%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%                                                                      %
%                                                                      %
%          A Bibliography fot the EACL 03 tutorial on                  %
%       Text Representation for Automatic Text Categorization          %
%                                                                      %
%                          compiled by                                 %
%                                                                      %
%                      Jose Maria Gomez Hidalgo                        %
%               Departamento de Inteligencia Artificial                %
%                      Universidad Europea CEES                        %
%              Villaviciosa de Odon 28670, Madrid, Spain               %
%                    http://www.esi.uem.es/~jmgomez/                   %
%                                                                      %
% The tutorial web site is:                                            %
%    http://www.esi.uem.es/~jmgomez/tutorials/eacl03/index.html        %
% The EACL 03 conference web site is:                                  %
%    http://www.conferences.hu/EACL03/                                 %
%                                                                      %
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

@ARTICLE{Adams01,
  author = {Katherine C. Adams},
  year = 2001,
  title = {Representing Knowledge in Enterprise Portals},
  journal = {KMWorld Magazine},
  volume = 10,
  number = 5
}
@ARTICLE{Apte94,
  author = {Apt{\'e}, Chidanand and Damerau, Fred J. and Weiss, Sholom M.},
  year = 1994,
  title = {Automated learning of decision rules for text categorization},
  journal = {ACM Transactions on Information Systems},
  volume = 12,
  number = 3,
  pages = {233--251}
}
@ARTICLE{Belkin92,
  author =       {N.J. Belkin and W.B Croft},
  title =        {Information Filtering and Information Retrieval: Two Sides of the Same Coin?},
  journal =      {Communications of the ACM},
  year =         {1992},
  volume =       {35},
  number =       {12},
  pages =        {29--38}
}

@ARTICLE{Benkhalifa01,
  author = {Mohammed Benkhalifa and Abdelhak Mouradi and Houssaine Bouyakhf},
  year = 2001,
  title = {Integrating External Knowledge to Supplement Training Data in
          Semi-Supervised Learning for Text Categorization},
  journal = {Information Retrieval},
  volume = 4,
  number = 2,
  pages = {91--113}
}
@INPROCEEDINGS{Buenaga00,
  author = {Manuel {de Buenaga Rodr{\'{\i}}guez} and {Jos{\'e} M.} {G{\'o}mez
           Hidalgo} and Bel{\'e}n {D{\'{\i}}az Agudo}},
  editor = {N. Nicolov and R. Mitkov},
  year = 2000,
  title = {Using Wordnet to Complement Training Information in Text
          Categorization},
  booktitle = {Recent Advances in Natural Language Processing II: Selected
              Papers from RANLP'97},
  series = {Current Issues in Linguistic Theory (CILT)},
  volume = 189,
  pages = {353--364},
  publisher = {John Benjamins}
}

@INCOLLECTION{Caropreso01,
  author = {Maria Fernanda Caropreso and Stan Matwin and Fabrizio Sebastiani},
  editor = {Amita G. Chin},
  year = 2001,
  title = {A learner-independent evaluation of the usefulness of statistical
          phrases for automated text categorization},
  booktitle = {Text Databases and Document Management: Theory and Practice},
  pages = {78--102},
  publisher = {Idea Group Publishing},
  address = {Hershey, US}
}
@INPROCEEDINGS{Cavnar94,
  author = {William B. Cavnar and John M. Trenkle},
  year = 1994,
  title = {N-Gram-Based Text Categorization},
  booktitle = {Proceedings of SDAIR-94, 3rd Annual Symposium on Document
              Analysis and Information Retrieval},
  pages = {161--175},
  address = {Las Vegas, US}
}
@INPROCEEDINGS{Chen00,
  author = {Hao Chen and Susan T. Dumais},
  year = 2000,
  title = {Bringing order to the {W}eb: automatically categorizing search
          results},
  booktitle = {Proceedings of CHI-00, ACM International Conference on Human
              Factors in Computing Systems},
  pages = {145--152},
  publisher = {ACM Press, New York, US},
  address = {Den Haag, NL}
}
@inproceedings{Church88,
    author = "K. Church",
    title = "A Stochastic Parts Program and Noun Phrase Parser for Unrestricted Text",
    booktitle = "Proceedings of Second Conference on Applied Natural Language Processing (ANLP'88)",
    year = "1988"
}

@TECHREPORT{Clough00,
  author = {Paul Clough},
  year = 2000,
  title = {Plagiarism in Natural and Programming Languages: An Overview of
          Current Tools and Technologies},
  number = {CS-00-05},
  institution = {Department of Computer Science, The University of Sheffield}
}
@INCOLLECTION{Cohen95,
  author = {William W. Cohen},
  editor = {De Raedt, Luc},
  year = 1995,
  title = {Learning to classify {E}nglish text with {ILP} methods},
  booktitle = {Advances in inductive logic programming},
  pages = {124--143},
  publisher = {IOS Press},
  address = {Amsterdam, NL}
}
@INPROCEEDINGS{Cohen98,
  author = {William W. Cohen and Haym Hirsh},
  editor = {Rakesh Agrawal and Paul E. Stolorz and Gregory Piatetsky-Shapiro},
  year = 1998,
  title = {Joins that generalize: text classification using {{\sc Whirl}}},
  booktitle = {Proceedings of KDD-98, 4th International Conference on
              Knowledge Discovery and Data Mining},
  pages = {169--173},
  publisher = {AAAI Press, Menlo Park, US},
  address = {New York, US}
}
@INPROCEEDINGS{Copeck00,
  author = {Terry Copeck and Ken Barker and Sylvain Delisle and Stan
           Szpakowicz},
  year = 2000,
  title = {Automating the Measurement of Linguistic Features to Help Classify
          Texts as Technical},
  booktitle = {Proceedings of {TALN} 2000},
  pages = {101--110}
}
@INPROCEEDINGS{Dagan97,
  author = {Ido Dagan and Yael Karov and Dan Roth},
  editor = {Claire Cardie and Ralph Weischedel},
  year = 1997,
  title = {Mistake-driven learning in text categorization},
  booktitle = {Proceedings of EMNLP-97, 2nd Conference on Empirical Methods in
              Natural Language Processing},
  pages = {55--63},
  publisher = {Association for Computational Linguistics, Morristown, US},
  address = {Providence, US}
}
@ARTICLE{DeVel01,
  author = {Olivier Y. {de Vel} and A. Anderson and M. Corney and George M.
           Mohay},
  year = 2001,
  title = {Mining Email Content for Author Identification Forensics},
  journal = {SIGMOD Record},
  volume = 30,
  number = 4,
  pages = {55--64}
}
@INPROCEEDINGS{Diaz01,
  author = {A. {D{\'{\i}}az Esteban} and M. {Ma{\~n}a L{\'o}pez} and M. {de
           Buenaga Rodr{\'{\i}}guez} and J.M. {G{\'o}mez Hidalgo}},
  year = 2001,
  title = {Using Linear Classifiers in the Integration of User Modeling and
          Text Content Analysis in the Personalization of a Web-Based Spanish
          News Service},
  booktitle = {Proceedings of the Workshop on Machine Learning, Information
              Retrieval and User Modeling, 8th International Conference on
              User Modeling}
}
@INPROCEEDINGS{Dumais92,
  author = {S. Dumais and J. Nielsen},
  year = 1992,
  title = {Automating the Assignment of Submitted Manuscripts to Reviewers},
  booktitle = {Proceedings of the 15th Annual International {ACM} {SIGIR}
              Conference on Research and Development in Information Retrieval}
}
@PHDTHESIS{Fagan87,
  author = {Fagan, Joel L.},
  year = 1987,
  title = {Experiments in automatic phrase indexing for document retrieval: a
          comparison of syntactic and non-syntactic methods},
  address = {Ithaca, US},
  school = {Department of Computer Science, Cornell University}
}
@ARTICLE{Fagan89,
  author = {Joel L. Fagan},
  year = 1989,
  title = {The effectiveness of a nonsyntactic approach to automatic phrase
          indexing for document retrieval},
  journal = {Journal of the American Society for Information Science},
  volume = 40,
  number = 2,
  pages = {115--132}
}
@INPROCEEDINGS{Fayyad96,
  author = {Usama Fayyad and Gregory Piatetsky-Shapiro and Padhraic Smyth},
  year = 1996,
  title = {Knowledge Discovery and Data Mining: Towards an Unifying Framework},
  booktitle = {Proceedings of the Second International Conference on Knowledge
              Discovery and Data Mining},
  publisher = {AAAI Press}
}
@INPROCEEDINGS{Finn02,
  author = {Aidan Finn and Nicholas Kushmerick and Barry Smyth},
  editor = {Fabio Crestani and Mark Girolami and Cornelis J. van Rijsbergen},
  year = 2002,
  title = {Genre Classification and Domain Transfer for Information Filtering},
  booktitle = {Proceedings of ECIR-02, 24th European Colloquium on Information
              Retrieval Research},
  pages = {353--362},
  note = {Published in the ``Lecture Notes in Computer Science'' series,
         number 2291},
  publisher = {Springer Verlag, Heidelberg, DE},
  address = {Glasgow, UK}
}
@INCOLLECTION{Forsyth99,
  author = {Richard S. Forsyth},
  editor = {Alex Gammerman},
  year = 1999,
  title = {New directions in text categorization},
  booktitle = {Causal models and intelligent data management},
  pages = {151--185},
  publisher = {Springer Verlag},
  address = {Heidelberg, DE}
}

@INPROCEEDINGS{Fukumoto01,
  author = {Fumiyo Fukumoto and Yoshimi Suzuki},
  year = 2001,
  title = {Learning Lexical Representation for Text Categorization},
  booktitle = {Proceedings of the {NAACL} 2001 Workshop on {WordNet} and Other
              Lexical Resources}
}
@INPROCEEDINGS{Furnkranz98,
  author = {J. Furnkranz and T. Mitchell and E. Riloff},
  year = 1998,
  title = {A Case Study in Using Linguistic Phrases for Text Categorization on
          the {WWW}},
  booktitle = {{AAAI/ICML} Workshop on Learning for Text Categorization}
}
@INPROCEEDINGS{Giraldez02,
  author = {Ignacio Gir{\'a}ldez and Enrique Puertas and {Jos{\'e}
           Mar{\'{\i}}a G{\'o}mez} and Ra{\'u}l Murciano and Inmaculada
           Chac{\'o}n},
  year = 2002,
  title = {{HERMES}: Intelligent Multilingual News Filtering Based on Language
          Engineering for Advanced User Profiling},
  booktitle = {Multilingual Information Access and Natural Language Processing
              Workshop Proceedings},
  pages = {81--88}
}
@INPROCEEDINGS{Gomez00,
  author = {{Jos{\'e} M.} {G{\'o}mez Hidalgo} and M. Ma{\~n}a L{\'o}pez and E.
           Puertas Sanz},
  year = 2000,
  title = {Combining Text and Heuristics for Cost-Sensitive Spam Filtering},
  booktitle = {Proceedings of the Fourth Computational Natural Language
              Learning Workshop, CoNLL-2000},
  publisher = {Association for Computational Linguistics}
}

@INPROCEEDINGS{Gomez02,
  author = {{Jos{\'e} Mar{\'{\i}}a} {Gomez Hidalgo}},
  year = 2002,
  title = {Evaluating Cost-Sensitive Unsolicited Bulk Email Categorization},
  booktitle = {Proceedings of SAC-02, 17th ACM Symposium on Applied Computing},
  pages = {615--620},
  address = {Madrid, ES}
}
@INPROCEEDINGS{Gomez02b,
  author = {{G{\'o}mez Hidalgo}, Jose M. and de Buenaga Rodr{\'{\i}}guez,
           Manuel and Ure{\~n}a L{\'o}pez, Luis A. and Mart{\'{\i}}n Valdivia,
           Maria T. and Garc{\'{\i}}a Vega, Manuel},
  year = 2002,
  title = {Integrating Lexical Knowledge in Learning-Based Text Categorization},
  booktitle = {Proceedings of JADT-02, 6th International Conference on the
              Statistical Analysis of Textual Data},
  pages = {},
  address = {St-Malo, FR}
}
@ARTICLE{Gomez02c,
  author = {{Jos{\'e} Mar{\'{\i}}a} {G{\'o}mez Hidalgo} and {Manuel de}
           {Buenaga Rodr{\'{\i}}guez} and Francisco {Carrero Garc{\'{\i}}a}
           and Enrique {Puertas Sanz}},
  year = 2002,
  title = {Text Filtering at {POESIA}: A New Internet Content Filtering Tool
          for Educational Environments},
  journal = {Procesamiento del Lenguaje Natural},
  volume = 29,
  pages = {291--292}
}
@INPROCEEDINGS{Gonzalo98,
  author = {Julio Gonzalo and Felisa Verdejo and Irina Chugur and Juan
           Cigarran},
  year = 1998,
  title = {Indexing with {WordNet} Synsets Can Improve Text Retrieval},
  booktitle = {Proceedings of the {COLING/ACL} Workshop on Usage of {WordNet}
              in Natural Language Processing Systems}
}
@INPROCEEDINGS{Hayes90,
  author = {Philip J. Hayes and Steven P. Weinstein},
  editor = {Alain Rappaport and Reid Smith},
  year = 1990,
  title = {{\sc Construe/Tis}: a system for content-based indexing of a
          database of news stories},
  booktitle = {Proceedings of IAAI-90, 2nd Conference on Innovative
              Applications of Artificial Intelligence},
  pages = {49--66},
  publisher = {AAAI Press, Menlo Park, US}
}
@INPROCEEDINGS{Hearst94,
  author = {Marti Hearst},
  year = 1994,
  title = {Using Categories to Provide Context for Full-Text Retrieval Results},
  booktitle = {Proceedings of {RIAO}, Intelligent Multimedia Information
              Retrieval Systems and Management}
}
@InProceedings{Hearst99,
  author =       "Marti A. Hearst",
  title =        "Untangling Text Data Mining",
  booktitle =    "Proceedings of ACL'99: the 37th Annual Meeting of the Association for Computational Linguistics",
  year =         "1999"
}

@INPROCEEDINGS{Joachims98,
  author = {Thorsten Joachims},
  editor = {Claire N{\'e}dellec and C{\'e}line Rouveirol},
  year = 1998,
  title = {Text categorization with support vector machines: learning with
          many relevant features},
  booktitle = {Proceedings of ECML-98, 10th European Conference on Machine
              Learning},
  pages = {137--142},
  note = {Published in the ``Lecture Notes in Computer Science'' series,
         number 1398},
  publisher = {Springer Verlag, Heidelberg, DE},
  address = {Chemnitz, DE}
}
@INPROCEEDINGS{Junker97,
  author = {Markus Junker and Andreas Abecker},
  editor = {Ruslan Milkov and Nicolas Nicolov and Nilokai Nikolov},
  year = 1997,
  title = {Exploiting Thesaurus Knowledge in Rule Induction for Text
          Classification},
  booktitle = {Proceedings of RANLP-97, 2nd International Conference on Recent
              Advances in Natural Language Processing},
  pages = {202--207},
  publisher = {},
  address = {Tzigov Chark, BL}
}
@INPROCEEDINGS{Karlgren94,
  author = {Jussi Karlgren and Douglass Cutting},
  year = 1994,
  title = {Recognizing Text Genres with Simple Metrics Using Discriminant
          Analysis},
  booktitle = {Proceedings of {COLING} 94}
}
@INPROCEEDINGS{Kessler97,
  author = {Brett Kessler and Geoff Nunberg and Hinrich Sch{\"u}tze},
  editor = {Philip R. Cohen and Wolfgang Wahlster},
  year = 1997,
  title = {Automatic detection of text genre},
  booktitle = {Proceedings of ACL-97, 35th Annual Meeting of the Association
              for Computational Linguistics},
  pages = {32--38},
  publisher = {Morgan Kaufmann Publishers, San Francisco, US},
  address = {Madrid, ES}
}
@INPROCEEDINGS{Kindermann00,
  author = {J{\"o}rg Kindermann and Joachim Diederich and Edda Leopold and
           Gerhard Paa{\ss}},
  year = 2000,
  title = {Authorship Attribution with Support Vector Machines},
  booktitle = {The Learning Workshop}
}
@INPROCEEDINGS{Labrou99,
  author = {Yannis Labrou and Tim Finin},
  year = 1999,
  title = {{{\sc Yahoo!}} as an ontology: using {{\sc Yahoo!}}\ categories to
          describe documents},
  booktitle = {Proceedings of CIKM-99, 8th ACM International Conference on
              Information and Knowledge Management},
  pages = {180--187},
  publisher = {ACM Press, New York, US},
  address = {Kansas City, US}
}
@INPROCEEDINGS{Larkey96,
  author = {Leah S. Larkey and W. Bruce Croft},
  editor = {Hans-Peter Frei and Donna Harman and Peter Sch{\"a}uble and Ross
           Wilkinson},
  year = 1996,
  title = {Combining classifiers in text categorization},
  booktitle = {Proceedings of SIGIR-96, 19th ACM International Conference on
              Research and Development in Information Retrieval},
  pages = {289--297},
  publisher = {ACM Press, New York, US},
  address = {Z{\"u}rich, CH}
}
@INPROCEEDINGS{Larkey98,
  author = {Leah S. Larkey},
  editor = {W. Bruce Croft and Alistair Moffat and Cornelis J. van Rijsbergen
           and Ross Wilkinson and Justin Zobel},
  year = 1998,
  title = {Automatic essay grading using text categorization techniques},
  booktitle = {Proceedings of SIGIR-98, 21st ACM International Conference on
              Research and Development in Information Retrieval},
  pages = {90--95},
  publisher = {ACM Press, New York, US},
  address = {Melbourne, AU}
}
@INPROCEEDINGS{Larkey99,
  author = {Leah S. Larkey},
  editor = {Edward A. Fox and Neil Rowe},
  year = 1999,
  title = {A patent search and classification system},
  booktitle = {Proceedings of DL-99, 4th ACM Conference on Digital Libraries},
  pages = {179--187},
  publisher = {ACM Press, New York, US},
  address = {Berkeley, US}
}
@PHDTHESIS{Lewis92,
  author = {Lewis, David D.},
  year = 1992,
  title = {Representation and learning in information retrieval},
  address = {Amherst, US},
  school = {Department of Computer Science, University of Massachusetts}
}
@INPROCEEDINGS{Lewis92b,
  author = {Lewis, David D.},
  editor = {Nicholas J. Belkin and Peter Ingwersen and Annelise Mark Pejtersen},
  year = 1992,
  title = {An evaluation of phrasal and clustered representations on a text
          categorization task},
  booktitle = {Proceedings of SIGIR-92, 15th ACM International Conference on
              Research and Development in Information Retrieval},
  pages = {37--50},
  publisher = {ACM Press, New York, US},
  address = {Kobenhavn, DK}
}
@INPROCEEDINGS{Liu01,
  author = {Jimin Liu and Tat-Seng Chua},
  year = 2001,
  title = {Building Semantic Perceptron Net for Topic Spotting},
  booktitle = {Proceedings of 37th Meeting of Association of Computational
              Linguistics {(ACL’2001)}}
}
@INPROCEEDINGS{McCallum98,
  author = {Andrew K. McCallum and Kamal Nigam},
  editor = {Jude W. Shavlik},
  year = 1998,
  title = {Employing {EM} in pool-based active learning for text
          classification},
  booktitle = {Proceedings of ICML-98, 15th International Conference on
              Machine Learning},
  pages = {350--358},
  publisher = {Morgan Kaufmann Publishers, San Francisco, US},
  address = {Madison, US}
}
@INPROCEEDINGS{Mladenic98,
  author = {Dunja Mladeni{\'{c}}},
  editor = {Henri Prade},
  year = 1998,
  title = {Turning {{\sc Yahoo!}}\ into an automatic {W}eb page classifier},
  booktitle = {Proceedings of ECAI-98, 13th European Conference on Artificial
              Intelligence},
  pages = {473--474},
  publisher = {John Wiley and Sons, Chichester, UK},
  address = {Brighton, UK}
}
@INPROCEEDINGS{Mladenic98b,
  author = {Dunja Mladeni{\'{c}} and Marko Grobelnik},
  year = 1998,
  title = {Word sequences as features in text-learning},
  booktitle = {Proceedings of ERK-98, the Seventh Electrotechnical and
              Computer Science Conference},
  pages = {145--148},
  address = {Ljubljana, SL}
}
@PHDTHESIS{Mladenic98c,
  author = {Dunja Mladeni{\'{c}}},
  year = 1998,
  title = {Machine Learning on non-homogeneous, distributed text data},
  address = {Ljubljana, SL},
  school = {J.\ Stefan Institute, University of Ljubljana}
}
@INPROCEEDINGS{Petridis01,
  author = {Vassilios Petridis and Vassilis G. Kaburlasos and Pavlina Fragkou
           and Athanasios Kehagias},
  year = 2001,
  title = {Text Classification Using the $\sigma$-{FLNMAP} Neural Network},
  booktitle = {Proceedings of the 2001 International Joint Conference on
              Neural Networks {(IJCNN’2001)}}
}
@ARTICLE{Porter80,
  author = {Martin F. Porter},
  year = 1980,
  title = {An algorithm for suffix stripping},
  journal = {Program},
  volume = 14,
  number = 3,
  pages = {130--137}
}
@ARTICLE{Riloff94,
  author = {Ellen Riloff and Wendy Lehnert},
  year = 1994,
  title = {Information extraction as a basis for high-precision text
          classification},
  journal = {ACM Transactions on Information Systems},
  volume = 12,
  number = 3,
  pages = {296--333}
}
@INPROCEEDINGS{Riloff95,
  author = {Ellen Riloff},
  editor = {Edward A. Fox and Peter Ingwersen and Raya Fidel},
  year = 1995,
  title = {Little Words Can Make a Big Difference for Text Classification},
  booktitle = {Proceedings of SIGIR-95, 18th ACM International Conference on
              Research and Development in Information Retrieval},
  pages = {130--136},
  publisher = {ACM Press, New York, US},
  address = {Seattle, US}
}
@INPROCEEDINGS{Riloff96,
  author = {Ellen Riloff},
  editor = {Stefan Wermter and Ellen Riloff and Gabriele Scheler},
  year = 1996,
  title = {Using Learned Extraction Patterns for Text Classification},
  booktitle = {Connectionist, statistical, and symbolic approaches to learning
              for natural language processing},
  pages = {275--289},
  note = {Published in the ``Lecture Notes in Computer Science'' series,
         number 1040},
  publisher = {Springer Verlag, Heidelberg, DE}
}
@INPROCEEDINGS{Sahami98,
  author = {Mehran Sahami and Salim Yusufali and Michelle Q. Baldonado},
  editor = {Ian Witten and Rob Akscyn and Frank M. Shipman},
  year = 1998,
  title = {{SONIA}: a service for organizing networked information
          autonomously},
  booktitle = {Proceedings of DL-98, 3rd ACM Conference on Digital Libraries},
  pages = {200--209},
  publisher = {ACM Press, New York, US},
  address = {Pittsburgh, US}
}
@INPROCEEDINGS{Sahami98b,
  author = {Mehran Sahami and Susan Dumais and David Heckerman and Eric
           Horvitz},
  year = 1998,
  title = {A Bayesian Approach to Filtering Junk E-Mail},
  booktitle = {Learning for Text Categorization: Papers from the 1998 Workshop},
  publisher = {AAAI Technical Report WS-98-05},
  address = {Madison, Wisconsin}
}

@BOOK{Salton89,
  author =       {Gerard Salton},
  title =        {Automatic text processing: the transformation, analysis, and retrieval of information by computer},
  publisher =    {Addison Wesley},
  year =         {1989}
}

@MASTERSTHESIS{Scott98,
  author = {Sam Scott},
  year = 1998,
  title = {Feature Engineering for a Symbolic Approach to Text Classification},
  address = {Ottawa, CA},
  school = {Computer Science Department, University of Ottawa}
}
@INPROCEEDINGS{Scott99,
  author = {Sam Scott and Stan Matwin},
  editor = {Ivan Bratko and Saso Dzeroski},
  year = 1999,
  title = {Feature engineering for text classification},
  booktitle = {Proceedings of ICML-99, 16th International Conference on
              Machine Learning},
  pages = {379--388},
  publisher = {Morgan Kaufmann Publishers, San Francisco, US},
  address = {Bled, SL}
}
@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}
}
@INPROCEEDINGS{Segal99,
  author = {R. Segal and J. Kephart},
  year = 1999,
  title = {{MailCat}: An Intelligent Assistant for Organizing E-Mail},
  booktitle = {Proceedings of the Third International Conference on Autonomous
              Agents}
}
@INPROCEEDINGS{Segal00,
  author = {R. Segal and J. Kephart},
  year = 2000,
  title = {Incremental Learning in {SwiftFile}},
  booktitle = {Proceedings of the Seventh International Conference on Machine
              Learning}
}
@INPROCEEDINGS{Sibun96,
  author = {Penelope Sibun and Jeffrey C. Reynar},
  year = 1996,
  title = {Language Identification: Examining the Issues},
  booktitle = {5th Symposium on Document Analysis and Information Retrieval},
  pages = {125--135},
  address = {Las Vegas, Nevada, U.S.A.}
}
@BOOK{SparckJones95,
  author = {Karen {Sparck Jones} and Julia Rose Galliers},
  year = 1995,
  title = {Evaluating Natural Language Processing Systems : An Analysis and
          Review},
  series = {Lecture Notes in Computer Science -- 1083 Lecture Notes in
           Artificial Intelligence},
  publisher = {Springer},
  address = {Berlin}
}
@ARTICLE{Stamatatos00,
  author = {Efstathios Stamatatos and Nikos Fakotakis and George Kokkinakis},
  year = 2000,
  title = {Automatic text categorization in terms of genre and author},
  journal = {Computational Linguistics},
  volume = 26,
  number = 4,
  pages = {471--495}
}
@INPROCEEDINGS{Suzuki01,
  author = {Yoshimi Suzuki and Fumiyo Fukumoto and Yoshihiro Sekiguchi},
  year = 2001,
  title = {Event Tracking Using {WordNet} Meronyms},
  booktitle = {Proceedings of the {NAACL} 2001 Workshop on {WordNet} and Other
              Lexical Resources}
}
@INPROCEEDINGS{Teahan00,
  author = {William J. Teahan},
  year = 2000,
  title = {Text classification and segmentation using minimum cross-entropy},
  booktitle = {Proceeding of RIAO-00, 6th International Conference ``Recherche
              d'Information Assistee par Ordinateur''},
  address = {Paris, FR}
}
@Book{Witten99,
    author =    "Ian H. Witten and Eibe Frank",
    title =     "Data Mining: Practical Machine Learning Tools and
                Techniques with Java Implementations",
    publisher = "Morgan Kaufmann",
    year =      "1999",
}


@INPROCEEDINGS{Yang99,
  author = {Yiming Yang and Xin Liu},
  editor = {Marti A. Hearst and Fredric Gey and Richard Tong},
  year = 1999,
  title = {A re-examination of text categorization methods},
  booktitle = {Proceedings of SIGIR-99, 22nd ACM International Conference on
              Research and Development in Information Retrieval},
  pages = {42--49},
  publisher = {ACM Press, New York, US},
  address = {Berkeley, US}
}
@INPROCEEDINGS{Yang97,
 AUTHOR         = "Y. Yang and J.O. Pedersen",
 TITLE          = "A comparative study on feature selection in text categorization",
 BOOKTITLE      = "Proceedings of ICML-97, 14th International Conference on Machine Learning",
 YEAR           = "1997"
 }
@INPROCEEDINGS{Zelikovitz01,
  author = {Sarah Zelikovitz and Haym Hirsh},
  editor = {Henrique Paques and Ling Liu and David Grossman},
  year = 2001,
  title = {Using {LSI} for Text Classification in the Presence of Background
          Text},
  booktitle = {Proceedings of CIKM-01, 10th ACM International Conference on
              Information and Knowledge Management},
  pages = {113--118},
  publisher = {ACM Press, New York, US},
  address = {Atlanta, US}
}