@proceedings{30474,
  author = {Tresp, Volker and Bundschus, Markus and Rettinger, Achim and Huang, Yi},
  interhash = {e27fbf5b5fb16f66cd0c7a3932fc4695},
  intrahash = {006468688804bc3563225b8dcd7aea97},
  journal = {Uncertainty Reasoning for the Semantic Web I Lecture Notes in AI},
  publisher = {Springer},
  title = {Towards machine learning on the semantic web},
  url = {http://wwwbrauer.informatik.tu-muenchen.de/~trespvol/papers/LearningRDF23.pdf},
  year = 2008
}

@article{kosala00web,
  address = {New York, NY, USA},
  author = {Kosala, R. and Blockeel, H.},
  bibsource = {DBLP, http://dblp.uni-trier.de},
  interhash = {99eea914954da48c9691277ce4e32932},
  intrahash = {59f6ef686827c7095cc89ebdb056a222},
  journal = {SIGKDD Explorations},
  number = 1,
  pages = {1--15},
  publisher = {ACM},
  title = {Web Mining Research: {A} Survey},
  url = {http://citeseer.nj.nec.com/kosala00web.html},
  volume = 2,
  year = 2000
}

@proceedings{Staab2004HOO,
  address = {Berlin; New York},
  booktitle = {International handbooks on information systems},
  editor = {Staab, Steffen and Studer, Rudi},
  interhash = {494a7427b9dd11496d824c824b35938b},
  intrahash = {f920f0aabbe7a02c9fe5d65c298bc8ea},
  issn = {3540408347  9783540408345},
  pages = {--},
  publisher = {Springer},
  refid = {53814725},
  title = {Handbook on ontologies},
  year = 2004
}

@article{citeulike:2146554,
  abstract = {Nowadays, multi-label classification methods are increasingly required by modern applications, such as protein function classification, music categorization and semantic scene classification. This paper introduces the task of multi-label classification, organizes the sparse related literature into a structured presentation and performs comparative experimental results of certain multi-label classification methods. It also contributes the definition of concepts for the quantification of the multi-label nature of a data set.},
  author = {Tsoumakas, G. and Katakis, I.},
  citeulike-article-id = {2146554},
  editor = {Taniar, David},
  interhash = {f8e6c4b6b3df7461d070a1a9cc1d15c1},
  intrahash = {52c3b18481f5146e4c213d609c1143fc},
  journal = {International Journal of Data Warehouse and Mining},
  number = 3,
  pages = {1--13},
  posted-at = {2007-12-19 13:38:29},
  priority = {2},
  publisher = {Idea Group Publishing},
  title = {Multi Label Classification: An Overview},
  volume = 3,
  year = 2007
}

@article{Famili:1997:1088-467X:3,
  abstract = {This paper first provides an overview of data preprocessing, focusing on problems of real world data. These are primarily problems that have to be carefully understood and solved before any data analysis process can start. The paper discusses in detail two main reasons for performing data preprocessing: (i) problems with the data and (ii) preparation for data analysis. The paper continues with details of data preprocessing techniques achieving each of the above mentioned objectives. A total of 14 techniques are discussed. Two examples of data preprocessing applications from two of the most data rich domains are given at the end. The applications are related to semiconductor manufacturing and aerospace domains where large amounts of data are available, and they are fairly reliable. Future directions and some challenges are discussed at the end.},
  author = {Famili, A. and Shen, W.-M. and Weber, R. and Simoudis, E.},
  doi = {doi:10.1016/S1088-467X(98)00007-9},
  interhash = {3da26163f9537a42a984f7bfb8456fd3},
  intrahash = {808497c457a1d53d78b5455f0ed71912},
  journal = {Intelligent Data Analysis},
  pages = {3-23(21)},
  title = {Data Preprocessing and Intelligent Data Analysis},
  url = {http://www.iit-iti.nrc-cnrc.gc.ca/publications/nrc-40166_e.html},
  volume = 1,
  year = 1997
}

@article{survey91safavian,
  abstract = {A survey is presented of current methods for decision tree classifier (DTC) designs and the various existing issues. After considering potential advantages of DTCs over single-state classifiers, the subjects of tree structure design, feature selection at each internal node, and decision and search strategies are discussed. The relation between decision trees and neutral networks (NN) is also discussed},
  author = {Safavian, S. R. and Landgrebe, D.},
  booktitle = {Systems, Man and Cybernetics, IEEE Transactions on},
  interhash = {d191b7a5dd9037f7e05357e9be3cf1c2},
  intrahash = {348c3ca0090e508133fffdf656b2432a},
  journal = {Systems, Man and Cybernetics, IEEE Transactions on},
  number = 3,
  pages = {660--674},
  title = {A survey of decision tree classifier methodology},
  url = {http://ieeexplore.ieee.org/xpls/abs\_all.jsp?arnumber=97458},
  volume = 21,
  year = 1991
}

@article{Burke02,
  author = {Burke, Robin},
  file = {Burke02.pdf:Burke02.pdf:PDF},
  interhash = {f40020400b8bc08adca29a987caf25d8},
  intrahash = {2dd27925f83ea7b04b5fc444938b866b},
  journal = {User Modeling and User Adapted Interaction},
  number = 4,
  owner = {stormerh},
  pages = {331-370},
  timestamp = {2006.11.20},
  title = {Hybrid Recommender Systems, Survey and Experiments},
  volume = 12,
  year = 2002
}

@article{keyhere,
  abstract = {Abstract  Ontology is one of the fundamental cornerstones of the semantic Web. The pervasive use of ontologies in information sharing
and knowledge management calls for efficient and effective approaches to ontology development. Ontology learning, which seeksto discover ontological knowledge from various forms of data automatically or semi-automatically, can overcome the bottleneckof ontology acquisition in ontology development. Despite the significant progress in ontology learning research over the pastdecade, there remain a number of open problems in this field. This paper provides a comprehensive review and discussion ofmajor issues, challenges, and opportunities in ontology learning. We propose a new learning-oriented model for ontology developmentand a framework for ontology learning. Moreover, we identify and discuss important dimensions for classifying ontology learningapproaches and techniques. In light of the impact of domain on choosing ontology learning approaches, we summarize domaincharacteristics that can facilitate future ontology learning effort. The paper offers a road map and a variety of insightsabout this fast-growing field.},
  author = {Zhou, Lina},
  interhash = {78b6d3db998dcd27c475dfff3816f48f},
  intrahash = {95b0f4f7c9c628e032d8bb4c69b432ed},
  journal = {Information Technology and Management},
  month = {#sep#},
  number = 3,
  pages = {241--252},
  title = {Ontology learning: state of the art and open issues},
  url = {http://dx.doi.org/10.1007/s10799-007-0019-5},
  volume = 8,
  year = 2007
}

@article{4686305,
  abstract = {Social tagging systems have recently became very popular as a means to classify large sets of resources shared among on-line communities over the social Web. However, the folksonomies resulting from the use of these systems revealed limitations : tags are ambiguous and their spelling may vary, and folksonomies are difficult to exploit in order to retrieve or exchange information. This article compares the recent attempts to overcome these limitations and to support the use of folksonomies with formal languages and ontologies from the Semantic Web.},
  author = {Limpens, Freddy and Gandon, Fabien and Buffa, Michel},
  doi = {10.1109/ASEW.2008.4686305},
  interhash = {cb1d534be80d664a50df66e8977b774e},
  intrahash = {9372f9c2db8b9f4cf05b3db84e6589ac},
  journal = {Automated Software Engineering - Workshops, 2008. ASE Workshops 2008. 23rd IEEE/ACM International Conference on},
  month = {Sept.},
  pages = {13-18},
  title = {Bridging ontologies and folksonomies to leverage knowledge sharing on the social Web: A brief survey},
  year = 2008
}

@article{1282,
  author = {Cimiano, Philipp and Völker, Johanna and Studer, Rudi},
  interhash = {aeb553dc2e190f0a5974dfdc709d450a},
  intrahash = {fe4c2950b5be221b493e29e4339240e8},
  journal = {Information, Wissenschaft und Praxis},
  month = OCT,
  note = {see the special issue for more contributions related to the Semantic Web},
  number = {6-7},
  pages = {315-320},
  title = {Ontologies on Demand? - A Description of the State-of-the-Art, Applications, Challenges and Trends for Ontology Learning from Text},
  url = {\url{http://www.aifb.uni-karlsruhe.de/WBS/pci/Publications/iwp06.pdf}},
  volume = 57,
  year = 2006
}

@article{Smeulders00CBIR,
  address = {Washington, DC, USA},
  author = {Smeulders, Arnold W. M. and Worring, Marcel and Santini, Simone and Gupta, Amarnath and Jain, Ramesh},
  citeulike-article-id = {942093},
  doi = {10.1109/34.895972},
  interhash = {ead44ca34c9a120a17c6d1cb757d3b8d},
  intrahash = {ff99ff85fdc2224d826dab75df21cf0d},
  issn = {0162-8828},
  journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
  month = {December},
  number = 12,
  pages = {1349--1380},
  posted-at = {2008-04-13 17:14:20},
  priority = {2},
  publisher = {IEEE Computer Society},
  title = {Content-Based Image Retrieval at the End of the Early Years},
  url = {http://portal.acm.org/citation.cfm?id=357873},
  volume = 22,
  year = 2000
}

@article{datta2008,
  abstract = {We have witnessed great interest and a wealth of promise in content-based image retrieval as an emerging technology. While the last decade laid foundation to such promise, it also paved the way for a large number of new techniques and systems, got many new people involved, and triggered stronger association of weakly related fields. In this paper, we survey almost 300 key theoretical and empirical contributions in the current decade related to image retrieval and automatic image annotation, and discuss the spawning of related sub-fields in the process. We also discuss significant challenges involved in the adaptation of existing image retrieval techniques to build systems that can be useful in the real-world. In retrospect of what has been achieved so far, we also conjecture what the future may hold for image retrieval research.},
  author = {Datta, Ritendra and Joshi, Dhiraj and Li, Jia and Wang, James Z.},
  interhash = {6f908ace6a3d5135960dc663d6335922},
  intrahash = {278a48194bc9afbd298c36dd497a9821},
  journal = {ACM Computing Surveys},
  number = 2,
  title = {Image Retrieval: Ideas, Influences, and Trends of the New Age},
  url = {http://infolab.stanford.edu/~wangz/project/imsearch/review/JOUR/},
  volume = 40,
  year = 2008
}

@article{974906,
  abstract = {Users of online search engines often find it difficult to express their need for information in the form of a query. However, if the user can identify examples of the kind of documents they require then they can employ a technique known as relevance feedback. Relevance feedback covers a range of techniques intended to improve a user's query and facilitate retrieval of information relevant to a user's information need. In this paper we survey relevance feedback techniques. We study both automatic techniques, in which the system modifies the user's query, and interactive techniques, in which the user has control over query modification. We also consider specific interfaces to relevance feedback systems and characteristics of searchers that can affect the use and success of relevance feedback systems.},
  address = {New York, NY, USA},
  author = {Ruthven, Ian and Lalmas, Mounia},
  doi = {http://dx.doi.org/10.1017/S0269888903000638},
  interhash = {965654547515dda5b340f80c41718ca4},
  intrahash = {0357d6b4d3aa885a0978036d50136373},
  issn = {0269-8889},
  journal = {Knowl. Eng. Rev.},
  number = 2,
  pages = {95--145},
  publisher = {Cambridge University Press},
  title = {A survey on the use of relevance feedback for information access systems},
  url = {http://personal.cis.strath.ac.uk/~ir/papers/ker.pdf},
  volume = 18,
  year = 2003
}

@inproceedings{domingos2003,
  author = {Domingos, P. and Abe, Y. and Anderson, C. and Doan, A. and Fox, D. and Halevy, A. and Hulten, G. and Kautz, H. and Lau, T. and Liao, L. and Madhavan, J. and Mausam and Patterson, D. and Richardson, M. and Sanghai, S. and Weld, D. and Wolfman, S.},
  booktitle = {Proceedings of the IJCAI-2003 Workshop on Learning Statistical Models from Relational Data},
  interhash = {2d2448903dc10789aef8e4238f0cc698},
  intrahash = {1a4c5b5688b4295ad19bd72295c25ba2},
  location = {Acapulco, Mexico: IJCAII},
  title = {Research on Statistical Relational Learning at the University of Washington},
  url = {http://www.cs.washington.edu/homes/pedrod/papers/srl03a.pdf},
  year = 2003
}

@inproceedings{neville2003srl,
  abstract = {Statistical relational learning (SRL) research has made significant progress over the last 5 years. We have successfully demonstrated the feasibility of a number of probabilistic models for relational data, including probabilistic relational models, Bayesian logic programs, and relational probability trees, and the interest in SRL isgrowing. However, in order to sustain and nurture the growth of SRL as a subfield we need to refocus our efforts on the science of machine learning — moving from demonstrations to comparative and ablation studies. We will outline four assertions that are implicit to SRL research but which have been only minimally evaluated. We hope to stimulate discussion as to how, as a community, these claims can be addressed in future research.},
  author = {Neville, J. and Rattigan, M. and Jensen, D.},
  booktitle = {Proceedings of the Workshop on Learning Statistical Models from Relational Data, Eighteenth International Joint Conference on Artificial Intelligence},
  date = {(2003)},
  interhash = {6d36575c17f75bc69e1ea941cda5d8fb},
  intrahash = {6f4fe9dc01547709202ad6556423e863},
  title = {Statistical relational learning: Four claims and a survey},
  url = {http://kdl.cs.umass.edu/papers/neville-et-al-srl2003.pdf},
  year = 2003
}

@article{ide98wsd,
  author = {Ide, N. and Véronis, J.},
  interhash = {639960f8e91b47185cab6f3194d9667f},
  intrahash = {7ec15face46e6b45586701c7fed93eab},
  journal = {Computational Linguistics},
  number = 1,
  pages = {1--40},
  title = {{Introduction to the Special Issue on Word Sense Disambiguation: The State of the Art}},
  volume = 24,
  year = 1998
}

@article{crestani1997spreading,
  abstract = {This paper surveys the use of Spreading Activation techniques onSemantic Networks in Associative Information Retrieval. The majorSpreading Activation models are presented and their applications toIR is surveyed. A number of works in this area are criticallyanalyzed in order to study the relevance of Spreading Activation forassociative IR.
ER  -},
  author = {Crestani, F.},
  interhash = {3dfe398bb588335ffc562088d5a509de},
  intrahash = {c26c16e0a8036000b788fada656f59dd},
  journal = {Artificial Intelligence Review},
  month = {December},
  number = 6,
  pages = {453--482},
  title = {Application of Spreading Activation Techniques in Information Retrieval},
  url = {http://dx.doi.org/10.1023/A:1006569829653},
  volume = 11,
  year = 1997
}

@misc{citeulike:1115448,
  abstract = {Tagging, folksonomy, distributed classification, ethnoclassification—however it is labelled, the concept of users creating and aggregating their own metadata is gaining ground on the internet. This literature review briefly defines the topic at hand, looking at current implementations and summarizing key advantages and disadvantages of distributed classification systems with reference to prominent folksonomy commentators.  After considering whether distributed classification can replace expert catalogers entirely, it concludes that distributed classification can make an important contribution to digital information organisation, but that it may need to be integrated with more traditional organisation tools to overcome its current weaknesses.},
  author = {Speller, Edith},
  citeulike-article-id = {1115448},
  interhash = {2d40636857edfcf58b0977948e40ce4d},
  intrahash = {16373fb33b38c4769794ed7e7875f27e},
  journal = {Library Student Journal},
  month = {February},
  priority = {0},
  title = {Library Student Journal: Collaborative tagging, folksonomies, distributed classification or ethnoclassification: a literature review.},
  url = {http://informatics.buffalo.edu/org/lsj/articles/speller_2007_2_collaborative.php},
  year = 2007
}

@misc{voss-2007,
  abstract = {This paper gives an overview of current trends in manual indexing on the Web. Along with a general rise of user generated content there are more and more tagging systems that allow users to annotate digital resources with tags (keywords) and share their annotations with other users. Tagging is frequently seen in contrast to traditional knowledge organization systems or as something completely new. This paper shows that tagging should better be seen as a popular form of manual indexing on the Web. Difference between controlled and free indexing blurs with sufficient feedback mechanisms. A revised typology of tagging systems is presented that includes different user roles and knowledge organization systems with hierarchical relationships and vocabulary control. A detailed bibliography of current research in collaborative tagging is included.},
  author = {Voss, Jakob},
  interhash = {c293cd6ef590c6aaf32df75cbdb9de82},
  intrahash = {9ec98351dc630ea6b1f65046ba44a8dd},
  title = {Tagging, Folksonomy \& Co - Renaissance of Manual Indexing?},
  url = {http://www.citebase.org/abstract?id=oai:arXiv.org:cs/0701072},
  year = 2007
}

@article{Rui05SurveyClustering,
  abstract = {Data analysis plays an indispensable role for understanding various
	phenomena. Cluster analysis, primitive exploration with little or
	no prior knowledge, consists of research developed across a wide
	variety of communities. The diversity, on one hand, equips us with
	many tools. On the other hand, the profusion of options causes confusion.
	We survey clustering algorithms for data sets appearing in statistics,
	computer science, and machine learning, and illustrate their applications
	in some benchmark data sets, the traveling salesman problem, and
	bioinformatics, a new field attracting intensive efforts. Several
	tightly related topics, proximity measure, and cluster validation,
	are also discussed.},
  author = {Xu, Rui and Wunsch, II},
  interhash = {7bd8c3f3c7ea707f110d76123e0d097c},
  intrahash = {92c03ba02a41f95ae315273939c8daa5},
  issn = {1045-9227},
  journal = {Neural Networks, IEEE Transactions on},
  number = 3,
  owner = {mgrani},
  pages = {645--678},
  timestamp = {2006.06.08},
  title = {Survey of clustering algorithms},
  volume = 16,
  year = 2005
}