@InProceedings{ardo99:_online99,
  AUTHOR= "A. Ardö and T. Koch",
  TITLE= "Automatic classification applied to the full-text {I}nternet documents in a robot-generated subject index",
  YEAR=1999,
  month = dec,
  pages = "239-246",
  booktitle = "Online Information 99, Proceedings",
  ISBN = {1-900871-44-0},
  note = "\htmladdnormallink{http://www.it.lth.se/anders/online99/}{http://www.it.lth.se/anders/online99/}"
}

@Misc{tidy,
 title = {{HTML} {T}idy {L}ibrary {P}roject},
 note =  "\htmladdnormallink{http://tidy.sourceforge.net/}{http://tidy.sourceforge.net/}"
}

@Misc{oai,
 title = {{The Open Archives Initiative Protocol for Metadata Harvesting}},
 note =  "\htmladdnormallink{http://www.openarchives.org/OAI/openarchivesprotocol.html}{http://www.openarchives.org/OAI/openarchivesprotocol.html}"
}

@Misc{hiitmpca,
 title = {Discrete {C}omponents {A}nalysis},
 note =  "\htmladdnormallink{http://www.componentanalysis.org/}{http://www.componentanalysis.org/}"
}

@Misc{robotexclusion,
 title = {Robots {E}xclusion {P}rotocol},
 note =  "\htmladdnormallink{http://www.robotstxt.org/wc/exclusion.html}{http://www.robotstxt.org/wc/exclusion.html}"
}

@TechReport{a32,
  author = {S. Lundberg and A. Ardö and A. Brümmer and T. Koch},
  title = {The {European Web Index}: An {Internet} Search Service for the {European} Higher Education, Research and Development Communities.},
  year = 1996,
  institution = {NetLab, Lund University Library},
  note = {Paper prepared to meet the requirements of Work Package 3 of EU Telematics for Research, project DESIRE. \htmladdnormallink{http://www.lub.lu.se/desire/radar/reports/D3.12}{http://www.lub.lu.se/desire/radar/reports/D3.12}},
  month = Aug
}

@InProceedings{a37,
  author = { A. Ardö and S. Lundberg},
  title = {A regional distributed {WWW} search and indexing service - the {DESIRE} way.},
  year = 1998,
  number = {1-7},
  volume = 30,
  pages = {173-183},
  note = {\htmladdnormallink{http://www.it.lth.se/anders/WWW7/}{http://www.it.lth.se/anders/WWW7/}},
  booktitle = {Proceedings of the Seventh International World Wide Web Conference},
  series = {Computer Networks and ISDN Systems},
  month = Apr
}


@InProceedings{Buntine2005,
 Author = "W.Buntine",
 Title = "{Open {S}ource {S}earch: {A} {D}ata {M}ining {P}latform}",
 Note = "To appear",
 booktitle = "SIGIR Forum",
 Year = 2005
}

@InProceedings{Aberer:2004,
 Author ="K. Aberer and F. Klemm and M. Rajman and Jie Wu",
 Title = "{An {A}rchitecture for {P2P} {I}nformation {R}etrieval}",
 booktitle = "27th Annual International ACM SIGIR Conference (SIGIR 2004), Workshop on Peer-to-Peer Information Retrieval, Sheffield, UK",
 Month = jul,
 Year = 2004
}

@misc{ALVIS,
  Title = "{{ALVIS} -{S}uperpeer {S}emantic {S}earch {E}ngine}",
  Note = "http://www.alvis.info/"
}

@misc{alvisarch,
  Title ="{ALVIS} architecture",
  Note = "http://www.alvis.info/alvis/architecture"
}

@misc{alvisxml,
  Author = {Kimmo Valtonen and Antti Tuominen and Wray Buntine},
  Title ="The {ALVIS} {D}ocument {A}rchitecture",
  Note = "\linebreak http://project.alvis.info/alvis\_docs/ALVIS\_X8\_20050130\_HUT\_KV.pdf"
}

@misc{Knowlib,
  Title ="Knowledge {D}iscovery and {D}igital {L}ibrary {R}esearch {G}roup",
  Note = "http://www.it.lth.se/knowlib/"
}

@misc{Combine,
  Title = "{Combine {W}eb crawler}",
  author = {A. Ard\"{o}},
  year = 2005,
  Note = "Software package for general and focused Web-crawling. http://combine.it.lth.se/"
}

@article{chakrabarti99focused,
    author = "Soumen Chakrabarti and Martin van den Berg and Byron Dom",
    title = "Focused crawling: a new approach to topic-specific {Web} resource discovery",
    journal = "Computer Networks (Amsterdam, Netherlands: 1999)",
    volume = "31",
    number = "11--16",
    pages = "1623--1640",
    year = "1999"
}

@article{larsson92,
   author = "Larson, R.R.",
   year = "1992",
   title = "Experiments in automatic {L}ibrary of {C}ongress classification",
   journal = "JASIS",
   volume = "43",
   number = "2",
   pages = "130--148"
}

@article{Golub_Review,
   author = "Koraljka Golub",
   title = "Automated subject classification of textual {Web} documents",
   journal = "Journal of Documentation",
   volume = "62",
   number = "3",
   year = 2006,
   pages = "350--371"
}

@inProceedings{pant04crawling,
  author    = {Gautam Pant and
               Padmini Srinivasan and
               Filippo Menczer},
  title     = {Crawling the Web.},
  year      = {2004},
  pages     = {153-178},
  editor    = {Mark Levene and
               Alexandra Poulovassilis},
  booktitle     = {Web Dynamics - Adapting to Change in Content, Size, Topology
               and Use},
  publisher = {Springer},
  isbn      = {3-540-40676-X}
}

@InProceedings{ardo05:_ECDL,
  author = {K. Golub and A. Ardö},
  year = 2005,
  month = sep,
  title = "{Importance of {HTML} {S}tructural {E}lements in {A}utomated {S}ubject {C}lassification}",
  pages = { 368 - 378 },
  series = {Lecture Notes in Computer Science},
  volume = 3652,
  publisher = {Springer},
  editor =       {Andreas Rauber and Stavros Christodoulakis and A Min Tjoa},
  booktitle =    {9th European Conference on Research and Advanced Technology for Digital Libraries
 - ECDL 2005},
  isbn =         {3-540-28767-1},
  note = { Manuscript at: \htmladdnormallink{http://www.it.lth.se/knowlib/publ/ECDL2005.pdf}{http://www.it.lth.se/knowlib/publ/ECDL2005.pdf}}
}

@Misc{MeSH,
  title = {{Medical Subject Headings, MeSH}},
  note = {\htmladdnormallink{http://www.nlm.nih.gov/mesh/meshhome.html}{http://www.nlm.nih.gov/mesh/meshhome.html}}
}

@Misc{ei,
  title = {{Engineering Information Inc}},
  note = {\htmladdnormallink{http://www.ei.org/}{http://www.ei.org/}}
}

@Misc{heritrix,
  title = {{Heritrix}},
  note = {\htmladdnormallink{http://crawler.archive.org/}{http://crawler.archive.org/}}
}

@Misc{wire,
  title = {{WIRE}},
  note = {\htmladdnormallink{http://www.cwr.cl/projects/WIRE/}{http://www.cwr.cl/projects/WIRE/}}
}

@Misc{nalanda,
  title = {{Nalanda iVia Focused Crawler}},
  note = {\htmladdnormallink{http://ivia.ucr.edu/projects/Nalanda/}{http://ivia.ucr.edu/projects/Nalanda/}}
}

@Misc{CombineDoc,
  title = {{Detailed documentation for the Combine system}},
  note = {\htmladdnormallink{http://combine.it.lth.se/documentation/}{http://combine.it.lth.se/documentation/}}
}

@InProceedings{ardo06:_ECDL,
  author = {K. Golub and A. Ardö and D. Mladenic and M. Grobelnik},
  year = 2006,
  month = sep,
  title = "{Comparing and Combining Two Approaches to Automated Subject Classification of Text}",
  pages = { 467--470 },
  series = {Lecture Notes in Computer Science},
  volume = 4172,
  publisher = {Springer},
  editor = {Julio Gonzalo and Constantino Thanos and M. Felisa Verdejo and Rafael C. Carrasco},
  booktitle =    {10th European Conference on Research and Advanced Technology for Digital Libraries
 - ECDL 2006},
  isbn =         {3-540-44636-2}
}

@article{GolubChall,
    author = "Koraljka Golub",
    title = "Automated subject classification of textual Web pages, based on a controlled vocabulary: challenges and recommendations",
    journal = "New review of hypermedia and multimedia",
    volume = "12",
    number = "1",
    month = jun,
    pages = "11-27",
    year = "2006",
    note = "Special issue on knowledge organization systems and services"
}

@InProceedings{GolubRole,
    author = "Koraljka Golub",
    title = "The Role of Different Thesauri Terms in Automated Subject Classification of Text",
    booktitle = "IEEE/WIC/ACM International Conference on Web Intelligence",
    month = dec,
    year = "2006"
}

@article{Lewis_etal_04,
    author = "D. D. Lewis and Y. Yang and T. Rose and F. Li",
    title = "RCV1: A new benchmark collection for text categorization research",
    journal = "The Journal of Machine Learning Research",
    volume = "",
    number = "5",
    pages = "361--397",
    year = "2004"
}

@article{Yang_99,
    author = "Y. Yang",
    title = "An evaluation of statistical approaches to text categorization",
    journal = "Journal of Information Retrieval",
    volume = "",
    number = "1",
    pages = "67--88",
    year = "1999"
}
%Y. Yang, An evaluation of statistical approaches to text categorization, Journal of Information Retrieval, 1999, 1(1/2), pp. 67-88.

@Book{Svenonius_2000,
  title = "The intellectual foundations of information organization",
  year = 2000,
  publisher = "MIT Press, Cambridge, MA, USA",
  author = "E. Svenonius"
}
%E. Svenonius, The intellectual foundations of information organization. Cambridge, MA: MIT Press, 2000.

@InProceedings{Chen_Dumais_2000,
    author = "H. Chen and S. T. Dumais",
    title = "Bringing order to the web: automatically categorizing search results",
    booktitle = "Proc. of CHI-00, ACM International Conference on Human Factors in Computing Systems",
    pages = "145--152",
    month = "",
    year = "2000"
}
%H. Chen, and S. T. Dumais, Bringing order to the web: automatically categorizing search results, in Proc. of CHI-00, ACM International Conference on Human Factors in Computing Systems, 2000, pp.145-52. 

@article{Bang_etal_06,
    author = "S. L. Bang and J. D. Yang and H. J. Yang",
    title = "Hierarchical document categorization with k-NN and concept-based thesauri",
    journal = "Information Processing and Management",
    volume = "",
    number = "42",
    pages = "387--406",
    year = "2006"
}
%S. L. Bang, J. D. Yang, and H. J. Yang, Hierarchical document categorization with k-NN and concept-based thesauri, Information Processing and Management, 2006, 42, pp. 387-406.

@article{Garces_etal_06,
    author = "P. J. Garcés and J. A. Olivas and F. P. Romero",
    title = "Concept-matching IR systems versus word-matching information retrieval systems: Considering fuzzy interrelations for indexing Web pages",
    journal = "JASIS\&T",
    volume = "57",
    number = "4",
    pages = "564--576",
    year = "2006"
}
%P. J. Garcés, J. A. Olivas, and F. P. Romero, Concept-matching IR systems versus word-matching information retrieval systems: Considering fuzzy interrelations for indexing Web pages, JASIS&T 2006, 57(4), pp. 564-576.

@InProceedings{Medelyan_06,
    author = "O. Medelyan and I. Witten",
    title = "Thesaurus based automatic keyphrase indexing",
    booktitle = "Proceedings of the Sixth ACM/IEEE Joint Conference on Digital Libraries, JCDL 06",
    pages = "296--297",
    month = "",
    year = "2006"
}
%O. Medelyan, and I. Witten, Thesaurus based automatic keyphrase indexing, in: Proc. of the JCDL 2006, pp. 296-297.

@Misc{International_85,
 title = {{Documentation - Methods for examining documents, determining their subjects, and selecting index terms}},
 note =  "International Organization for Standardization, Standard 5963-1985"
}
%International Organization for Standardization. Documentation - Methods for examining documents, determining their subjects, and selecting index terms, ISO Standard 5963-1985. 

@book{Lancaster_03,
  title = "Indexing and abstracting in theory and practice",
  year = 2003,
  publisher = "Facet, London",
  note = "3rd ed.",
  author = "F. W. Lancaster"
}
%F. W. Lancaster, Indexing and abstracting in theory and practice. 3rd ed., London: Facet, 2003.

@book{Olson_01,
  title = "Subject analysis in online catalogs",
  year = 2001,
  publisher = "Englewood, CO: Libraries Unlimited",
  note = "2nd ed.",
  author = "H. A. Olson and J. J. Boll"
}
%H. A. Olson, and J. J. Boll, Subject analysis in online catalogs. 2nd ed. Englewood, CO: Libraries Unlimited, 2001.

@Misc{Hjorland06,
 title = {{Lifeboat for knowledge organization: indexing theory}},
 note =  "\htmladdnormallink{http://www.db.dk/bh/Lifeboat\_KO/CONCEPTS/indexing\_theory.htm}{http://www.db.dk/bh/Lifeboat_KO/CONCEPTS/indexing_theory.htm}"
}
%B. Hjřrland, Lifeboat for knowledge organization: indexing theory.  Available: http://www.db.dk/bh/Lifeboat_KO/CONCEPTS/indexing_theory.htm  

@book{1Ingwersen_05,
  title = "The turn: integration of information seeking and retrieval in context",
  year = 2005,
  publisher = "Springer, Dordrecht, The Netherlands",
  author = "P. Ingwersen and K. Järvelin"
}
%P. Ingwersen, and K. Järvelin, The turn: integration of information seeking and retrieval in context. Dordrecht, The Netherlands: Springer, 2005.

@article{Sebastiani_02,
    author = "F. Sebastiani",
    title = "Machine learning in automated text categorization",
    journal = "ACM Computing Surveys",
    volume = "34",
    number = "1",
    pages = "1--47",
    year = "2002"
}
%F. Sebastiani, Machine learning in automated text categorization, ACM Computing Surveys, 2002, 34(1), pp. 1-47.

@Misc{Compendex,
 title = {{Compendex database}},
 note =  "\htmladdnormallink{http://www.engineeringvillage2.org/}{http://www.engineeringvillage2.org/}"
}
%Compendex database. Available: http://www.engineeringvillage2.org/.
@MastersThesis{Rafael06,
  school =       {Dept. of Information Technology, Lund University, P.O. Box 118, S-221~00 Lund, Sweden},
  author = {Rafael Romero Trujilo},
  title = {Simulation Tool to Study Focused Web Crawling Strategies},
  month = mar,
 note =  "\htmladdnormallink{http://combine.it.lth.se/CrawlSim/CrawlSim.pdf}{http://combine.it.lth.se/CrawlSim/CrawlSim.pdf}",
  year = 2006
}