@PhdThesis{74,
author = {David Lewis},
title = {Representation and Learning in Information Retrieval},
school = {University of Massachusetts},
year = 1992
}
@InProceedings{75,
author = "David D. Lewis and Robert E. Schapire and James P. Callan and Ron Papka",
title = "Training Algorithms for Linear Text Classifiers",
booktitle = "Proceedings of {SIGIR}-96, 19th {ACM} International Conference on Research and Development in Information Retrieval",
publisher = "ACM Press, New York, US",
address = "Z{\"{u}}rich, CH",
editor = "Hans-Peter Frei and Donna Harman and Peter Sch{\"{a}}uble and Ross Wilkinson",
pages = "298--306",
year = 1996,
url = "citeseer.nj.nec.com/lewis96training.html"
}
@InProceedings{76,
author = {Robert E. Schapire and Yoram Singer and Amit Singhal},
title = {Boosting and Rocchio Applied to Text Filtering},
booktitle = {Proceedings of the Twenty First Annual International ACM SIGIR Conference on Research and Development in Information Retrieval},
year = 1998
}
@InProceedings{77,
author = {Raj D. Iyer and David D. Lewis and Robert E. Schapire and Yoram Singerz and Amit Singhal},
title = {Boosting for Document Routing},
booktitle = {Ninth International Conference on Information and Knowledge Management (CIKM) 2000},
year = 2000
}
@Article{78,
author = {Robert E. Shapire and Yoram Singer},
title = {BoosTexter: A Boosting-based System for Text Categorization},
journal = {Machine Learning},
year = 2000,
volume = 39,
number = {2/3},
pages = {135--168}
}
@Article{80,
author = {Abraham Bookstein and Don Kraft},
title = {Operations Research Applied to Document Indexing and Retrieval Decisions},
journal = {Journal of the Association for Computing Machinery},
year = 1977,
volume = 24,
number = 3,
pages = {418--427},
month = {July}
}
@article{92,
author = "David A. Grossman and Ophir Frieder and David O. Holmes and David C. Roberts",
title = "Integrating Structured Data and Text: A Relational Approach",
journal = "Journal of the American Society of Information Science",
volume = 48,
number = 2,
pages = "122--132",
year = 1997,
url = "citeseer.nj.nec.com/article/grossman95integrating.html"
}
@Article{102,
author = {Sholom M. Weiss and Chidanand Apte and Fred J. Damerau and David E. Johnson and Frank J. Oles and Thilo Goetz and Thomas Hampp},
title = {Maximizing Text-Mining Performance},
journal = {IEEE Intelligent Systems},
year = 1999
}
@misc{120,
author = "A. McCallum and K. Nigam",
title = "A comparison of event models for Naive Bayes text classification",
text = "A. McCallum and K. Nigam. A comparison of event models for Naive Bayestext classification. In AAAI-98 Workshop on Learning for Text Categorization, 1998.",
year = "1998",
url = "citeseer.nj.nec.com/mccallum98comparison.html" }
@Article{ nigam00text,
author = "Kamal Nigam and Andrew K. McCallum and Sebastian Thrun and Tom M. Mitchell",
title = "Text Classification from Labeled and Unlabeled Documents using {EM}",
journal = "Machine Learning",
volume = "39",
number = "2/3",
pages = "103--134",
year = "2000",
url = "citeseer.nj.nec.com/nigam99text.html" }
@Book{138,
author = {C.J. van Rijsbergen},
title = {Information Retrieval},
publisher = {Butterworths},
year = 1979
}
@Misc{139,
author = {David D. Lewis and Yoram Singer},
title = {Introduction to Machine Learning for Information Retrieval},
howpublished = {Tutorial presented at 23rd {ACM SIGIR} Conference},
month = {August},
year = 2002
}
@Misc{140,
author = {David D. Lewis and Yoram Singer},
title = {Reference List to Accompany {SIGIR}-97 Tutorial on Machine Learning for Information Retrieval},
howpublished = {Tutorial presented at 23rd {ACM SIGIR} Conference},
month = {August},
year = 2002
}
@misc{141,
author = "D. Lewis",
title = "Active by accident: Relevance feedback in information retrieval",
text = "DD Lewis. Active by accident: Relevance feedback in information retrieval.
In AAAI Fall Symposium on Active Learning, 1995.",
year = 1995,
url = "citeseer.nj.nec.com/lewis95active.html" }
@Article{394,
author = {Michael W. Berry and Zlatko Drmac and Elizabeth R. Jessup},
title = {Matrices, Vector Spaces and Information Retrieval},
journal = {SIAM Review},
year = 1999,
volume = 41,
number = 2,
pages = {335--362}
}
@Misc{466,
author = {G. Holmes and C.G. Nevill-Manning},
title = {Feature Selection Via the Discovery of Simple Classification Rules}
}
@inproceedings{479,
author = "D. D. Lewis",
title = "{Evaluating and Optimizing Autonomous Text Classification Systems}",
booktitle = "Proceedings of the 18th Annual International {ACM} {SIGIR} Conference on Research and Development in Information Retrieval",
publisher = "ACM Press",
address = "Seattle, Washington",
editor = "E. A. Fox and P. Ingwersen and R. Fidel",
pages = "246--254",
year = 1995,
url = "citeseer.nj.nec.com/lewis95evaluating.html" }
@inproceedings{479,
author = "D. D. Lewis",
title = "{Evaluating and Optimizing Autonomous Text Classification Systems}",
booktitle = "Proceedings of the 18th Annual International {ACM} {SIGIR} Conference on Research and Development in Information Retrieval",
publisher = "ACM Press",
address = "Seattle, Washington",
editor = "E. A. Fox and P. Ingwersen and R. Fidel",
pages = "246--254",
year = 1995,
url = "citeseer.nj.nec.com/lewis95evaluating.html" }
@article{485,
author = "Norbert Fuhr",
title = "Probabilistic Models in Information Retrieval",
journal = "The Computer Journal",
volume = 35,
number = 3,
pages = "243--255",
year = 1992,
url = "citeseer.nj.nec.com/fuhr92probabilistic.html"}
@Misc{501,
author = {Ramon Ferrer Cancho and Ricard V. Sole},
title = {Two regimes in the frequency the origins of complex lexicons: {Z}ipf's law revisited}
}
@inproceedings{547,
author = "Eibe Frank and Gordon W. Paynter and Ian H. Witten and Carl Gutwin and Craig G. Nevill-Manning",
title = "Domain-Specific Keyphrase Extraction",
booktitle = "{IJCAI}",
pages = "668--673",
year = "1999",
url = "citeseer.nj.nec.com/frank99domainspecific.html" }
@Misc{553,
author = {S. Muthu Muthukrishnan},
title = {Efficient Algorithms for Document Retrieval Problems}
}
@InProceedings{605,
author = "Amit Singhal and Chris Buckley and Mandar Mitra",
title = "Pivoted Document Length Normalization",
booktitle = "Research and Development in Information Retrieval",
pages = "21--29",
year = 1996,
url = "citeseer.nj.nec.com/singhal96pivoted.html"
}
@Article{606,
author = {S.E. Robertson and K. Sparck Jones},
title = {Relevance Weighting of Search Terms},
journal = {Journal of the American Society for Information Science},
year = 1976,
volume = 27,
number = 3,
pages = {129--146}
}
@inproceedings{618,
author = "Daphne Koller and Mehran Sahami",
title = "Hierarchically classifying documents using very few words",
booktitle = "Proceedings of {ICML}-97, 14th International Conference on Machine Learning",
publisher = "Morgan Kaufmann Publishers, San Francisco, US",
address = "Nashville, US",
editor = "Douglas H. Fisher",
pages = "170--178",
year = "1997",
url = "citeseer.nj.nec.com/koller97hierarchically.html" }
@Article{645,
author = "Scott C. Deerwester and Susan T. Dumais and Thomas K. Landauer and George W. Furnas and Richard A. Harshman",
title = "Indexing by Latent Semantic Analysis",
journal = "Journal of the American Society of Information Science",
volume = 41,
number = 6,
pages = "391--407",
year = 1990,
url = "citeseer.nj.nec.com/deerwester90indexing.html"
}
@techreport{646,
author = "Michael W. Berry and Susan T. Dumais and Gavin W. O'Brien",
title = "Using Linear Algebra for Intelligent Information Retrieval",
number = "UT-CS-94-270",
year = 1994,
url = "citeseer.nj.nec.com/berry95using.html" }
@inproceedings{649,
author = "D. D. Lewis",
title = "{Feature Selection and Feature Extraction for Text Categorization}",
booktitle = "Proceedings of Speech and Natural Language Workshop",
publisher = "Morgan Kaufmann",
address = "San Mateo, California",
pages = "212--217",
year = 1992,
url = "citeseer.nj.nec.com/lewis92feature.html" }
@Article{650,
author = "Soumen Chakrabarti and Byron Dom and Rakesh Agrawal and Prabhakar Raghavan",
title = "Scalable Feature Selection, Classification and Signature Generation for Organizing Large Text Databases into Hierarchical Topic Taxonomies",
journal = "{VLDB} Journal: Very Large Data Bases",
volume = 7,
number = 3,
pages = "163--178",
year = 1998,
url = "citeseer.nj.nec.com/chakrabarti98scalable.html"
}
@Article{652,
author = {William P. Jones and George W. Fumas},
title = {Pictures of Relevance: A Geometric Analysis of Similarity Measures},
journal = {Journal of the American Society for Information Science},
year = 1987,
volume = 38,
number = 6,
pages = {420--442},
month = {November}
}
@Article{653,
author = {Nicholas J. Belkin and W. Bruce Croft},
title = {Information Filtering and Information Retrieval: Two Sides of the Same Coin?},
journal = {Communications of the {ACM}},
volume = 35,
number = 12,
year = 1992,
issn = {0001-0782},
pages = {29--38},
doi = {http://doi.acm.org/10.1145/138859.138861},
publisher = {ACM Press},
}
@Article{654,
author = {K. Sparck Jones and S. Walker and S. E. Robertson},
title = {A Probabilistic Model of Information Retrieval: Development and Comparative Experiments; Part 1},
journal = {Information Processing and Management},
year = 2000,
volume = 36,
number = 6,
pages = {779--808},
month = {November}
}
@Article{655,
author = {K. Sparck Jones and S. Walker and S. E. Robertson},
title = {A Probabilistic Model of Information Retrieval: Development and Comparative Experiments; Part 1},
journal = {Information Processing and Management},
year = 2000,
volume = 36,
number = 6,
pages = {779--808},
month = {November}
}
@Article{656,
author = {S. E. Robertson and S. Walker and M. Beaulieu},
title = {Experimentation as a Way of Life: Okapi at {TREC}},
journal = {Information Processing and Management},
year = 2000,
volume = 36,
number = 1,
pages = {95--108}
}
@Article{657,
author = {Ellen M. Voorhees},
title = {Variations in Relevance Judgments and the Measurement of Retrieval Effectiveness},
journal = {Information Processing and Management},
year = 2000,
volume = 36,
number = 5,
pages = {697--716},
month = {September}
}
@Article{658,
author = {Norbert Fuhr},
title = {Models for Retrieval with Probabilistic Indexing},
journal = {Information Processing and Management},
year = 1989,
volume = 25,
number = 1,
pages = {55--72}
}
@Article{660,
author = {Pauline V. Angione},
title = {On the Equivalence of Boolean and Weighted Searching Based on the Convertibility of Query Forms},
journal = {Journal of the American Society for Information Science},
year = 1975,
pages = {112--124},
month = {March--April}
}
@Article{661,
author = {Paul Travis Nicholls},
title = {Estimation of {Z}ipf Parameters},
journal = {Journal of the American Society of Infomation Science},
year = 1987,
volume = 38,
number = 6,
pages = {443--445}
}
@InProceedings{665,
author = {Jay M. Ponte and W. Bruce Croft},
title = {A Language Modeling Approach to Information Retrieval},
booktitle = {Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval},
year = 1998,
isbn = {1-58113-015-5},
pages = {275--281},
location = {Melbourne, Australia},
doi = {http://doi.acm.org/10.1145/290941.291008},
publisher = {{ACM} Press},
}
@InProceedings{666,
author = {John Lafferty and Chengxiang Zhai},
title = {Document language models, query models, and risk minimization for information retrieval},
booktitle = {Proceedings of the 24th annual international ACM SIGIR conference on Research and development in information retrieval},
year = 2001,
isbn = {1-58113-331-6},
pages = {111--119},
location = {New Orleans, Louisiana, United States},
doi = {http://doi.acm.org/10.1145/383952.383970},
publisher = {ACM Press},
}
@InProceedings{667,
author = {ChengXiang Zhai and John Lafferty},
title = {Two-stage Language Models for Information Retrieval},
booktitle = {Proceedings of the 25th Annual International {ACM SIGIR} Conference on Research and Development in Information Retrieval},
year = 2002,
isbn = {1-58113-561-0},
pages = {49--56},
location = {Tampere, Finland},
doi = {http://doi.acm.org/10.1145/564376.564387},
publisher = {ACM Press},
}
@inproceedings{668,
author = {Chengxiang Zhai and John Lafferty},
title = {Model-Based Feedback in the Language Modeling Approach to Information Retrieval},
booktitle = {Proceedings of the Tenth International Conference on Information and Knowledge Management},
year = {2001},
isbn = {1-58113-436-3},
pages = {403--410},
location = {Atlanta, Georgia, {USA}},
doi = {http://doi.acm.org/10.1145/502585.502654},
publisher = {{ACM} Press},
}
@InProceedings{669,
author = {Fei Song and W. Bruce Croft},
title = {A General Language Model for Information Retrieval},
booktitle = {Proceedings of the Eighth International Conference on Information and Knowledge Management},
year = {1999},
isbn = {1-58113-146-1},
pages = {316--321},
location = {Kansas City, Missouri, United States},
doi = {http://doi.acm.org/10.1145/319950.320022},
publisher = {{ACM} Press},
}
@InProceedings{670,
author = {Rong Jin and Alex G. Hauptmann and Cheng Xiang Zhai},
title = {Title Language Model for Information Retrieval},
booktitle = {Proceedings of the 25th Annual International {ACM SIGIR} Conference on Research and Development in Information Retrieval},
year = 2002,
isbn = {1-58113-561-0},
pages = {42--48},
location = {Tampere, Finland},
doi = {http://doi.acm.org/10.1145/564376.564386},
publisher = {ACM Press},
}
@inproceedings{671,
author = {Adam Berger and John Lafferty},
title = {Information Retrieval as Statistical Translation},
booktitle = {Proceedings of the 22nd Annual International {ACM SIGIR} Conference on Research and Development in Information Retrieval},
year = 1999,
isbn = {1-58113-096-1},
pages = {222--229},
location = {Berkeley, California, United States},
doi = {http://doi.acm.org/10.1145/312624.312681},
publisher = {{ACM} Press},
}
@Article{673,
author = {Abraham Bookstein and Vladimir A. Kulyukin and Timo Raita},
title = {Generalized Hamming Distance},
journal = {Information Retrieval},
year = 2002,
volume = 5,
number = 4,
pages = {353--375},
month = {October}
}
@inproceedings{674,
author = {Abraham Bookstein},
title = {Implications of Boolean Structure for Probabilistic Retrieval},
booktitle = {Proceedings of the 8th Annual International {ACM SIGIR} Conference on Research and Development in Information Retrieval},
year = 1985,
isbn = {0-89791-159-8},
pages = {11--17},
location = {Montreal, Quebec, Canada},
doi = {http://doi.acm.org/10.1145/253495.253505},
publisher = {{ACM} Press},
}
@inproceedings{675,
author = {Joon Ho Lee},
title = {Properties of Extended Boolean Models in Information Retrieval},
booktitle = {Proceedings of the 17th Annual International {ACM SIGIR} Conference on Research and Development in Information Retrieval},
year = 1994,
isbn = {0-387-19889-X},
pages = {182--190},
location = {Dublin, Ireland},
publisher = {Springer-Verlag New York, Inc.},
}
@InProceedings{676,
author = {Joon Ho Lee and Won Yong Kin and Myoung Ho Kim and Yoon Joon Lee},
title = {On the Evaluation of Boolean Operators in the Extended Boolean Retrieval Framework},
booktitle = {Proceedings of the 16th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval},
year = 1993,
isbn = {0-89791-605-0},
pages = {291--297},
location = {Pittsburgh, Pennsylvania, United States},
doi = {http://doi.acm.org/10.1145/160688.160741},
publisher = {{ACM} Press},
}
@Article{677,
author = {W. G. Waller and Donald H. Kraft},
title = {A Mathematical Model of a Weighted Boolean Retrieval System},
journal = {Information Processing and Management},
year = 1979,
volume = 15,
number = 5,
pages = {219--267}
}
@Article{678,
author = "Abraham Bookstein and Shmuel T. Klein and Timo Raita",
title = "Clumping Properties of Content-Bearing Words",
journal = "Journal of the American Society of Information Science",
volume = 49,
number = 2,
pages = "102--114",
year = 1998,
url = "citeseer.nj.nec.com/bookstein98clumping.html"
}
@Misc{679,
author = {William E. Winkler},
title = {Machine Learning, Information Retrieval, and Record Linkage}
}
@InProceedings{680,
author = {A. Bookstein},
title = {Set Oriented Retrieval},
booktitle = {Proceedings of the 11th Annual International {ACM SIGIR} Conference on Research and Development in Information Retrieval},
year = 1988,
isbn = {2-7061-0309-4},
pages = {583--596},
location = {Grenoble, France},
doi = {http://doi.acm.org/10.1145/62437.62499},
publisher = {{ACM} Press}
}
@InProceedings{681,
author = {R. Manmatha and T. Rath and F. Feng},
title = {Modeling Score Distributions for Combining the Outputs of Search Engines},
booktitle = {Proceedings of the 24th Annual International {ACM SIGIR} Conference on Research and Development in Information Retrieval},
year = 2001,
isbn = {1-58113-331-6},
pages = {267--275},
location = {New Orleans, Louisiana, United States},
doi = {http://doi.acm.org/10.1145/383952.384005},
publisher = {ACM Press},
}
@Article{682,
author = {John A. Swets},
title = {Information Retrieval Systems},
journal = {Science},
year = 1963,
volume = 141,
number = 3577,
pages = {245--250},
month = {July}
}
@Article{683,
author = {Ivan P. Fellegi and Alan B. Sunter},
title = {A Theory for Record Linkage},
journal = {Journal of the American Statistical Association},
year = 1969,
volume = 64,
number = 328,
pages = {1183--1210},
month = {December}
}
@Article{684,
author = {Gerard Salton and Edward A. Fox and Harry Wu},
title = {Extended Boolean Information Retrieval},
journal = {Communications of the {ACM}},
year = 1983,
volume = 26,
number = 12,
month = {December}
}
@Article{685,
author = {Robert M. Losee},
title = {When Information Retrieval Measures Agree about the Relative Quality of Document Rankings},
journal = {Journal of the American Society for Information Science},
year = 2000,
volume = 51,
number = 9,
pages = {834--840}
}
@InProceedings{686,
author = "Daphne Koller and Mehran Sahami",
title = "Toward Optimal Feature Selection",
booktitle = "International Conference on Machine Learning",
pages = "284--292",
year = 1996,
url = "citeseer.nj.nec.com/koller96toward.html"
}
@Misc{689,
author = "M. Keim and D. Lewis and D. Madigan",
title = "Bayesian Information Retrieval: Preliminary Evaluation",
text = "KEIM, M., LEWIS, D. D., AND MADIGAN, D. Bayesian information retrieval:
Preliminary evaluation. In Preliminary Papers of the Sixth International
Workshop on Artificial Intelligence and Statistics (Ft. Lauderdale, Florida,
Jan. 1997), D. Madigan and P. Smyth, Eds., pp. 303--310.",
year = 1997,
url = "citeseer.nj.nec.com/keim97bayesian.html"
}
@InProceedings{690,
author = "David D. Lewis",
title = "Naive ({B}ayes) at Forty: The Independence Assumption in Information Retrieval.",
booktitle = "Proceedings of {ECML}-98, 10th European Conference on Machine Learning",
number = 1398,
publisher = "Springer Verlag, Heidelberg, DE",
address = "Chemnitz, DE",
editor = "Claire N{\'{e}}dellec and C{\'{e}}line Rouveirol",
pages = "4--15",
year = 1998,
url = "citeseer.nj.nec.com/lewis98naive.html"
}
@InProceedings{691,
author = "Yiming Yang and Jan O. Pedersen",
title = "A Comparative Study on Feature Selection in Text Categorization",
booktitle = "Proceedings of {ICML}-97, 14th International Conference on Machine Learning",
publisher = "Morgan Kaufmann Publishers, San Francisco, US",
address = "Nashville, US",
editor = "Douglas H. Fisher",
pages = "412--420",
year = 1997,
url = "citeseer.nj.nec.com/yang97comparative.html"
}
@Article{692,
author = {Duncan A. Buell and Donald H. Kraft},
title = {Threshold Values and Boolean Retrieval Systems},
journal = {Information Processing and Manangement},
year = 1981,
volume = 17,
pages = {127--136}
}
@Article{693,
author = {Abraham Bookstein and William Cooper},
title = {A General Mathematical Model for Information Retrieval Systems},
journal = {Library Quarterly},
year = 1976,
volume = 46,
number = 2,
pages = {153--167}
}
@Article{694,
author = {W.G. Waller and Donald H. Kraft},
title = {A Mathematical Model of a Weighted Boolean Retrieval System},
journal = {Information Processing and Management},
year = 1979,
volume = 15,
number = 5,
pages = {235--245}
}
@Misc{696,
author = {Warren R. Greiff and W. Bruce Croft},
title = {Computational Tractable Probabilistic Modeling of Boolean Operators}
}
@InProceedings{697,
author = "Yiming Yang",
title = "A Study on Thresholding Strategies for Text Categorization",
booktitle = "Proceedings of {SIGIR}-01, 24th {ACM} International Conference on Research and Development in Information Retrieval",
publisher = "ACM Press, New York, US",
address = "New Orleans, US",
editor = "W. Bruce Croft and David J. Harper and Donald H. Kraft and Justin Zobel",
pages = "137--145",
year = 2001,
url = "citeseer.nj.nec.com/yang01study.html"
}
@Book{698,
editor = {Luis Gravano},
title = {Special Issue on Text and Databases},
publisher = {{IEEE} Computer Society},
year = 2001,
volume = 24,
number = 4,
series = {Bulletin of the Technical Committee on Data Engineering},
month = {December}
}
@Article{699,
author = {Gerard Salton and Christopher Buckley},
title = {Term-Weighting Approaches in Automatic Text Retrieval},
journal = {Information Processing and Management},
year = 1988,
volume = 24,
number = 5,
pages = {513--523}
}
@InProceedings{701,
author = "David D. Lewis and William A. Gale",
title = "A Sequential Algorithm for Training Text Classifiers",
booktitle = "Proceedings of {SIGIR}-94, 17th {ACM} International Conference on Research and Development in Information Retrieval",
publisher = "Springer Verlag, Heidelberg, DE",
address = "Dublin, IE",
editor = "W. Bruce Croft and Cornelis J. van Rijsbergen",
pages = "3--12",
year = 1994,
url = "citeseer.nj.nec.com/lewis94sequential.html"
}
@InProceedings{702,
author = {David D. Lewis},
title = {A Sequential Algorithm for Training Text Classifiers: Corrigendum and Additional Data},
booktitle = {{SIGIR} Forum},
pages = {13--19},
year = 1995,
volume = 29,
number = 2
}
@InProceedings{703,
author = "David D. Lewis and W. Bruce Croft",
title = "Term Clustering of Syntactic Phrases",
booktitle = "Proc. of the Thirteenth Annual International {ACM SIGIR} Conference on Research and Development in Information Retrieval",
pages = "385--404",
year = 1990,
url = "citeseer.nj.nec.com/lewis90term.html"
}
@Article{704,
author = {C.J. van Rijsbergen},
title = {A Theoretical Basis for Use of Co-occurrence Data in Information Retrieval},
journal = {Journal of Documentation},
year = 1977,
volume = 33,
number = 2,
pages = {106--119}
}
@Article{705,
author = {Robert M. Losee and Abraham Bookstein},
title = {Integrating Boolean Queries in Conjunctive Normal Form with Probabilistic Retrieval Models},
journal = {Information Processing and Management},
year = 1988,
volume = 24,
number = 3,
pages = {315--321}
}
@Article{706,
author = {William S. Cooper},
title = {Getting Beyond Boole},
journal = {Information Processing and Management},
year = 1988,
volume = 24,
number = 3,
pages = {243--248}
}
@Article{707,
author = {Gerard Salton and Chris Buckley},
title = {Improving Retrieval Performance by Relevance Feedback},
journal = {Journal of the American Society for Information Science},
year = 1990,
volume = 41,
number = 4,
pages = {288--297}
}
@InProceedings{708,
author = {David D. Lewis},
title = {Learning in Intelligent Information Retrieval},
booktitle = {Machine Learning: Proceedings of the Eighth International Workshop ({ML}91)},
pages = {235--239},
year = 1991
}
@Article{710,
author = {Tadeusz Radecki},
title = {Trends in Research on Information Retrieval -- The Potential for Improvements in Conventional Boolean Retrieval Systems},
journal = {Information Processing and Mangement},
year = 1988,
volume = 24,
number = 3,
pages = {219--227}
}
@Article{711,
author = "Jon M. Kleinberg",
title = "Authoritative Sources in a Hyperlinked Environment",
journal = "Journal of the {ACM}",
volume = 46,
number = 5,
pages = "604--632",
year = 1999,
url = "citeseer.nj.nec.com/kleinberg97authoritative.html"
}
@Misc{713,
author = {Dunja Mladeni\'c},
title = {Feature Subset Selection in Text-Learning}
}
@InProceedings{714,
author = "Brian T. Bartell and Garrison W. Cottrell and Richard K. Belew",
title = "Latent Semantic Indexing is an Optimal Special Case of Multidimensional Scaling",
booktitle = "Research and Development in Information Retrieval",
pages = "161--167",
year = 1992,
url = "citeseer.nj.nec.com/bartell92latent.html" }
@InProceedings{716,
author = {Michael Berry and Jack Dongarra},
title = {Atlanta Organizers Put Mathematics to Work For the Math Sciences Community},
booktitle = {{SIAM} News},
year = 1999,
volume = 32,
number = 6,
month = {July/August}
}
@Article{717,
author = {I.A.R. Moghrabi and R.A. Makholian},
title = {A New Approach to Clustering Records in Information Retrieval Systems},
journal = {Information Retrieval},
year = 2000,
volume = 3,
number = 2,
pages = {105--126}
}
@inproceedings{718,
author = "Marti A. Hearst and Jan O. Pedersen",
title = "Reexamining the Cluster Hypothesis: Scatter/Gather on Retrieval Results",
booktitle = "Proceedings of {SIGIR}-96, 19th {ACM} International Conference on Research and Development in Information Retrieval",
address = "Z{\"{u}}rich, CH",
pages = "76--84",
year = 1996,
url = "citeseer.nj.nec.com/hearst96reexamining.html"
}
@TechReport{719,
author = "S. M. R{\"u}ger and S. E. Gauch",
title = "Feature Reduction for Document Clustering and Classification",
institution = "Computing Department, Imperial College",
address = "London, UK",
year = 2000,
url = "citeseer.nj.nec.com/uger00feature.html"
}
@InProceedings{720,
author = {Ellen M. Voorhees},
title = {The Cluster Hypothesis Revisited},
booktitle = {Proceedings of the 8th Annual International {ACM SIGIR} Conference on Research and Development in Information Retrieval},
year = 1985,
isbn = {0-89791-159-8},
pages = {188--196},
location = {Montreal, Quebec, Canada},
doi = {http://doi.acm.org/10.1145/253495.253524},
publisher = {{ACM} Press},
}
@InBook{721,
editor = {Gerard Salton},
title = {The {SMART} Retrieval System: Experiments in Automatic Document Processing},
chapter = {Cluster Search Strategies and the Optimization of Retrieval Effectiveness},
publisher = {Prentice Hall},
year = 1971
}
@Article{722,
author = {Peter Willett},
title = {Recent Rrends in Hierarchic Document Clustering: A Critical Review},
journal = {Information Processing and Management},
year = 1988,
volume = 24,
number = 5,
pages = {577--597}
}
@Article{732,
author = {N. Jardine and C.J. van Rijsbergen},
title = {The Use of Hierarchic Clustering in Information Retrieval},
journal = {Information Storage and Retrieval},
year = 1971,
volume = 7,
pages = {217--240}
}
@InBook{724,
editor = {Gerard Salton},
title = {The SMART Retrieval System},
chapter = {Relevance Assessments and Retrieval System Evaluation},
publisher = {Prentice-Hall},
year = 1971,
pages = {506--527}
}
@Article{725,
author = {Marc Damashek},
title = {Gauging Similarity with n-Grams: Language-Independent Categorization of Text},
journal = {Science},
year = 1995,
volume = 267,
pages = {843--848},
month = {February}
}
@Article{726,
author = {Elizabeth D. Liddy and Woojin Paik and Edmund S. Yu},
title = {Text Categorization for Multiple Users Based on Semantic Features from a Machine-Readable Dictionary},
journal = {{ACM} Transactions on Information Systems},
year = 1994,
volume = 12,
number = 3,
pages = {278--295},
month = {July}
}
@Article{727,
author = {Jung Jin Lee and Paul B. Kantor},
title = {A Study of Probabilistic Information Retrieval Systems in the Case of Inconsistent Expert Judgments},
journal = {Journal of the American Society for Information Science},
year = 1991,
volume = 42,
number = 3,
pages = {166--172}
}
@Article{728,
author = {N.J. Belkin and P. Kantor and E.A. Fox and J.A. Shaw},
title = {Combining the Evidence of Multiple Query Representations for Information Retrieval},
journal = {Information Processing and Management},
year = 1995,
volume = 31,
number = 3,
pages = {431--448}
}
@InCollection{729,
author = {Paul B. Kantor},
title = {Information Retrieval Techniques},
booktitle = {Annual Review of Information Science and Technology},
pages = {53--90},
publisher = {American Society for Information Science},
year = 1994,
editor = {Martha E. Williams},
volume = 29
}
@Article{730,
author = {Elke Mittendorf and Bojidar Mateev and Peter Schauable},
title = {Using the Co-occurence of Words for Retrieval Weighting},
journal = {Information Retrieval},
year = 2000,
volume = 3,
number = 3,
pages = {243--251},
month = {October}
}
@Article{731,
author = {W.B. Croft and D.J. Harper},
title = {Using Probabilistic Models of Document Retrieval Without Relevance Information},
journal = {Journal of Documentation},
year = 1979,
volume = 35,
number = 4,
pages = {285--295}
}
@inproceedings{732,
author = {S. E. Robertson and S. Walker},
title = {Some Simple Effective Approximations to the 2-Poisson Model for Probabilistic Weighted Retrieval},
booktitle = {Proceedings of the 17th Annual International {ACM SIGIR} Conference on Research and Development in Information Retrieval},
year = 1994,
isbn = {0-387-19889-X},
pages = {232--241},
location = {Dublin, Ireland},
publisher = {Springer-Verlag New York, Inc.},
}
@Article{733,
author = {Abraham Bookstein},
title = {When the Most "Pertinent" Document Should Not Be Retrieved - An Analysis of the {S}wets Model},
journal = {Information Processing and Management},
year = 1977,
volume = 13,
pages = {377--383}
}
@Article{741,
author = {G. Salton and A. Wong and C. S. Yang},
title = {A Vector Space Model for Automatic Indexing},
journal = {Communications of the ACM},
volume = 18,
number = 11,
year = 1975,
issn = {0001-0782},
pages = {613--620},
doi = {http://doi.acm.org/10.1145/361219.361220},
publisher = {ACM Press},
}
@Article{743,
author = {G. Salton and E.A. Fox and E. Voorhees},
title = {Advanced Feedback Methods in Information Retrieval},
journal = {Journal of the American Society for Information Science},
year = 1985,
volume = 36,
number = 3,
pages = {200--210}
}
@Article{744,
author = {C.J. van Rijsbergen and D.J. Harper and M.F. Porter},
title = {The Selection of Good Search Terms},
journal = {Information Processing and Management},
year = 1981,
volume = 17,
pages = {77-91}
}
@Article{745,
author = {B.C. Brookes},
title = {The Measures of Information Retrieval Effectiveness Proposed by Swets},
journal = {Information Processing and Mangement},
year = 1968,
volume = 24,
number = 1,
pages = {41--54}
}
@Article{746,
author = {G. Salton and E. Voorhees and E.A. Fox},
title = {A Comparison of Two Methods for Boolean Query Relevancy Feedback},
journal = {Information Processing and Mangement},
year = 1984,
volume = 20,
number = {5/6},
pages = {637--651}
}
@Article{747,
author = {Tadeusz Radecki},
title = {Probabilistic Methods for Ranking Output Documents in Conventional Boolean Retrieval Systems},
journal = {Information Processing and Management},
year = 1988,
volume = 24,
number = 3,
pages = {281--302}
}
@Article{748,
author = {Paul B. Kantor},
title = {The Logic of Weighted Queries},
journal = {IEEE Transactions on Systems, Man and Cybernetics},
year = 1981,
volume = 11,
number = 12,
pages = {816--821}
}
@InBook{749,
author = {Rocchio, Jr., J.J.},
editor = {Gerard Salton},
title = {The SMART Retrieval System: Experiments in Automatic Document Processing},
chapter = {Relevance Feedback in Information Retrieval},
publisher = {Prentice-Hall},
year = 1971,
pages = {313--323}
}
@Article{750,
author = {Zhixiang Chen and Binhai Zhu},
title = {Some Formal Analysis of Rocchio's Similarity-Based Relevance Feedback Algorithm},
journal = {Information Retrieval},
year = 2002,
volume = 5,
number = 1,
pages = {61--86}
}
@TechReport{756,
author = {S.E. Robertson and K. Spark Jones},
title = {Simple Proven Approaches to Text Retrieval},
institution = {Cambridge University Computer Laboratory},
year = 1997,
number = {TR356},
annote = {Tech. Rep. TR356}
}
@InProceedings{757,
author = "Warren R. Greiff",
title = "A Theory of Term Weighting Based on Exploratory Data Analysis",
booktitle = "Research and Development in Information Retrieval",
pages = "11-19",
year = 1998
}
@InProceedings{758,
author = {Harry Wu and Gerard Salton},
title = {A Comparison of Search Term Weighting: Term Relevance vs. Inverse Document Frequency},
booktitle = {Proceedings of the 4th annual international ACM SIGIR conference on Information storage and retrieval},
year = 1981,
isbn = {0-89791-052-4},
pages = {30--39},
location = {Oakland, California},
doi = {http://doi.acm.org/10.1145/511754.511759},
publisher = {ACM Press},
}
@InProceedings{759,
author = {S. E. Robertson and S. Walker},
title = {On Relevance Weights with Little Relevance Information},
booktitle = {Proceedings of the 20th annual international ACM SIGIR conference on Research and development in information retrieval},
year = 1997,
isbn = {0-89791-836-3},
pages = {16--24},
location = {Philadelphia, Pennsylvania, United States},
doi = {http://doi.acm.org/10.1145/258525.258529},
publisher = {ACM Press},
}
@Article{788,
author = {W.J. Thompson},
title = {Poisson Distributions},
journal = {Computing in Science and Engineering},
year = 2001,
volume = 3,
number = 3,
pages = {78--82},
month = {May-June},
note = {see also IEEE Computational Science and Engineering}
}
@Article{789,
author = {W.J. Thompson},
title = {Don't Subtract the Background},
journal = {Computing in Science and Engineering},
year = 1999,
volume = 1,
number = 5,
pages = {84--88},
month = {September-October},
note = {see also IEEE Computational Science and Engineering, signal count analysis method}
}
@Article{793,
author = {D. E. Johnson, F. J. Oles, T. Zhang, T. Goetz},
title = {A Decision-Tree Based Symbolic Rule Induction System for Text Categorization},
journal = {IBM Systems Journal},
year = 2002,
volume = 41,
number = 3,
pages = {428-436}
}