@article{1550700, abstract = {Ontologies play a vital role in many web- and internet-related applications. This work presents a system for accelerating the ontology building process via semi-automatically learning a hierarchal ontology given a set of domain-specific web documents and a set of seed concepts. The methods are tested with web documents in the domain of agriculture. The ontology is constructed through the use of two complementary approaches. The presented system has been used to build an ontology in the agricultural domain using a set of Arabic extension documents and evaluated against a modified version of the AGROVOC ontology.}, address = {Inderscience Publishers, Geneva, SWITZERLAND}, author = {Hazman, Maryam and El-Beltagy, Samhaa R. and Rafea, Ahmed}, doi = {http://dx.doi.org/10.1504/IJMSO.2009.026251}, interhash = {fe27d687bcba91a7a6fe51eec9a2b87d}, intrahash = {589512e472b561da3770905d01773d00}, issn = {1744-2621}, journal = {Int. J. Metadata Semant. Ontologies}, number = {1/2}, pages = {24--33}, publisher = {Inderscience Publishers}, title = {Ontology learning from domain specific web documents}, url = {http://portal.acm.org/citation.cfm?id=1550700}, volume = 4, year = 2009 } @article{10.1109/ITCS.2009.234, address = {Los Alamitos, CA, USA}, author = {Yuhuang, Wu and Yusheng, Li}, doi = {http://doi.ieeecomputersociety.org/10.1109/ITCS.2009.234}, interhash = {2bd791fbd5d2a6da2d5565e078fe506c}, intrahash = {ba7ef53003a4627552991094558822c3}, isbn = {978-0-7695-3688-0}, journal = {Information Technology and Computer Science, International Conference on}, pages = {485-488}, publisher = {IEEE Computer Society}, title = {Design and Realization for Ontology Learning Model Based on Web}, url = {http://www.computer.org/portal/web/csdl/doi/10.1109/ITCS.2009.234}, volume = 2, year = 2009 } @book{Gómez-Pérez:2004, abstract = {Literaturverz. S. 363 - 388}, author = {Gómez-Pérez, Asunción and Fernández-López, Mariano and Corcho, Oscar}, interhash = {084af60958abe30b431aa5acc30696af}, intrahash = {7bccdc4007d7a15b3215e941abec80da}, isbn = {1-85233-551-3}, opac = {http://opac.bibliothek.uni-kassel.de/DB=1/PPN?PPN=125031319}, publisher = {Springer London [u.a.]}, title = {Ontological engineering}, url = {http://opac.bibliothek.uni-kassel.de/DB=1/PPN?PPN=125031319}, year = 2004 } @inproceedings{Ome01, author = {Omelayenko, Borys}, booktitle = {Proceedings of the International Workshop on Web Dynamics, held in conj. with the 8th International Conference on Database Theory (ICDT’01), London, UK}, interhash = {011d45b904b02fdf1a65122d2832710b}, intrahash = {3edf80da8b39eefeea46379581628adf}, title = {Learning of Ontologies for the Web: the Analysis of Existent Approaches}, url = {http://www.dcs.bbk.ac.uk/webDyn/webDynPapers/omelayenko.pdf}, year = 2001 } @article{375731, abstract = {A data-integration system provides access to a multitude of data sources through a single mediated schema. A key bottleneck in building such systems has been the laborious manual construction of semantic mappings between the source schemas and the mediated schema. We describe LSD, a system that employs and extends current machine-learning techniques to semi-automatically find such mappings. LSD first asks the user to provide the semantic mappings for a small set of data sources, then uses these mappings together with the sources to train a set of learners. Each learner exploits a different type of information either in the source schemas or in their data. Once the learners have been trained, LSD finds semantic mappings for a new data source by applying the learners, then combining their predictions using a meta-learner. To further improve matching accuracy, we extend machine learning techniques so that LSD can incorporate domain constraints as an additional source of knowledge, and develop a novel learner that utilizes the structural information in XML documents. Our approach thus is distinguished in that it incorporates multiple types of knowledge. Importantly, its architecture is extensible to additional learners that may exploit new kinds of information. We describe a set of experiments on several real-world domains, and show that LSD proposes semantic mappings with a high degree of accuracy.}, address = {New York, NY, USA}, author = {Doan, AnHai and Domingos, Pedro and Halevy, Alon Y.}, doi = {http://doi.acm.org/10.1145/376284.375731}, interhash = {1550f1948858bf8b315ea2fc6ed789cd}, intrahash = {29e7660361ca79b97b00e5db51fb66ee}, issn = {0163-5808}, journal = {SIGMOD Rec.}, number = 2, pages = {509--520}, publisher = {ACM}, title = {Reconciling schemas of disparate data sources: a machine-learning approach}, url = {http://portal.acm.org/citation.cfm?id=375731&dl=GUIDE&coll=GUIDE&CFID=75153142&CFTOKEN=89522229}, volume = 30, year = 2001 } @inproceedings{conf/Rudolph07, address = {Berlin, Heidelberg}, author = {Rudolph, Sebastian and Völker, Johanna and Hitzler, Pascal}, booktitle = {Proceedings of the 15th International Conference on Conceptual Structures (ICCS 2007)}, crossref = {conf/iccs/2006}, editor = {Priss, Uta and Polovina, Simon and Hill, Richard}, interhash = {95939c2e69ef57fcf65e93df6010fe60}, intrahash = {06b7dbf2f1ae4a442bb1559c499dae16}, isbn = {3-540-73680-8}, month = {July}, pages = {488-491}, publisher = {Springer-Verlag}, series = {Lecture Notes in Artificial Intelligence}, title = {Supporting Lexical Ontology Learning by Relational Exploration}, url = {http://www.aifb.uni-karlsruhe.de/WBS/phi/resources/publications/iccs07-relexp.pdf}, volume = 4604, year = 2007 } @techreport{Gomez-Perez_OntoWeb03, author = {{G{\'o}mez-P{\'e}rez}, Asuncion and Manzano-Macho, David}, file = {Gomez-Perez_OntoWeb03.pdf:Gomez_Perez/Gomez-Perez_OntoWeb03.pdf:PDF}, institution = {OntoWeb Consortium}, interhash = {8ee5304684f3b0974890a7427c2438ae}, intrahash = {6b56e7f1d2b3913be8a04a09c6d566c1}, number = {1.5}, title = {A survey of ontology learning methods and techniques}, type = {Deliverable}, url = {http://www.deri.at/fileadmin/documents/deliverables/Ontoweb/D1.5.pdf}, year = 2003 } @book{buitelaar2008ontology, asin = {1586038184}, author = {Buitelaar, Paul and Cimiano, Philipp}, dewey = {006.33}, ean = {9781586038182}, edition = {illustrated edition}, interhash = {985072a36f1f789052de6678e17e4eb8}, intrahash = {c7267178358f790c16aac7288ad56167}, isbn = {1586038184}, publisher = {Ios Press Inc}, title = {Ontology Learning and Population: Bridging the Gap Between Text and Knowledge }, url = {http://www.booksonline.iospress.nl/Content/View.aspx?piid=8211}, volume = 167, year = 2008 } @inproceedings{1661779, abstract = {A folksonomy refers to a collection of user-defined tags with which users describe contents published on the Web. With the flourish of Web 2.0, folksonomies have become an important mean to develop the Semantic Web. Because tags in folksonomies are authored freely, there is a need to understand the structure and semantics of these tags in various applications. In this paper, we propose a learning approach to create an ontology that captures the hierarchical semantic structure of folksonomies. Our experimental results on two different genres of real world data sets show that our method can effectively learn the ontology structure from the folksonomies.}, address = {San Francisco, CA, USA}, author = {Tang, Jie and fung Leung, Ho and Luo, Qiong and Chen, Dewei and Gong, Jibin}, booktitle = {IJCAI'09: Proceedings of the 21st international jont conference on Artifical intelligence}, interhash = {17f95a6ba585888cf45443926d8b7e98}, intrahash = {7b335f08a288a79eb70eff89f1ec7630}, location = {Pasadena, California, USA}, pages = {2089--2094}, publisher = {Morgan Kaufmann Publishers Inc.}, title = {Towards ontology learning from folksonomies}, url = {http://ijcai.org/papers09/Papers/IJCAI09-344.pdf}, year = 2009 } @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 } @inproceedings{conf/wise/EdaYY08, author = {Eda, Takeharu and Yoshikawa, Masatoshi and Yamamuro, Masashi}, booktitle = {WISE}, crossref = {conf/wise/2008}, date = {2008-08-25}, editor = {Bailey, James and Maier, David and Schewe, Klaus-Dieter and Thalheim, Bernhard and Wang, Xiaoyang Sean}, ee = {http://dx.doi.org/10.1007/978-3-540-85481-4_13}, interhash = {9d4e2e5c9ea51b5ee850d328eb940524}, intrahash = {a9d9bbe9f365dc1da1df79fffbf95a0d}, isbn = {978-3-540-85480-7}, pages = {151-162}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Locally Expandable Allocation of Folksonomy Tags in a Directed Acyclic Graph.}, url = {http://dblp.uni-trier.de/db/conf/wise/wise2008.html#EdaYY08}, volume = 5175, year = 2008 } @mastersthesis{stützer2008ol, address = {Kassel}, author = {Stützer, Stefan}, interhash = {9426b67db29c7270955ae22202c28c82}, intrahash = {23b133bc2e6a4e00ab243efa98a02a12}, school = {University of Kassel}, title = {Lernen von Ontologien aus kollaborativen Tagging-Systemen}, type = {Master Thesis}, year = 2009 } @incollection{bloehdorn2006learning, abstract = {Recent work has shown improvements in text clustering and classification tasks by integrating conceptual features extracted from ontologies. In this paper we present text mining experiments in the medical domain in which the ontological structures used are acquired automatically in an unsupervised learning process from the text corpus in question. We compare results obtained using the automatically learned ontologies with those obtained using manually engineered ones. Our results show that both types of ontologies improve results on text clustering and classification tasks, whereby the automatically acquired ontologies yield a improvement competitive with the manually engineered ones. ER -}, author = {Bloehdorn, Stephan and Cimiano, Philipp and Hotho, Andreas}, booktitle = {From Data and Information Analysis to Knowledge Engineering}, doi = {http://dx.doi.org/10.1007/3-540-31314-1_40}, interhash = {cf1af505b638677f00b3d3d7a5903199}, intrahash = {bc1d40cf4fd64780ecf712b1e40f31de}, isbn = {978-3-540-31313-7}, pages = {334--341}, publisher = {Springer Berlin Heidelberg}, title = {Learning Ontologies to Improve Text Clustering and Classification}, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/2006/2006-03-gfkl05-bloehdorn-etal-learning-ontologies.pdf}, year = 2006 } @article{1356291, address = {Inderscience Publishers, Geneva, SWITZERLAND}, author = {Meyer, M. and Rensing, C. and Steinmetz, R.}, doi = {http://dx.doi.org/10.1504/IJAMC.2008.016758}, interhash = {ef644e35df4c37fb1057330ffe09faf8}, intrahash = {185c6aed86c00188b23c0ca1c83c4e90}, issn = {1462-4613}, journal = {Int. J. Adv. Media Commun.}, number = 1, pages = {59--72}, publisher = {Inderscience Publishers}, title = {Using community & generated contents as a substitute corpus for metadata generation}, url = {http://portal.acm.org/citation.cfm?id=1356291}, volume = 2, year = 2008 } @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 } @misc{Medelyan2008, abstract = { Wikipedia is a goldmine of information; not just for its many readers, but also for the growing community of researchers who recognize it as a resource of exceptional scale and utility. It represents a vast investment of manual effort and judgment: a huge, constantly evolving tapestry of concepts and relations that is being applied to a host of tasks. This article provides a comprehensive description of this work. It focuses on research that extracts and makes use of the concepts, relations, facts and descriptions found in Wikipedia, and organizes the work into four broad categories: applying Wikipedia to natural language processing; using it to facilitate information retrieval and information extraction; and as a resource for ontology building. The article addresses how Wikipedia is being used as is, how it is being improved and adapted, and how it is being combined with other structures to create entirely new resources. We identify the research groups and individuals involved, and how their work has developed in the last few years. We provide a comprehensive list of the open-source software they have produced. We also discuss the implications of this work for the long-awaited semantic web. }, author = {Medelyan, Olena and Legg, Catherine and Milne, David and Witten, Ian H.}, interhash = {6614c7cd27d80abd691b2ef463941d1c}, intrahash = {0e7499a4f087f74ad0be674047cf315d}, note = {cite arxiv:0809.4530 Comment: An extensive survey of re-using information in Wikipedia in natural language processing, information retreival and extraction and ontology building. submitted}, title = {Mining Meaning from Wikipedia}, url = {http://arxiv.org/abs/0809.4530}, year = 2008 } @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{blaz06ontogen, abstract = {In this paper we present a new version of OntoGen system for semi-automatic data-driven ontology construction. The system is based on a novel ontology learning framework which formalizes and extends the role of machine learning and text mining algorithms used in the previous version. List of new features includes extended number of supported ontology formats (RDFS and OWL), supervised methods for concept discovery (based on Active Learning), adding of new instances to ontology and improved user interface (based on comments from the users).}, author = {Fortuna, Blaz and Grobelnik, Marko and Mladenić, Dunja}, interhash = {91f979c3983afb0d8ef4e7c51e46c5aa}, intrahash = {fb694aa68ef84daf7556cd14b92bdc04}, location = {http://www.scientificcommons.org/17521109}, title = {Semi-automatic data-driven ontology construction system}, year = 2006 } @inproceedings{PuWang:2007, abstract = {The exponential growth of text documents available on the Internet has created an urgent need for accurate, fast, and general purpose text classification algorithms. However, the "bag of words" representation used for these classification methods is often unsatisfactory as it ignores relationships between important terms that do not co-occur literally. In order to deal with this problem, we integrate background knowledge - in our application: Wikipedia - into the process of classifying text documents. The experimental evaluation on Reuters newsfeeds and several other corpus shows that our classification results with encyclopedia knowledge are much better than the baseline "bag of words " methods.}, author = {Wang, Pu and Hu, Jian and Zeng, Hua-Jun and Chen, Lijun and Chen, Zheng}, booktitle = {Data Mining, 2007. ICDM 2007. Seventh IEEE International Conference on}, doi = {10.1109/ICDM.2007.77}, interhash = {8a899b60047e20e162fc12b2ff6f8142}, intrahash = {66058efbca5abd1222f72c32365d23fa}, isbn = {978-0-7695-3018-5}, issn = {1550-4786}, pages = {332-341}, title = {Improving Text Classification by Using Encyclopedia Knowledge}, url = {ftp://ftp.computer.org/press/outgoing/proceedings/icdm07/Data/3018a332.pdf}, year = 2007 } @inproceedings{nldb05, address = {Alicante, Spain}, author = {Cimiano, Philipp and Völker, Johanna}, booktitle = {Proceedings of the 10th International Conference on Applications of Natural Language to Information Systems (NLDB)}, editor = {Montoyo, Andres and Munoz, Rafael and Metais, Elisabeth}, interhash = {c90cb094c9f4f3cca1214d0478ffeb07}, intrahash = {072436e5adc4f5fdc39f4baeaa55b077}, month = JUN, pages = {227-238}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Text2Onto - A Framework for Ontology Learning and Data-driven Change Discovery}, url = {\url{http://www.aifb.uni-karlsruhe.de/WBS/jvo/publications/Text2Onto_nldb_2005.pdf}}, volume = 3513, year = 2005 }