodesic Distance for Support Vector Machines", journal = "Acta Automatica Sinica", volume = "31", number = "2", year = "2005", pages = "202--208", URL = "http://www.aas.net.cn/qikan/manage/wenzhang/050205.pdf", } @InProceedings{Zelnik04, title = "Self-Tuning Spectral Clustering", author = "Lihi Zelnik-Manor and Pietro Perona", year = "2004", bibdate = "2006-02-13", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/nips/nips2004.html#Zelnik-ManorP04", booktitle = "NIPS", URL = "http://books.nips.cc/papers/files/nips17/NIPS2004\_0572.pdf", } @Book{Golub96, author = "Gene H. Golub and Charles F. {Van Loan}", title = "Matrix Computations, 3nd Edition", publisher = "The Johns Hopkins University Press", address = "Baltimore, MD", year = "1996", } @Book{Wu04, author = "Bang Ye Wu and Kun-Mao Chao", title = "Spanning Trees and Optimization Problems", publisher = "Chapman and Hall/CRC", address = "Boca Raton, Florida", year = "2004", } @InProceedings{Fischer03, title = "Clustering with the Connectivity Kernel", author = "Bernd Fischer and Volker Roth and Joachim M. Buhmann", publisher = "MIT Press", year = "2003", bibdate = "2004-10-12", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/nips/nips2003.html#FischerRB03", booktitle = "NIPS", editor = "Sebastian Thrun and Lawrence K. Saul and Bernhard Sch{\"o}lkopf", ISBN = "0-262-20152-6", URL = "http://books.nips.cc/papers/files/nips16/NIPS2003\_AA12.pdf", } @InProceedings{Gent03, author = "Ian P. Gent and Patrick Prosser and Barbara M. Smith and Wu Wei", title = "Supertree Construction with Constraint Programming", booktitle = "ICCP: International Conference on Constraint Programming (CP), LNCS", year = "2003", } @Misc{Deza92, title = "Applications of Cut Polyhedra", author = "M. Deza and M. Laurent", year = "1992", month = oct # "~22", bibsource = "OAI-PMH server at cs1.ist.psu.edu", language = "en", oai = "oai:CiteSeerPSU:14607", rights = "unrestricted", URL = "http://citeseer.ist.psu.edu/14607.html; ftp://ftp.ens.fr/pub/dmi/users/liens/liens-92-18.A4.ps.Z", } @InProceedings{Chapelle02, title = "Cluster Kernels for Semi-Supervised Learning", author = "Olivier Chapelle and Jason Weston and Bernhard Sch{\"o}lkopf", publisher = "MIT Press", year = "2002", bibdate = "2004-10-12", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/nips/nips2002.html#ChapelleWS02", booktitle = "NIPS", editor = "Suzanna Becker and Sebastian Thrun and Klaus Obermayer", ISBN = "0-262-02550-7", pages = "585--592", URL = "http://books.nips.cc/papers/files/nips15/AA13.pdf", } @InProceedings{Szummer01, title = "Partially labeled classification with Markov random walks", author = "Martin Szummer and Tommi Jaakkola", bibdate = "2003-01-31", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/nips/nips2001.html#SzummerJ01", booktitle = "NIPS", booktitle = "Advances in Neural Information Processing Systems 14 [Neural Information Processing Systems: Natural and Synthetic, {NIPS} 2001, December 3-8, 2001, Vancouver, British Columbia, Canada]", publisher = "MIT Press", year = "2001", editor = "Thomas G. Dietterich and Suzanna Becker and Zoubin Ghahramani", pages = "945--952", URL = "http://www-2.cs.cmu.edu/Groups/NIPS/NIPS2001/papers/psgz/AA36.ps.gz", } @Misc{Weston04, title = "Semi-Supervised Protein Classification using Cluster Kernels", author = "Jason Weston and Christina Leslie and Dengyong Zhou and Andre Elisseeff and William Stafford Noble", year = "2004", abstract = "A key issue in supervised protein classification is the representation of input sequences of amino acids. Recent work using string kernels for protein data has achieved state-of-the-art classification performance. However, such representations are based only on labeled data --- examples with known 3D structures, organized into structural classes --- while in practice, unlabeled data is far more plentiful. In this work, we develop simple and scalable cluster kernel techniques for incorporating unlabeled data into the representation of protein sequences. We show that our methods greatly improve the classification performance of string kernels and outperform standard approaches for using unlabeled data, such as adding close homologs of the positive examples to the training data. We achieve equal or superior performance to previously presented cluster kernel methods while achieving far greater computational efficiency.", bibsource = "OAI-PMH server at eprints.pascal-network.org", oai = "oai:eprints.pascal-network.org:479", subject = "Theory \& Algorithms", type = "Conference or Workshop Item; PeerReviewed", URL = "http://eprints.pascal-network.org/archive/00000479/; http://eprints.pascal-network.org/archive/00000479/01/CLUS.pdf", } @InProceedings{Cristianini01, title = "On Kernel-Target Alignment", author = "Nello Cristianini and John Shawe-Taylor and Andr{\'e} Elisseeff and Jaz S. Kandola", bibdate = "2004-10-12", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/nips/nips2001.html#CristianiniSEK01", booktitle = "Advances in Neural Information Processing Systems 14 [Neural Information Processing Systems: Natural and Synthetic, {NIPS} 2001, December 3-8, 2001, Vancouver, British Columbia, Canada]", publisher = "MIT Press", year = "2001", editor = "Thomas G. Dietterich and Suzanna Becker and Zoubin Ghahramani", pages = "367--373", URL = "http://www-2.cs.cmu.edu/Groups/NIPS/NIPS2001/papers/psgz/LT17.ps.gz", } @Book{Jain88, author = "Anil K. Jain and Richard C. Dubes", title = "Algorithms for Clustering Data", publisher = "Prentice-Hall", year = "1988", } @Book{Borg05, author = "Ingwer Borg and Patrick J. F. Groenen", title = "Modern multidimensional scaling, 2nd edition", publisher = "Springer-Verlag", address = "New York", year = "2005", } @InProceedings{Ham04, title = "A kernel view of the dimensionality reduction of manifolds", author = "Jihun Ham and Daniel D. Lee and Sebastian Mika and Bernhard Sch{\"o}lkopf", booktitle = "Machine Learning, Proceedings of the Twenty-first International Conference ({ICML} 2004), Banff, Alberta, Canada, July 4-8, 2004", publisher = "ACM", year = "2004", volume = "69", editor = "Carla E. Brodley", series = "ACM International Conference Proceeding Series", } @BOOK{Bishop06, AUTHOR = "Christopher M. Bishop", TITLE = "Pattern Recognition and Machine Learning", YEAR = 2006, PUBLISHER = "Springer Verlag", ADDRESS = "New York" } @BOOK{Csato08, AUTHOR = "Lehel Csat\'{o} and Zal\'{a}n Bod\'{o}", TITLE = "Neurális hálók és a gépi tanulás módszerei (Re\c{t}ele neurale \c{s}i metode de instruire automat\u{a})", YEAR = "2008", PUBLISHER = "Presa Universitar\u{a} Clujean\u{a}", ADDRESS = "Cluj-Napoca", } @Book{Morelos02, author = "Robert Morelos-Zaragoza", title = "The Art of Error Correcting Coding", publisher = "John Wiley and Sons, Inc.", address = "pub-WILEY:adr", pages = "xvi + 221", year = "2002", ISBN = "0-471-49581-6", isbn-13 = "978-0-471-49581-9", } @Article{Diettrich95, author = "T. G. Dietterich and G. Bakiri", title = "Solving Multiclass Learning Problems via Error-Correcting Output Codes", journal = "Journal of Artificial Intelligence Research", volume = "2", year = "1995", pages = "263--286", } @InProceedings{Platt99, title = "Large Margin {DAG}s for Multiclass Classification", author = "John C. Platt and Nello Cristianini and John Shawe-Taylor", publisher = "The MIT Press", year = "1999", bibdate = "2003-05-28", booktitle = "NIPS", editor = "Sara A. Solla and Todd K. Leen and Klaus-Robert M{\"u}ller", ISBN = "0-262-19450-3", pages = "547--553", URL = "http://nips.djvuzone.org/djvu/nips12/0547.djvu", } @Inproceedings{Weston99, author= "J. Weston and C. Watkins", title= "Support vector machines for multiclass pattern recognition", booktitle= "Proceedings of the Seventh European Symposium On Artificial Neural Networks", year= "1999", month= "4", url= "http://citeseer.ist.psu.edu/article/weston99support.html", } @InProceedings{Crammer02, title = "A new family of online algorithms for category ranking", author = "Koby Crammer and Yoram Singer", booktitle = {The 25th Annual International ACM SIGIR Conference}, publisher = "ACM", year = "2002", URL = "http://doi.acm.org/10.1145/564376.564404" } @Misc{Hsu01, title = "A Comparison of Methods for Multi-class Support Vector Machines", author = "Chih-wei Hsu and Chih-jen Lin", year = "2001", URL = "http://citeseer.ist.psu.edu/537288.html", } @INPROCEEDINGS{Berger99, author = {Adam Berger}, title = {Error-correcting output coding for text classification}, booktitle = {Proceedings of IJCAI-99 Workshop on Machine Learning for Information Filtering}, year = {1999}, } @Misc{Lin03, title = "A Study on Sigmoid Kernels for {SVM} and the Training of non-{PSD} Kernels by {SMO}-type Methods", author = "Hsuan-tien Lin and Chih-jen Lin", year = "2003", URL = "http://citeseer.ist.psu.edu/584223.html", } @Article{Furnkrantz02, author = "Johannes F{\"u}rnkranz", title = "Round Robin Classification", journal = "Journal of Machine Learning Research", volume = "2", year = "2002", pages = "721--747", } @Book{Baeza99, author = "Ricardo Baeza-Yates and Berthier Ribeiro-Neto", keywords = "information retrieval", publisher = "Addison-Wesley", title = "Modern Information Retrieval", URL = "http://sunsite.dcc.uchile.cl/irbook", year = "1999", } @InProceedings{Fuhr91, author = "Norbert Fuhr and Stephan Hartmann and Gerhard Knorz and Gerhard Lustig and Michael Schwantner and Konstadinos Tzeras", title = "{AIR/X} -- a Rule-Based Multistage Indexing System for Large Subject Fields", booktitle = "Proceedings of RIAO-91, 3rd International Conference ``Recherche d'Information Assistee par Ordinateur''", publisher = "Elsevier Science Publishers, Amsterdam, NL", editor = "Andr{\'e} Lichnerowicz", address = "Barcelona, ES", year = "1991", pages = "606--623", URL = "http://www.darmstadt.gmd.de/~tzeras/FullPapers/gz/Fuhr-etal-91.ps.gz", } @Article{Yang99a, author = "Yiming Yang", title = "An evaluation of statistical approaches to text categorization", journal = "Information Retrieval", volume = "1", number = "1-2", pages = "69--90", year = "1999", URL = "citeseer.nj.nec.com/yang97evaluation.html", } @InProceedings{Yang99b, author = "Yiming Yang and Xin Liu", title = "A re-examination of text categorization methods", booktitle = "SIGIR", year = "1999", pages = "42--49", } @InProceedings{Yang97, author = "Yiming Yang and Jan O. Pedersen", title = "A Comparative Study on Feature Selection in Text Categorization", booktitle = "International Conference on Machine Learning", pages = "412--420", year = "1997", URL = "citeseer.nj.nec.com/yang97comparative.html", } @Article{Sebastiani02, author = "Fabrizio Sebastiani", year = "2002", title = "Machine learning in automated text categorization", journal = "ACM Computing Surveys", volume = "34", number = "1", pages = "1--47", } @Article{Guyon03, author = "Isabelle Guyon and Andr{\'{e}} Elisseeff", title = "An Introduction to Variable and Feature Selection", journal = "Journal of Machine Learning Research", volume = "3", year = "2003", pages = "1157--1182", } @Book{Zdziarski05, author = "Jonathan A. Zdziarski", title = "Ending spam: {Bayesian} content filtering and the art of statistical language classification", publisher = "No Starch Press", address = "pub-NO-STARCH:adr", pages = "312 (est.)", year = "2005", ISBN = "1-59327-052-6", isbn-13 = "978-1-59327-052-0", LCCN = "TK5105.743 .Z35 2005", bibdate = "Wed Jun 22 14:40:22 MDT 2005", bibsource = "z3950.loc.gov:7090/Voyager", URL = "ftp://uiarchive.cso.uiuc.edu/pub/etext/gutenberg/; http://www.oreilly.com/catalog/1593270526/; http://www.loc.gov/catdir/toc/ecip0510/2005008221.html", subject = "Spam filtering (Electronic mail); Filters (Mathematics)", } @InProceedings{Minier06, author = "Zsolt Minier and Zal\'{a}n Bod\'{o} and Lehel Csat\'{o}", title = "Segmentation-based feature selection for text categorization", booktitle = "Proceedings of the 2nd International Conference on Intelligent Computer Communication and Processing (ICCP 2006)", year = "2006", month = "September 1--2", location = "Cluj-Napoca, Romania", publisher = "IEEE", pages = "53--59", } @InProceedings{Bodo07, author = "Zal\'{a}n Bod\'{o} and Zsolt Minier and Lehel Csat\'{o}", year = "2007", title = "Text Categorization Experiments Using {W}ikipedia", booktitle = "Proceedings of the conference Knowledge Engineering: Principles and Techniques (KEPT 2007)", location = "Cluj-Napoca, Romania", month = "June 6--7", publisher = "Presa Universitarã Clujeanã", note = "Special Issue of Studia Universitatis Babe\c{s}-Bolyai, Series Informatica", pages = "66--72", } @InProceedings{Minier07, author = "Zsolt Minier and Zal\'{a}n Bod\'{o} and Lehel Csat\'{o}", year = "2007", title = "Wikipedia-based Kernels for Text Categorization", booktitle = "Proceedings of the 9th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC 2007)", month = "September 26--29", publisher = "IEEE", location = "Timi\c{s}oara, Romania", pages = "157--164", } @InProceedings{Bodo08, author = "Zal\'{a}n Bod\'{o}", title = "Hierarchical Cluster Kernels For Supervised And Semi-Supervised Learning", booktitle = "Proceedings of the 4nd International Conference on Intelligent Computer Communication and Processing (ICCP 2008)", year = "2008", month = "August 28--30", location = "Cluj-Napoca, Romania", publisher = "IEEE", pages = "9--16", } @techreport{Miller93, author = "G. A. Miller and R. Beckwith and C. Fellbaum and D. Gross and K. Miller", title = "Five Papers on WordNet", type = "{Technical Report}", year = "1993", institution = "Cognitive Science Laboratory, Princeton University", } @inproceedings{Corley05, author = "Courtney Corley and Andr{\'a}s Csomai and Rada Mihalcea", title = "Text Semantic Similarity, with Applications", booktitle = "Proceedings of International Conference Recent Advances in Natural Language Processing (RANLP 2005)", location = "Borovets, Bulgaria", month = "September", year = "2005", } @Article{Weston03, author = "Jason Weston and Andr{\'{e}} Elisseeff and Bernhard Sch{\"o}lkopf and Mike Tipping", title = "Use of the Zero-Norm with Linear Models and Kernel Methods", journal = "Journal of Machine Learning Research", volume = "3", year = "2003", pages = "1439--1461", } @Article{Lodhi02, author = "Huma Lodhi and Craig Saunders and John Shawe-Taylor and Nello Cristianini and Chris Watkins", title = "Text Classification using String Kernels", journal = "Journal of Machine Learning Research", volume = "2", year = "2002", pages = "419--444", } @InProceedings{Vishwanathan02a, title = "Fast Kernels for String and Tree Matching", author = "S. V. N. Vishwanathan and Alexander J. Smola", publisher = "MIT Press", year = "2002", bibdate = "2006-02-15", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/nips/nips2002.html#ViswanathanS02", booktitle = "NIPS", editor = "Suzanna Becker and Sebastian Thrun and Klaus Obermayer", ISBN = "0-262-02550-7", pages = "569--576", URL = "http://books.nips.cc/papers/files/nips15/AA11.pdf", } @InProceedings{Leslie03, author = "Christina Leslie and Rui Kuang", title = "Fast Kernels for Inexact String Matching", booktitle = "COLT: Proceedings of the Workshop on Computational Learning Theory, Morgan Kaufmann Publishers", year = "2003", } @InProceedings{Leslie02, title = "Mismatch String Kernels for {SVM} Protein Classification", author = "Christina S. Leslie and Eleazar Eskin and Jason Weston and William Stafford Noble", publisher = "MIT Press", year = "2002", bibdate = "2004-10-12", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/nips/nips2002.html#LeslieEWN02", booktitle = "NIPS", editor = "Suzanna Becker and Sebastian Thrun and Klaus Obermayer", ISBN = "0-262-02550-7", pages = "1417--1424", URL = "http://books.nips.cc/papers/files/nips15/AP03.pdf", } @Article{Cristianini02, title = "Latent Semantic Kernels", author = "Nello Cristianini and John Shawe-Taylor and Huma Lodhi", journal = "J. Intell. Inf. Syst", year = "2002", number = "2-3", volume = "18", bibdate = "2003-12-03", bibsource = "DBLP, http://dblp.uni-trier.de/db/journals/jiis/jiis18.html#CristianiniSL02", pages = "127--152", } @Book{ShaweTaylor04, author = "J. Shawe-Taylor and N. Cristianini", title = "Kernel Methods for Pattern Analysis", publisher = "Cambridge University Press", year = "2004", URL = "http://www.kernel-methods.net/", bibsource = "http://www.visionbib.com/bibliography/book28.html#TT1458", } @InProceedings{Cristianini03, title = "Kernel Methods for Text Processing", author = "N. Cristianini and J. Kandola and A. Vinokourov and J. Shawe-Taylor", publisher = "IOS Press", year = "2003", bibdate = "2004-10-12", booktitle = "Advances in Learning Theory: Methods, Models and Applications", editor = "J. A. K. Suykens and G. Horv{\'a}th and S. Basu and C. Micchelli and J. Vandewalle", pages = "197--221", } @Book{VanRijsbergen79, author = "Cornelis J. Van Rijsbergen", year = "1979", publisher = "Butterworths", title = "Information Retrieval", } @incollection{Weston06, author = "Jason Weston and Christina Leslie and Eugene Ie and William Stafford Noble", title = "Semi-Supervised Protein Classification Using Cluster Kernels", booktitle = "Semi-Supervised Learning", editor = "Olivier Chapelle and Bernhard Sch{\"o}lkopf and Alexander Zien", publisher = "MIT Press", year = "2006", chapter = "19", pages = "343--360" } @Book{Cormen01, address = "Cambridge, MA", year = "2001", title = "Introduction to Algorithms", publisher = "MIT Press", author = "T. H. Cormen and C. E. Leiserson and R. L. Rivest and C. Stein", } @InProceedings{Dhillon04, title = "Kernel k-means: spectral clustering and normalized cuts", author = "Inderjit S. Dhillon and Yuqiang Guan and Brian Kulis", booktitle = {ACM SIGKDD -- Knowledge discovery and data mining}, URL = "http://doi.acm.org/10.1145/1014052.1014118", year = 2004, pages = {551--556} } @TechReport{Vishwanathan02b, title = "Kernel Enabled {K}-Means Algorithm", author = "S.V.N. Vishwanathan and Narasimha M. Murty", institution = {The Indian Institute of Science, Bangalore}, year = "2002", URL = "http://eprints.iisc.ernet.in/archive/00000010", } @Book{Lutkepohl96, author = "H. L{\"u}tkepohl", title = "Handbook of matrices", publisher = "John Wiley \& Sons Ltd.", address = "Chichester", year = "1996", pages = "xvi+304", ISBN = "0-471-97015-8", } @InProceedings{Ng02, author = "Andrew Y. Ng and Michael Jordan and Yair Weiss", title = "On Spectral Clustering: Analysis and an algorithm", booktitle = "Advances in Neural Information Processing Systems 14", editor = "T. G. Dietterich and S. Becker and Zoubin Ghahramani", year = "2002", publisher = "MIT Press", address = "Cambridge, MA", URL = "http://www-2.cs.cmu.edu/\~{}nips/2001papers/psgz/AA35.ps.gz", } @InProceedings{Sindhwani05, title = "Beyond the point cloud: from transductive to semi-supervised learning", author = "Vikas Sindhwani and Partha Niyogi and Mikhail Belkin", bibdate = "2006-04-25", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/icml/icml2005.html#SindhwaniNB05", booktitle = "Machine Learning, Proceedings of the Twenty-Second International Conference ({ICML} 2005), Bonn, Germany, August 7-11, 2005", publisher = "ACM", year = "2005", volume = "119", editor = "Luc De Raedt and Stefan Wrobel", ISBN = "1-59593-180-5", pages = "824--831", series = "ACM International Conference Proceeding Series", URL = "http://doi.acm.org/10.1145/1102351.1102455", } @techreport{Luxburg06, author = {Ulrike von Luxburg}, institution = {Max Planck Institute for Biological Cybernetics}, month = {August}, number = {149}, title = {A tutorial on spectral clustering}, year = {2006} } @phdthesis{Bie05, author = {Tijl De Bie}, title = {Semi-Supervised Learning Based On Kernel Methods And Graph Cut Algorithms}, year = {2005}, school = {Katholieke Universiteit Leuven}, address = {Kasteelpark Arenberg 10, 3001 Leuven (Heverlee)}, } @Book{Cover06, author = "T. Cover and J. Thomas", title = "Elements of Information Theory, Second Edition", publisher = "Wiley-Interscience", year = "2006", } @phdthesis{Zhu05, author = {Xiaojin Zhu}, note = {Chair-John Lafferty and Chair-Ronald Rosenfeld}, title = {Semi-supervised learning with graphs}, year = {2005}, isbn = {0-542-19059-1}, order_no = {AAI3179046}, school = {Carnegie Mellon University}, address = {Pittsburgh, PA, USA}, } @techreport{Zhu02, author = "Xiaojin Zhu and Zoubin Ghahramani", title = "Learning from labeled and unlabeled data with label propagation", institution = "Carnegie Mellon University", number = "CMU-CALD-02-107", year = "2002", } @InProceedings{Chung97, author = "Chung", title = "Spectral Graph Theory (reprinted with corrections)", booktitle = "CBMS: Conference Board of the Mathematical Sciences, Regional Conference Series", year = "1997", } @InProceedings{Zhou04, title = "Semi-supervised Learning on Directed Graphs", author = "Dengyong Zhou and Bernhard Sch{\"o}lkopf and Thomas Hofmann", year = "2004", bibdate = "2006-02-13", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/nips/nips2004.html#ZhouSH04", booktitle = "NIPS", URL = "http://books.nips.cc/papers/files/nips17/NIPS2004_0540.pdf", } @InProceedings{Blum01, author = "Avrim Blum and Shuchi Chawla", title = "Learning from Labeled and Unlabeled Data Using Graph Mincuts", booktitle = "Proc. 18th International Conf. on Machine Learning", publisher = "Morgan Kaufmann, San Francisco, CA", year = "2001", pages = "19--26", } @techreport{Page98, author = "Lawrence Page and Sergey Brin and Rajeev Motwani and Terry Winograd", institution = "Stanford Digital Library Technologies Project", title = "The PageRank Citation Ranking: Bringing Order to the Web", year = "1998", } @book{Langville06, author = {Langville, Amy N. and Meyer, Carl D. }, howpublished = {Hardcover}, isbn = {0691122024}, publisher = {{Princeton University Press}}, title = {Google's PageRank and Beyond: The Science of Search Engine Rankings}, year = {2006} } @Article{Cohn96, author = "David A. Cohn and Zoubin Ghahramani and Michael I. Jordan", title = "Active Learning with Statistical Models", journal = "Journal of Artificial Intelligence Research", ISSN = "1076-9757", pages = "129--145", volume = "4", year = "1996", } @phdthesis{Basu05, title = "Semi-supervised Clustering: Probabilistic Models, Algorithms and Experiments", author = "Sugato Basu", year = "2005", school = "The University of Texas at Austin", } @InProceedings{Bie04, title = "Learning from General Label Constraints", author = "Tijl De Bie and Johan A. K. Suykens and Bart De Moor", booktitle = "Structural, Syntactic, and Statistical Pattern Recognition, Joint {IAPR} International Workshops, {SSPR} 2004 and {SPR} 2004, Lisbon, Portugal, August 18-20, 2004 Proceedings", publisher = "Springer", year = "2004", volume = "3138", editor = "Ana L. N. Fred and Terry Caelli and Robert P. W. Duin and Aur{\'e}lio C. Campilho and Dick de Ridder", ISBN = "3-540-22570-6", pages = "671--679", series = "Lecture Notes in Computer Science", } @Article{Nigam00, title = "Text Classification from Labeled and Unlabeled Documents using {EM}", author = "Kamal Nigam and Andrew McCallum and Sebastian Thrun and Tom M. Mitchell", journal = "Machine Learning", year = "2000", number = "2/3", volume = "39", bibdate = "2002-01-03", pages = "103--134", } @PhdThesis{Nigam01, title = "Using unlabeled data to improve text classification", author = "Kamal Nigam", publisher = "Pittsburgh, Pa., School of Computer Science, Carnegie Mellon University,", year = "2001", school = "Carnegie Mellon University", subject = "Text processing (Computer science); Data mining.", } @Book{Mitchell97, author = "Tom Mitchell", year = "1997", publisher = "McGraw-Hill", title = "Machine Learning", } @Book{Vapnik98, author = "V. Vapnik", title = "Statistical Learning Theory", publisher = "Wiley", year = "1998", } @Article{Aizerman64, title = "Theoretical foundations of the potential function method in pattern recognition learning", author = "A. Aizerman and E. M. Braverman and L. I. Rozonoer", journal = "Automation and Remote Control", year = "1964", volume = "25", pages = "821--837", } @Article{Boser92, title = "A Training Algorithm for Optimal Margin Classifiers", author = "B. E. Boser and I. Guyon and V. N. Vapnik", journal = "Computational Learning Theory", year = "1992", volume = "5", pages = "144--152", } @Article{Roweis00, author = "S. T. Roweis and L. K. Saul", title = "Nonlinear Dimensionality Reduction by Locally Linear Embedding", journal = "Science", volume = "290", year = "2000", pages = "2323--2326", URL = "http://www.sciencemag.org/content/vol290/issue5500/", bibsource = "http://www.visionbib.com/bibliography/pattern601.html#TT44718", } @misc{Saul01, author = "L. K. Saul and S. T. Roweis", title = "An Introduction to Locally Linear Embedding", year = "2001", } @inproceedings{Decoste01, author = "Dennis {DeCoste}", title = "Visualizing mercer kernel feature spaces via kernelized locally-linear embeddings", booktitle = "8th International Conference on Neural Information Processing", year = "2001", url = "citeseer.ist.psu.edu/decoste01visualizing.html" } @inproceedings{Busa05, author = "R{\'o}bert Busa-Fekete and Andr{\'a}s Kocsor", title = "Locally Linear Embedding and its Variants for Feature Extraction", booktitle = "IEEE International Workshop on Soft Computing Applications, SOFA 2005", year = "2005", } @misc{Shlens05, author = "Jonathon Shlens", title = "A Tutorial on Principal Component Analysis", year = "2005", address = "Salk Institute for Biological Studies University of California, San Diego", } @article{Scholkopf99, author = {Bernhard Sch{\"o}lkopf and Alexander J. Smola and Klaus-Robert M{\"u}ller}, title = {Kernel principal component analysis}, journal = {Advances in kernel methods: support vector learning}, year = {1999}, isbn = {0-262-19416-3}, pages = {327-352}, publisher = {MIT Press}, address = {Cambridge, MA, USA}, url = {citeseer.ist.psu.edu/article/sch99kernel.html} } @TechReport{Scholkopf96, author = "Berhard Sch{\"o}lkopf and Alexander Smola and Klaus-Robert M{\"u}ller", title = "Nonlinear Component Analysis as a Kernel Eigenvalue Problem", institution = "Max-Planck Institut f{\"u}r biologische Kybernetik, Arbeitsgruppe B{\"u}lthoff", year = "1996", number = "44", address = "Spemannstrasse 38, 2076 Tobingen, Germany", month = dec, keywords = "nonlinear component analysis; principal component analysis", abstract = "We describe a new method for performing a nonlinear form of Principal Component Analysis. By the use of integral operator kernel functions, we can efficiently compute principal components in high-dimensional feature spaces, related to input space by some nonlinear map; for instance the space of all possible 5-pixel products in $16 \times 16$ images. We give the derivation of the method, along with a discussion of other techniques which can be made nonlinear with the kernel approach; and present first experimental results on nonlinear feature extraction for pattern recognition.", } @InProceedings{Kandola02, title = "Learning Semantic Similarity", author = "Jaz S. Kandola and John Shawe-Taylor and Nello Cristianini", publisher = "MIT Press", year = "2002", booktitle = "NIPS", editor = "Suzanna Becker and Sebastian Thrun and Klaus Obermayer", ISBN = "0-262-02550-7", pages = "657--664", URL = "http://books.nips.cc/papers/files/nips15/AA22.pdf", } @InProceedings{Joachims98, title = "Text Categorization with Suport Vector Machines: Learning with Many Relevant Features", author = "Thorsten Joachims", booktitle = "Machine Learning: {ECML}-98, 10th European Conference on Machine Learning, Chemnitz, Germany, April 21-23, 1998, Proceedings", publisher = "Springer", year = "1998", volume = "1398", editor = "Claire Nedellec and C{\'e}line Rouveirol", ISBN = "3-540-64417-2", pages = "137--142", series = "Lecture Notes in Computer Science", } @TechReport{Joachims97, author = "Thorsten Joachims", year = "1997", address = "Dortmund, Germany", institution = "Universit{\"a}t Dortmund", number = "LS VIII-Report", title = "Text Categorization with support vector machines: Learning with many relevant features", } @techreport{Varelas05, title = "Semantic Similarity Methods in WordNet and Their Application to Information Retrieval on the Web", author = "Giannis Varelas", institution = "Technical Univ. of Crete (TUC), Dept. of Electronic and Computer Engineering, Chania, Crete, Greece", year = "2005", number = "TR-TUC-ISL-01-2005", url = "http://www.intelligence.tuc.gr/publications/Varelas.pdf" } @misc{Hirst97, title = "Lexical Chains as Representations of Context for the Detection and Correction of Malapropisms", author = "Graeme Hirst and David St-onge", year = "1997", month = aug # "~31", citeseer-references = "oai:CiteSeerPSU:587343; oai:CiteSeerPSU:155268; oai:CiteSeerPSU:565397", annote = "Graeme Hirst (Department of Computer Science; University of Toronto; Toronto; Ontario; Canada M5S 1A4); David St-onge (Department of Computer Science; University of Toronto; Toronto; Ontario; Canada M5S 1A4);", bibsource = "OAI-PMH server at cs1.ist.psu.edu", description = "this paper, we examine the idea of lexical chains as such a representation. We show how they can be constructed by means of WordNet, and how they can be applied in one particular linguistic task: the detection and correction of malapropisms.", language = "en", oai = "oai:CiteSeerPSU:109361", rights = "unrestricted", URL = "http://citeseer.ist.psu.edu/109361.html; http://www.cs.utoronto.ca/~pedmonds/cl-group/pubs/ps-files/Hirst+StOnge-Wordnet-95.ps.gz", } @inproceedings{Wu94, title = "Verb Semantics and Lexical Selection", author = "Zhibiao Wu and Martha Stone Palmer", year = "1994", bibdate = "2004-02-13", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/acl/acl94.html#WuP94", booktitle = "ACL", pages = "133--138", } @inproceedings{Resnik95, title = "Using Information Content to Evaluate Semantic Similarity in a Taxonomy", author = "Philip Resnik", year = "1995", bibdate = "2002-01-03", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/ijcai/ijcai95.html#Resnik95", booktitle = "IJCAI", pages = "448--453", } @InProceedings{Patwardhan03, title = "Using Measures of Semantic Relatedness for Word Sense Disambiguation", author = "Siddharth Patwardhan and Satanjeev Banerjee and Ted Pedersen", booktitle = "Computational Linguistics and Intelligent Text Processing, 4th International Conference, {CICL}ing 2003, Mexico City, Mexico, February 16-22, 2003, Proceedings", publisher = "Springer", year = "2003", volume = "2588", editor = "Alexander F. Gelbukh", ISBN = "3-540-00532-3", pages = "241--257", series = "Lecture Notes in Computer Science", URL = "http://link.springer.de/link/service/series/0558/bibs/2588/25880241.htm", } @inproceedings{Banerjee02, title = "An Adapted Lesk Algorithm for Word Sense Disambiguation Using WordNet", author = "Satanjeev Banerjee and Ted Pedersen", year = "2002", bibdate = "2002-02-06", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/cicling/cicling2002.html#BanerjeeP02", booktitle = "CICLing", pages = "136--145", URL = "http://link.springer.de/link/service/series/0558/bibs/2276/22760136.htm", } @article{Schutze98, title = "Automatic Word Sense Discrimination", author = "Hinrich Sch{\"u}tze", journal = "Computational Linguistics", year = "1998", number = "1", volume = "24", bibdate = "2002-01-03", bibsource = "DBLP, http://dblp.uni-trier.de/db/journals/coling/coling24.html#Schutze98", pages = "97--123", } @Article{Deerwester90, author = "Scott Deerwester and Susan T. Dumais and George W. Furnas and Thomas K. Landauer and Richard Harshman", title = "Indexing by Latent Semantic Analysis", journal = "Journal of the American Society for Information Science", year = "1990", month = jun, volume = "41", entered-by = "Lucy Berlin", keywords = "lsi, latent semantic indexing, IR", abstract = "~", } @inproceedings{Lin98, title = "An Information-Theoretic Definition of Similarity", author = "Dekang Lin", year = "1998", bibdate = "2002-12-04", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/icml/icml1998.html#Lin98", booktitle = "ICML", pages = "296--304", } @InProceedings{Lewis95, author = "David D. Lewis", year = "1995", address = "New York, NY, USA", booktitle = "SIGIR '95", pages = "246--254", publisher = "ACM Press", title = "Evaluating and optimizing autonomous text classification systems", } @Book{Tikk07, author = "Domonkos Tikk", title = "Sz{\"o}vegb{\'a}ny{\'a}szat", publisher = "Typotex", year = "2007", address = "Budapest", } @Book{Jackson02, title = "Natural Language Processing for Online Applications: Text Retrieval, Extraction \& Categorization", author = "Peter Jackson and Isabelle Moulinier", publisher = "John Benjamins", year = "2002", bibdate = "2003-07-16", ISBN = "90-272-4989-X", URL = "http://members.aol.com/JacksonPE/music1/nlp4olap.htm", } @InProceedings{Moschitti03, title = "A Study on Optimal Parameter Tuning for Rocchio Text Classifier", author = "Alessandro Moschitti", bibdate = "2003-04-30", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/ecir/ecir2003.html#Moschitti03", booktitle = "Advances in Information Retrieval, 25th European Conference on {IR} Research, {ECIR} 2003, Pisa, Italy, April 14-16, 2003, Proceedings", publisher = "Springer", year = "2003", volume = "2633", editor = "Fabrizio Sebastiani", ISBN = "3-540-01274-5", pages = "420--435", series = "Lecture Notes in Computer Science", URL = "http://link.springer.de/link/service/series/0558/bibs/2633/26330420.htm", } @Book{Tatar03, title = "Aplica\c{t}ii \^{\i}n prelucrarea limbajului natural", author = "Doina T\u{a}tar", publisher = "Editura Albastr\u{a}", year = "2003", } @Article{Yang94, title = "An Example-Based Mapping Method for Text Categorization and Retrieval", author = "Yiming Yang and Christopher G. Chute", journal = "ACM Transactions on Information Systems", pages = "252--295", month = jul, year = "1994", volume = "12", number = "3", } @InProceedings{Yang92, title = "A Linear Least Squares Fit Mapping Method For Information Retrieval From Natural Language Texts", author = "Yiming Yang and Christopher G. Chute", year = "1992", bibdate = "2004-06-24", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/coling/coling1992.html#YangC92", booktitle = "COLING", pages = "447--453", URL = "http://acl.ldc.upenn.edu/C/C92/C92-2069.pdf", } @Misc{Rennie02, title = "Not Too Hot, Not Too Cold: The Bundled-{SVM} is Just Right!", author = "Lawrence Shih and Yu-han Chang and Jason Rennie and David Karger", year = "2002", month = jul # "~10", abstract = "The Support Vector Machine (SVM) typically outperforms other algorithms on text classification problems, but requires training time roughly quadratic in the number of training documents. In contrast, linear time algorithms like Naive Bayes have lower performance, but can easily handle huge training sets. In this paper, we describe a technique that creates a continuum of classifiers between the SVM and a Naive Bayes like algorithm.", annote = "David Karger (Artificial Intelligence Laboratory ; Massachusetts Institute of Technology ; Cambridge , MA 02139);", bibsource = "OAI-PMH server at cs1.ist.psu.edu", language = "en", oai = "oai:CiteSeerPSU:527366", rights = "unrestricted", URL = "http://citeseer.ist.psu.edu/527366.html; http://www.ai.mit.edu/~jrennie/papers/icml02-bundled.ps.gz", } @Misc{Voss05, author = {Jakob Voss}, title = {Measuring Wikipedia}, url = {http://www.citebase.org/abstract?id=oai:eprints.rclis.org:3610}, year = {2005} } @article{Salton75, author = "G. Salton and A. Wong and A. C. S. Yang", year = "1975", journal = "Communications of the ACM", pages = "229--237", volume = "18", title = "A vector space model for automatic indexing", } @InProceedings{Gabrilovich07, author = "Evgeniy Gabrilovich and Shaul Markovitch", year = "2007", title = "Computing Semantic Relatedness using Wikipedia-based Explicit Semantic Analysis", booktitle = "Proceedings of The 20th International Joint Conference on Artificial Intelligence {(IJCAI)}", location = "Hyderabad, India", month = "January", } @InProceedings{Gliozzo05, author = "Alfio Gliozzo and Carlo Strapparava", title = "Domain Kernels for Text Categorization", booktitle = "Proceedings of the Ninth Conference on Computational Natural Language Learning (CoNLL-2005)", month = jun, year = "2005", address = "Ann Arbor, Michigan", publisher = "Association for Computational Linguistics", pages = "56--63", URL = "http://www.aclweb.org/anthology/W/W05/W05-0608", } @InProceedings{Wong85, author = "S. K. M. Wong and W. Ziarko and P. C. N. Wong", year = "1985", month = jun, address = "Montreal, Quebec, Canada", booktitle = "Proceedings of the 8th annual international ACM SIGIR conference on Research and development in information retrieval", editor = "Jean M. Tague", pages = "18--25", publisher = "ACM Press", title = "Generalized vector spaces model in information retrieval, Proceedings of the 8th annual international {ACM} {SIGIR} conference on Research and development in information retrieval", } @Article{Wong87, author = "S. K. M. Wong and W. Ziarko and V. V. Raghavan and P. C. N. Wong", title = "On Modeling of Information Retrieval Concepts in Vector Spaces", journal = "ACM Trans. on Database Sys.", volume = "12", number = "2", pages = "299", month = jun, year = "1987", keywords = "TODS", } @InProceedings{Lee05, title = "An empirical evaluation of models of text document similarity", author = "Michael D. Lee and Brandon Pincombe and Matthew Welsh", year = 2005, booktitle = "CogSci2005", pages = "1254--1259", URL = "www.rpi.edu/~grayw/courses/cogs6100-CEg/fall05/downloads/LeePinWel05_CSC.pdf" } @Book{Duda01, author = "Richard Duda and Peter Hart and David Stork", title = "Pattern Classification", publisher = "John Wiley and Sons", year = "2001", note = "0-471-05669-3", } @TechReport{Berkhin02, author = "Pavel Berkhin", title = "Survey of clustering data mining techniques", type = "Technical report", institution = "Accrue Software", address = "San Jose, CA", year = "2002", } @Article{Ward63, author = "Joe H. {Ward, Jr.}", title = "Hierarchical grouping to optimize an objective function", journal = "Journal of the American Statistical Association", volume = "58", pages = "236--244", year = "1963", comment = "Reference from PRNN", } @book{Abadir05, author = {Karim M. Abadir and Jan R. Magnus}, publisher = {Cambridge University Press}, title = {Matrix Algebra}, year = {2005} } @article{Yang02, author = {Zhong-Peng Yang and Xian Zhang and Chong-Guang Cao}, title = {Inequalities involving Khatri-Rao products of Hermitian matrices}, journal = {The Korean Journal of Computational \& Applied Mathematics}, volume = {9}, number = {1}, year = {2002}, issn = {1229-9502}, pages = {125--133}, publisher = {The Editorial Office, KJCAM}, address = {Chungnam, Korea}, } @InProceedings{Hagen91, title = "Fast Spectral Methods for Ratio Cut Partitioning and Clustering", author = "Lars W. Hagen and Andrew B. Kahng", year = "1991", booktitle = "ICCAD", pages = "10--13", } @Article{Shi97, author = "J. Shi and J. Malik", title = "Normalized cuts and image segmentation", journal = "IEEE Conf. Computer Vision and Pattern Recognition", month = jun, year = "1997", keywords = "conf, 2D, image, IP, probability, inference, II, AI", abstract = "via rohan '99", } @techreport{Kandola02b, author = {J. Kandola and J. Shawe-Taylor and N. Cristianini}, publisher = {NeuroCOLT}, title = {Optimizing kernel alignment over combinations of kernels}, number = "2002-121", institution = {Department of Computer Science, Royal Holloway, University of London, UK}, year = {2002} } @InProceedings{Diosan07, title = "Improving {SVM} Performance Using a Linear Combination of Kernels", author = "Laura Diosan and Mihai Oltean and Alexandrina Rogozan and Jean-Pierre P{\'e}cuchet", bibdate = "2007-07-06", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/icannga/icannga2007-2.html#DiosanORP07", booktitle = "Adaptive and Natural Computing Algorithms, 8th International Conference, {ICANNGA} 2007, Warsaw, Poland, April 11-14, 2007, Proceedings, Part {II}", publisher = "Springer", year = "2007", volume = "4432", editor = "Bartlomiej Beliczynski and Andrzej Dzielinski and Marcin Iwanowski and Bernardete Ribeiro", ISBN = "978-3-540-71590-0", pages = "218--227", series = "Lecture Notes in Computer Science", } @article{Debole04, author = {Franca Debole and Fabrizio Sebastiani}, title = {An analysis of the relative hardness of Reuters-21578 subsets}, journal = {Journal of the American Society for Information Science and Technology}, year = {2004}, volume = {56}, pages = {971--974} } @Misc{Zhu07b, author = "Xiaojin Zhu", title = "Semi-Supervised Learning", year = "2007", note = "ICML 2007 Tutorial, Corvallis, OR, USA", URL = "http://pages.cs.wisc.edu/~jerryzhu/icml07tutorial.html", } @InProceedings{Zhu07c, title = "Humans Perform Semi-Supervised Classification Too", author = "Xiaojin Zhu and Timothy J. Rogers and Ruichen Qian and Chuck Kalish", publisher = "AAAI Press", year = "2007", bibdate = "2007-09-05", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/aaai/aaai2007.html#ZhuRQK07", booktitle = "AAAI", ISBN = "978-1-57735-323-2", pages = "864", } @Book{Estes94, title = {Classification and Cognition}, author = {W. K. Estes}, publisher = {Oxford University Press}, year = {1994}, isbn = {9780195073355}, keywords = {categorisation, cognitive psychology, science, } } @article{Estes07, author = {Graf K. Estes and Julia L. Evans and Martha W. Alibali and Jenny R. Saffran}, issn = {0956-7976}, journal = {Psychological Science}, month = {March}, number = {3}, pages = {254--260}, publisher = {Blackwell Publishing}, title = {Can Infants Map Meaning to Newly Segmented Words?: Statistical Segmentation and Word Learning}, volume = {18}, year = {2007} } @Book{Hawkins04, author = "Jeff Hawkins and Sandra Blakeslee", title = "On Intelligence", publisher = "Times Books", year = "2004", address = "New York", ISBN = "0-8050-7456-2", } @techreport{Langley06, author = {Pat Langley}, title = {Intelligent Behavior in Humans and Machines}, institution = {Computational Learning Laboratory, CSLI, Stanford University, CA}, year = {2006} } @techreport{Mitchell06, author = {Tom M. Mitchell}, title = {The Discipline of Machine Learning}, number = "CMU-ML-06-108", institution = "School of Computer Science, Carnegie Mellon University, Pittsburgh, PA", year = {2006} } @Article{Jain99, author = "A. K. Jain and M. N. Murty and P. J. Flynn", title = "Data Clustering: {A} Review", journal = "CSURV: Computing Surveys", volume = "31", year = "1999", } @Book{Russel95, author = "S. Russel and P. Norvig", title = "Artificial Intelligence: a Modern Approach", publisher = "Prentice-Hall", year = "1995", } @Article{Dempster77, author = "A. P. Dempster and N. M. Laird and Donald B. Rubin", title = "Maximum likelihood from incomplete data via the {EM} algorithm", journal = "Journal of the Royal Statistical Society, Series B", year = "1977", volume = "39", pages = "1--38", } @book{Grinstead03, title = {Introduction to Probability}, author = {Charles M. Grinstead and J. Laurie Snell}, howpublished = {GNU FDL PDF online}, institution = {AMS}, publisher = {AMS}, url = {http://www.dartmouth.edu/~chance/teaching_aids/books_articles/probability_book/book.html}, year = {2003}, } @misc{Sloughter01, title = "The Calculus of Functions of Several Variables", author = "Dan Sloughter", year = "2001", institution = "Furman University", } @Book{Jolliffe02, author = "I. T. Jolliffe", title = "Principal Component Analysis", series = "Series in Statistics", pages = "502", publisher = "Springer Verlag", year = "2002", } @Article{Cover67, author = "T. M. Cover and P. E. Hart", title = "Nearest Neighbor Pattern Classification", journal = "IEEE Transactions on Information Theory", year = "1967", volume = "IT-13", ref = "Q7", } @InProceedings{Bodo08b, author = "Zal\'{a}n Bod\'{o} and Zsolt Minier", title = "On Supervised and Semi-Supervised K-Nearest Neighbor Algorithms", booktitle = "Proceedings of the 7th Joint Conference on Mathematics and Computer Science", year = "2008", month = "July", location = "Cluj-Napoca, Romania", publisher = "Studia Universitatis Babe\c{s}-Bolyai, Series Informatica", volume = "LIII", number = "2", pages = "79--92", } @Article{Vishwanathan06, title = "Kernel extrapolation", author = "S. V. N. Vishwanathan and Karsten M. Borgwardt and Omri Guttman and Alexander J. Smola", journal = "Neurocomputing", year = "2006", number = "7-9", volume = "69", bibdate = "2006-05-02", pages = "721--729", } @Article{Bodo09, author = "Zal\'{a}n Bod\'{o} and Lehel Csat\'{o}", title = "Hierarchical and Reweighting Cluster Kernels for Semi-Supervised Learning", journal = "Carpathian Journal of Mathematics", year = "2009", note = "(submitted)", } @InCollection{Leacock98, author = "Claudia Leacock and Martin Chodorow", title = "Combining Local Context and {W}ord{N}et Similarity for Word Sense Identification", booktitle = "Word{N}et: An Electronic Lexical Database", publisher = "The {MIT} Press", year = "1998", editor = "Christaine Fellbaum", pages = "265--283", address = "Cambridge, Massachusetts", topic = "wordnet;lexical-disambiguation;", } @Article{Jiang97, title = "Semantic Similarity Based on Corpus Statistics and Lexical Taxonomy", author = "Jay J. Jiang and David W. Conrath", journal = "CoRR", year = "1997", volume = "cmp-lg/9709008", note = "informal publication", bibdate = "2008-01-02", bibsource = "DBLP, http://dblp.uni-trier.de/db/journals/corr/corr9709.html#cmp-lg-9709008", URL = "http://arxiv.org/abs/cmp-lg/9709008", } @InProceedings{Csato09, author = "Lehel Csat\'{o} and Zal\'{a}n Bod\'{o}", year = "2009", title = "Decomposition Methods for Label Propagation", booktitle = "Proceedings of the conference Knowledge Engineering: Principles and Techniques (KEPT 2009)", location = "Cluj-Napoca, Romania", month = "July 2--4", publisher = "Presa Universitarã Clujeanã", note = "Special Issue of Studia Universitatis Babe\c{s}-Bolyai, Series Informatica", pages = "127--130", } @InProceedings{Bodo09b, author = "Zal\'{a}n Bod\'{o} and Zsolt Minier", year = "2009", title = "Semi-supervised Feature Selections with SVMS", booktitle = "Proceedings of the conference Knowledge Engineering: Principles and Techniques (KEPT 2009)", location = "Cluj-Napoca, Romania", month = "July 2--4", publisher = "Presa Universitarã Clujeanã", note = "Special Issue of Studia Universitatis Babe\c{s}-Bolyai, Series Informatica", pages = "159--162", }