@inproceedings{bullinaria2008semantic, author = {Bullinaria, J.A.}, file = {bullinaria2008semantic.pdf:bullinaria2008semantic.pdf:PDF}, groups = {public}, interhash = {cdb7b1ff0e89f61f84e2c15a0e46c221}, intrahash = {efae206c0f89363a3273a8d57c87eff5}, journal = {ESSLLI Workshop on Distributional Lexical Semantics}, timestamp = {2011-01-28 09:53:43}, title = {Semantic Categorization Using Simple Word Co-occurrence statistics}, username = {dbenz}, year = 2008 } @inproceedings{christiaens2006metadata, abstract = {In this paper we give a brief overview of different metadata mechanisms (like ontologies and folksonomies) and how they relate to each other. We identify major strengths and weaknesses of these mechanisms. We claim that these mechanisms can be classified from restricted (e.g., ontology) to free (e.g., free text tagging). In our view, these mechanisms should not be used in isolation, but rather as complementary solutions, in a continuous process wherein the strong points of one increase the semantic depth of the other. We give an overview of early active research already going on in this direction and propose that methodologies to support this process be developed. We demonstrate a possible approach, in which we mix tagging, taxonomy and ontology.}, author = {Christiaens, Stijn}, booktitle = {Lecture Notes in Computer Science: On the Move to Meaningful Internet Systems 2006: OTM 2006 Workshops}, file = {christiaens2006metadata.pdf:christiaens2006metadata.pdf:PDF}, groups = {public}, interhash = {f733d993459329ed1ef9f26d303ba0d9}, intrahash = {efc1396e845f3db1688dc8ef154d9520}, lastdatemodified = {2007-01-04}, lastname = {Christiaens}, own = {notown}, pdf = {christiaens06-metadata.pdf}, publisher = {Springer}, read = {notread}, timestamp = {2007-09-11 13:31:23}, title = {Metadata Mechanisms: From Ontology to Folksonomy ... and Back}, url = {http://www.springerlink.com/content/m370107220473394}, username = {dbenz}, workshoppub = {1}, year = 2006 } @article{raysonecember2008from, abstract = {This paper reports the extension of the key words method for the comparison of corpora. Using automatic tagging software that assigns part-of-speech and semantic field (domain) tags, a method is described which permits the extraction of key domains by applying the keyness calculation to tag frequency lists. The combination of the key words and key domains methods is shown to allow macroscopic analysis (the study of the characteristics of whole texts or varieties of language) to inform the microscopic level (focussing on the use of a particular linguistic feature) and thereby suggesting those linguistic features which should be investigated further. The resulting 'data-driven' approach presented here combines elements of both the 'corpus-based' and 'corpus-driven' paradigms in corpus linguistics. A web-based tool, Wmatrix, implementing the proposed method is applied in a case study: the comparison of UK 2001 general election manifestos of the Labour and Liberal Democratic parties.}, author = {Rayson, Paul}, doi = {10.1075/ijcl.13.4.06ray}, groups = {public}, interhash = {dff324bd5ca64c55a2e491e439a7b5c8}, intrahash = {753a948e9239f56f7d29b1d24bebb2a9}, journal = {International Journal of Corpus Linguistics}, journalpub = {1}, pages = {519-549(31)}, title = {From key words to key semantic domains}, url = {http://www.ingentaconnect.com/content/jbp/ijcl/2008/00000013/00000004/art00005}, username = {dbenz}, volume = 13, year = 2008 } @inproceedings{veres2006language, abstract = {Folksonomies are classification schemes that emerge from the collective actions of users who tag resources with an unrestricted set of key terms. There has been a flurry of activity in this domain recently with a number of high profile web sites and search engines adopting the practice. They have sparked a great deal of excitement and debate in the popular and technical literature, accompanied by a number of analyses of the statistical properties of tagging behavior. However, none has addressed the deep nature of folksonomies. What is the nature of a tag? Where does it come from? How is it related to a resource? In this paper we present a study in which the linguistic properties of folksonomies reveal them to contain, on the one hand, tags that are similar to standard categories in taxonomies. But on the other hand, they contain additional tags to describe class properties. The implications of the findings for the relationship between folksonomy and ontology are discussed.}, address = {Berlin / Heidelberg}, author = {Veres, Csaba}, booktitle = {Natural Language Processing and Information Systems}, file = {veres2006language.pdf:veres2006language.pdf:PDF}, groups = {public}, interhash = {1787dec43f3c11153fc9d2617af8829c}, intrahash = {617763caa416f98b398cd2b2f71338ee}, lastdatemodified = {2006-09-30}, lastname = {Veres}, month = {July}, own = {notown}, pages = {58-69}, pdf = {veres06-language.pdf}, publisher = {Springer}, read = {notread}, series = {Lecture Notes in Computer Science}, timestamp = {2007-09-11 13:31:39}, title = {The Language of Folksonomies: What Tags Reveal About User Classification.}, url = {http://dx.doi.org/10.1007/11765448_6}, username = {dbenz}, volume = {3999/2006}, year = 2006 } @article{golder2006structurec, abstract = {Collaborative tagging describes the process by which many users add metadata in the form of keywords to shared content. Recently, collaborative tagging has grown in popularity on the web, on sites that allow users to tag bookmarks, photographs and other content. In this paper we analyze the structure of collaborative tagging systems as well as their dynamical aspects. Specifically, we discovered regularities in user activity, tag frequencies, kinds of tags used, bursts of popularity in bookmarking and a remarkable stability in the relative proportions of tags within a given url. We also present a dynamical model of collaborative tagging that predicts these stable patterns and relates them to imitation and shared knowledge.}, author = {Golder, Scott and Huberman, Bernardo A.}, file = {golder2006structure.pdf:golder2006structure.pdf:PDF}, groups = {public}, interhash = {03565ad9c6fc315068e528a53ed158ae}, intrahash = {f26e96f09d59ba7d33d5339fa5d4891b}, journal = {Journal of Information Sciences}, journalpub = {1}, lastdatemodified = {2007-04-27}, lastname = {Golder}, month = {April}, number = 2, own = {own}, pages = {198--208}, pdf = {golder06-structure.pdf}, read = {readnext}, timestamp = {2011-01-28 11:35:13}, title = {The Structure of Collaborative Tagging Systems}, url = {http://.hpl.hp.com/research/idl/papers/tags/index.html}, username = {dbenz}, volume = 32, year = 2006 } @inproceedings{abel2008benefit, abstract = {With the advent of Web 2.0 folksonomy systems like Flickr, del.icio.us, etc. have become very popular. They enable users to annotate resources (images, websites, etc.) with freely chosen keywords, so-called tags. The evolving set of such tag assignments, which are generally user-tag-resource bindings, are called folksonomies. Folksonomies embody valuable information that can be exploited by search and ranking algorithms. In this paper we describe our ongoing research in analyzing the benefit of additional semantics in folksonomy systems. We present the GroupMe! folksonomy system, which brings additional semantics to tagging systems by enabling users to group resources. We furthermore introduce different group-sensitive ranking algorithms that outperform existing folksonomy ranking strategies and define SocialHITS - a HITS-based algorithm to detect hubs and authorities in folksonomy systems.}, address = {New York, NY, USA}, author = {Abel, Fabian}, booktitle = {PIKM '08: Proceeding of the 2nd PhD workshop on Information and knowledge management}, doi = {http://doi.acm.org/10.1145/1458550.1458560}, file = {abrams1997how.pdf:abrams1997how.pdf:PDF;abel2008benefit.pdf:abel2008benefit.pdf:PDF}, groups = {tagora}, interhash = {4a9d21e3405a26ab6c7e3c78f5eab98b}, intrahash = {0276b8f54393fcfd8b24cd2a1f67ccaa}, isbn = {978-1-60558-257-3}, location = {Napa Valley, California, USA}, pages = {49--56}, publisher = {ACM}, timestamp = {2010-01-18 20:11:55}, title = {The benefit of additional semantics in folksonomy systems}, url = {http://portal.acm.org/citation.cfm?id=1458560}, username = {dbenz}, year = 2008 } @inproceedings{ankolekar2007two, abstract = {A common perception is that there are two competing visions for the future evolution of the Web: the Semantic Web and Web 2.0. A closer look, though, reveals that the core technologies and concerns of these two approaches are complementary and that each field can and must draw from the other’s strengths. We believe that future web applications will retain the Web 2.0 focus on community and usability, while drawing on Semantic Web infrastructure to facilitate mashup-like information sharing. However, there are several open issues that must be addressed before such applications can become commonplace. In this paper, we outline a semantic weblogs scenario that illustrates the potential for combining Web 2.0 and Semantic Web technologies, while highlighting the unresolved issues that impede its realization. Nevertheless, we believe that the scenario can be realized in the short-term. We point to recent progress made in resolving each of the issues as well as future research directions for each of the communities.}, address = {New York, NY, USA}, author = {Ankolekar, Anupriya and Krötzsch, Markus and Tran, Thanh and Vrandecic, Denny}, booktitle = {WWW '07: Proceedings of the 16th international conference on World Wide Web}, doi = {http://doi.acm.org/10.1145/1242572.1242684}, file = {ankolekar2007two.pdf:ankolekar2007two.pdf:PDF}, groups = {public}, interhash = {1e51bd6cd043142a8de98b93e82b68b1}, intrahash = {6b493ae653fcff556997f30273d766b9}, isbn = {978-1-59593-654-7}, location = {Banff, Alberta, Canada}, pages = {825--834}, publisher = {ACM Press}, timestamp = {2007-08-05 16:27:33}, title = {The two cultures: mashing up web 2.0 and the semantic web}, url = {http://portal.acm.org/citation.cfm?id=1242684&coll=GUIDE&dl=ACM&CFID=21633871&CFTOKEN=81037701}, username = {dbenz}, year = 2007 } @article{berendt2010bridging, author = {Berendt, Bettina and Hotho, Andreas and Stumme, Gerd}, doi = {DOI: 10.1016/j.websem.2010.04.008}, groups = {public}, interhash = {4969eb2b7bf1fabe60c5f23ab6383d77}, intrahash = {f8d7bc2af5753906dc3897196daac18c}, issn = {1570-8268}, journal = {Web Semantics: Science, Services and Agents on the World Wide Web}, journalpub = {1}, note = {Bridging the Gap--Data Mining and Social Network Analysis for Integrating Semantic Web and Web 2.0; The Future of Knowledge Dissemination: The Elsevier Grand Challenge for the Life Sciences}, number = {2-3}, pages = {95 - 96}, timestamp = {2010-08-09 07:26:14}, title = {Bridging the Gap--Data Mining and Social Network Analysis for Integrating Semantic Web and Web 2.0}, url = {http://www.sciencedirect.com/science/article/B758F-4YXK4HW-1/2/4cb514565477c54160b5e6eb716c32d7}, username = {dbenz}, volume = 8, year = 2010 } @article{cattuto2006semiotic, abstract = {Abstract A distributed classification paradigm known as collaborative tagging has been successfully deployed in large-scale web applications designed to manage and share diverse online resources. Users of these applications organize resources by associating with them freely chosen text labels, or tags. Here we regard tags as basic dynamical entities and study the semiotic dynamics underlying collaborative tagging. We collect data from a popular system and focus on tags associated with a given resource. We find that the frequencies of tags obey to a generalized Zipf�s law and show that a Yule�Simon process with memory can be used to explain the observed frequency distributions in terms of a simple model of user behavior}, author = {Cattuto, Ciro}, file = {cattuto2006semiotic.pdf:cattuto2006semiotic.pdf:PDF}, groups = {public}, interhash = {6651fe8b8916e8407f738325c092b860}, intrahash = {df2a1161a75e3f328f82c204f942bb8a}, journal = {The European Physical Journal C - Particles and Fields}, journalpub = {1}, lastdatemodified = {2006-09-25}, lastname = {Cattuto}, longnotes = {doi:10.1140/epjcd/s2006-03-004-4}, month = {August}, own = {notown}, pages = {33--37}, pdf = {cattuto2006-semiotic.pdf}, read = {notread}, timestamp = {2007-09-11 13:31:22}, title = {Semiotic dynamics in online social communities}, url = {http://www.springerlink.com/content/t964j63030507341}, username = {dbenz}, volume = 46, year = 2006 } @article{cattuto2007semiotic, abstract = {Collaborative tagging has been quickly gaining ground because of its ability to recruit the activity of web users into effectively organizing and sharing vast amounts of information. Here we collect data from a popular system and investigate the statistical properties of tag co-occurrence. We introduce a stochastic model of user behavior embodying two main aspects of collaborative tagging: (i) a frequency-bias mechanism related to the idea that users are exposed to each other's tagging activity; (ii) a notion of memory - or aging of resources - in the form of a heavy-tailed access to the past state of the system. Remarkably, our simple modeling is able to account quantitatively for the observed experimental features, with a surprisingly high accuracy. This points in the direction of a universal behavior of users, who - despite the complexity of their own cognitive processes and the uncoordinated and selfish nature of their tagging activity - appear to follow simple activity patterns.}, author = {Cattuto, Ciro and Loreto, Vittorio and Pietronero, Luciano}, file = {cattuto2007semiotic.pdf:cattuto2007semiotic.pdf:PDF}, groups = {public}, interhash = {189402152f540f931a0eea5b8538411f}, intrahash = {95a8e6a348e0acde9ce781004c45b94e}, journal = {Proceedings of the National Academy of Sciences United States of America}, journalpub = {1}, lastdatemodified = {2007-05-14}, lastname = {Cattuto}, own = {notown}, pages = 1461, pdf = {cattuto06-collaborative.pdf}, read = {notread}, timestamp = {2007-09-11 13:31:22}, title = {Semiotic Dynamics and Collaborative Tagging}, url = {http://www.citebase.org/abstract?id=oai:arXiv.org:cs/0605015}, username = {dbenz}, volume = 104, year = 2007 } @inproceedings{liu2008between, abstract = {We present our first user study of CRAFT, a semantic prototype for collaborative investigation and analysis, which allows users to extend the system's ontology to capture new concepts as they conduct their work. We devised a paradigm in which multiple series of ontologies evolve in different trajectories from the same initial point. We analyze the ontology evolution quantitatively with several metrics, and user behavior qualitatively through interviews and observation. Based on our study, we propose a set of design suggestions for semantic applications with collaborative and implicit ontology development.}, address = {New York, NY, USA}, author = {Liu, Jiahui and Gruen, Daniel M.}, booktitle = {IUI '08: Proceedings of the 13th international conference on Intelligent user interfaces}, doi = {http://doi.acm.org/10.1145/1378773.1378830}, file = {liu2008between.pdf:liu2008between.pdf:PDF}, groups = {public}, interhash = {45e8362f274501ec6b2a81e2693b405e}, intrahash = {8c92fc47200127eeb84f2964a3d1b528}, isbn = {978-1-59593-987-6}, location = {Gran Canaria, Spain}, pages = {361--364}, publisher = {ACM}, timestamp = {2010-01-18 20:13:25}, title = {Between ontology and folksonomy: a study of collaborative and implicit ontology evolution}, url = {http://portal.acm.org/citation.cfm?id=1378830}, username = {dbenz}, year = 2008 } @article{lux2008from, abstract = {Is Web 2.0 just hype or just a buzzword, which might disappear in the near future One way to find answers to these questions is to investigate the actual benefit of the Web 2.0 for real use cases. Within this contribution we study a very special aspect of the Web 2.0 the folksonomy and its use within self-directed learning. Guided by conceptual principles of emergent computing we point out methods, which might be able to let semantics emerge from folksonomies and discuss the effect of the results in self-directed learning.}, author = {Lux, Mathias and Dösinger, Gisela}, doi = {10.1504/IJKL.2007.016709}, groups = {public}, interhash = {5dde7a91231320f96c0c4b3e7ba9a503}, intrahash = {dd5cdcc6449d97622033bbebcd4d1874}, journal = {International Journal of Knowledge and Learning}, journalpub = {1}, month = jan, number = {4-5}, pages = {515--528}, timestamp = {2010-08-11 07:26:38}, title = {From folksonomies to ontologies: employing wisdom of the crowds to serve learning purposes}, url = {http://www.ingentaconnect.com/content/ind/ijkl/2008/00000003/F0020004/art00009}, username = {dbenz}, volume = 3, year = 2008 } @inproceedings{marlow2006position, abstract = {In recent years, tagging systems have become increasingly popular. These systems enable users to add keywords (i.e., �tags�) to Internet resources (e.g., web pages, images, videos) without relying on a controlled vocabulary. Tagging systems have the potential to improve search, spam detection, reputation systems, and personal organization while introducing new modalities of social communication and opportunities for data mining. This potential is largely due to the social structure that underlies many of the current systems. Despite the rapid expansion of applications that support tagging of resources, tagging systems are still not well studied or understood. In this paper, we provide a short description of the academic related work to date. We offer a model of tagging systems, specifically in the context of web-based systems, to help us illustrate the possible benefits of these tools. Since many such systems already exist, we provide a taxonomy of tagging systems to help inform their analysis and design, and thus enable researchers to frame and compare evidence for the sustainability of such systems. We also provide a simple taxonomy of incentives and contribution models to inform potential evaluative frameworks. While this work does not present comprehensive empirical results, we present a preliminary study of the photosharing and tagging system Flickr to demonstrate our model and explore some of the issues in one sample system. This analysis helps us outline and motivate possible future directions of research in tagging systems.}, address = {Edinburgh, Scotland}, author = {Marlow, Cameron and Naaman, Mor and Boyd, Danah and Davis, Marc}, booktitle = {Proceedings of the Collaborative Web Tagging Workshop at the WWW 2006}, file = {marlow2006position.pdf:marlow2006position.pdf:PDF}, groups = {public}, interhash = {7446351e0d902ee4f36fb750f82c50a5}, intrahash = {d9f433de0945351fa2157c1424d9fe67}, lastdatemodified = {2006-07-17}, lastname = {Marlow}, month = May, own = {own}, pdf = {marlow06-tagging.pdf}, read = {readnext}, timestamp = {2007-09-11 13:31:31}, title = {{Position Paper, Tagging, Taxonomy, Flickr, Article, ToRead}}, url = {http://.rawsugar.com/www2006/cfp.html}, username = {dbenz}, year = 2006 } @inproceedings{veres2006concept, abstract = {The recent popularity of social software in the wake of the much hyped "Web2.0" has resulted in a flurry of activity around folksonomies, the emergent systems of classification that result from making public the individual users’ personal classifications in the form of simple free form "tags". Several approaches have emerged in the analysis of these folksonomies including mathematical approaches for clustering and identifying affinities, social theories about cultural factors in tagging, and cognitive theories about their mental underpinnings. In this paper we argue that the most useful analysis is in terms of mental phenomena since naive classification is essentially a cognitive task. We then describe a method for extracting structural properties of free form user tags, based on the linguistic properties of the tags. This reveals some deep insights in the conceptual modeling behavior of naive users. Finally we explore the usefulness of the latent structural properties of free form "tag clouds" for interoperability between folksonomies from different services.}, author = {Veres, C.}, booktitle = {Conceptual Modeling - ER 2006}, file = {veres2006concept.pdf:veres2006concept.pdf:PDF}, groups = {public}, interhash = {ce1a0dcac78702811f22fe3dc41bc46e}, intrahash = {13540d1afb327c09e9c894a011b6450a}, lastdatemodified = {2007-01-08}, lastname = {Veres}, own = {notown}, pages = {325--338}, pdf = {veres06-concept.pdf}, read = {notread}, timestamp = {2009-09-02 13:26:48}, title = {Concept Modeling by the Masses: Folksonomy Structure and Interoperability}, url = {http://dx.doi.org/10.1007/11901181_25}, username = {dbenz}, year = 2006 } @inproceedings{wu2006harvesting, abstract = {Collaborative tagging systems, or folksonomies, have the potential of becoming technological infrastructure to support knowledge management activities in an organization or a society. There are many challenges, however. This paper presents designs that enhance collaborative tagging systems to meet some key challenges: community identification, ontology generation, user and document recommendation. Design prototypes, evaluation methodology and selected preliminary results are presented.}, address = {New York, NY, USA}, author = {Wu, Harris and Zubair, Mohammad and Maly, Kurt}, booktitle = {HYPERTEXT '06: Proceedings of the seventeenth conference on Hypertext and hypermedia}, file = {wu2006harvesting.pdf:wu2006harvesting.pdf:PDF}, groups = {public}, interhash = {ea6aa5db3724812d08347d5a8309bea4}, intrahash = {b5bfeb993316b0021084d5ac197bf5ca}, lastdatemodified = {2006-09-25}, lastname = {Wu}, own = {notown}, pages = {111--114}, pdf = {wu06-harvesting.pdf}, publisher = {ACM Press}, read = {notread}, timestamp = {2007-09-11 13:31:41}, title = {Harvesting social knowledge from folksonomies}, url = {http://portal.acm.org/citation.cfm?id=1149941.1149962}, username = {dbenz}, year = 2006 } @article{cattuto2007network, abstract = {Social resource sharing systems like YouTube and del.icio.us have acquired a large number of users within the last few years. They provide rich resources for data analysis, information retrieval, and knowledge discovery applications. A first step towards this end is to gain better insights into content and structure of these systems. In this paper, we will analyse the main network characteristics of two of these systems. We consider their underlying data structures - so-called folksonomies - as tri-partite hypergraphs, and adapt classical network measures like characteristic path length and clustering coefficient to them.Subsequently, we introduce a network of tag co-occurrence and investigate some of its statistical properties, focusing on correlations in node connectivity and pointing out features that reflect emergent semantics within the folksonomy. We show that simple statistical indicators unambiguously spot non-social behavior such as spam.}, address = {Amsterdam, The Netherlands}, author = {Cattuto, Ciro and Schmitz, Christoph and Baldassarri, Andrea and Servedio, Vito D. P. and Loreto, Vittorio and Hotho, Andreas and Grahl, Miranda and Stumme, Gerd}, file = {cattuto2007network.pdf:cattuto2007network.pdf:PDF}, groups = {public}, interhash = {fc5f2df61d28bc99b7e15029da125588}, intrahash = {1dfe8b2aa29adf4929cbb845950f78bc}, issn = {0921-7126}, journal = {AI Communications}, journalpub = {1}, month = dec, number = 4, pages = {245--262}, publisher = {IOS Press}, timestamp = {2010-11-10 15:35:25}, title = {Network properties of folksonomies}, url = {http://portal.acm.org/citation.cfm?id=1365538}, username = {dbenz}, volume = 20, year = 2007 } @inproceedings{halpin2006dynamics, abstract = {The debate within the Web community over the optimal means by which to organize information often pits formalized classifications against distributed collaborative tagging systems. A number of questions remain unanswered, however, regarding the nature of collaborative tagging systems including the dynamics of such systems and whether coherent classification schemes can emerge from undirected tagging by users. Currently millions of users are using collaborative tagging without centrally organizing principles, and many suspect this exhibits features considered to be indicative of a complex system. If this is the case, it remains to be seem whether collaborative tagging by users over time leads to emergent classi- fication schemes that could be formalized into an ontology usable by the Semantic Web. This paper uses data from �popular� tagged sites on the social bookmarking site del.icio.us to examine the dynamics of such collaborative tagging systems. In particular, we are trying to determine whether the distribution of tag frequencies stabilizes, which indicates a degree of cohesion or consensus among users about the optimal tags to describe particular sites. We use tag co-occurrence networks for a sample domain of tags to analyze the meaning of particular tags given their relationship to other tags and automatically create an ontology. We also produce a generative model of collaborative tagging in order to model and understand some of the basic dynamics behind the process.}, author = {Halpin, Harry and Robu, Valentin and Shepard, Hana}, booktitle = {Proceedings of the 1st Semantic Authoring and Annotation Workshop (SAAW'06)}, file = {halpin2006dynamics.pdf:halpin2006dynamics.pdf:PDF}, groups = {public}, interhash = {86b08d03b5f0bd947fd9095dc2c9a70c}, intrahash = {266b31ad3599499aacf593e82e775c5b}, lastdatemodified = {2007-01-04}, lastname = {Halpin}, own = {notown}, pdf = {halpin06-dynamics.pdf}, read = {notread}, timestamp = {2007-05-25 16:05:53}, title = {The Dynamics and Semantics of Collaborative Tagging}, username = {dbenz}, year = 2006 } @article{maedche2005ontology, abstract = {he Semantic Web relies heavily on formal ontologies to structure data for comprehensive and transportable machine understanding. Thus, the proliferation of ontologies factors largely in the Semantic Web’s success. Ontology learning greatly helps ontology engineers construct ontologies. The vision of ontology learning that we propose includes a number of complementary disciplines that feed on different types of unstructured, semistructured, and fully structured data to support semiautomatic, cooperative ontology engineering. Our ontology- learning framework proceeds through ontology import, extraction, pruning, refinement, and evaluation, giving the ontology engineer coordinated tools for ontology modeling. Besides the general framework and architecture, this article discusses techniques in the ontology-learning cycle that we implemented in our ontology-learning environment, such as ontology learning from free text, dictionaries, and legacy ontologies. We also refer to other techniques for future implementation, such as reverse engineering of ontologies from database schemata or learning from XML documents.}, author = {Maedche, A. and Staab, S.}, file = {maedche2005ontology.pdf:maedche2005ontology.pdf:PDF}, groups = {public}, interhash = {77b7223b737581bba0f4819b1de46b73}, intrahash = {29f44c4032ba381ec36fb5d0f36a1955}, issn = {1541-1672}, journal = {Intelligent Systems, IEEE}, journalpub = {1}, number = 2, pages = {72--79}, publisher = {IEEE}, timestamp = {2010-11-10 10:43:24}, title = {Ontology learning for the semantic web}, url = {http://scholar.google.de/scholar.bib?q=info:4sWpt0uwOjkJ:scholar.google.com/&output=citation&hl=de&as_sdt=2000&ct=citation&cd=0}, username = {dbenz}, volume = 16, year = 2005 } @incollection{rudolph2007supporting, abstract = {Designing and refining ontologies becomes a tedious task, once the boundary to real-world-size knowledge bases has been crossed. Hence semi-automatic methods supporting those tasks will determine the future success of ontologies in practice. In this paper we describe a way for ontology creation and refinement by combining techniques from natural language processing (NLP) and formal concept analysis (FCA). We point out how synergy between those two fields can be established thereby overcoming each other’s shortcomings.}, address = {Berlin / Heidelberg}, affiliation = {Institute AIFB, Universität Karlsruhe Germany}, author = {Rudolph, Sebastian and Völker, Johanna and Hitzler, Pascal}, booktitle = {Conceptual Structures: Knowledge Architectures for Smart Applications}, doi = {10.1007/978-3-540-73681-3_41}, editor = {Priss, Uta and Polovina, Simon and Hill, Richard}, file = {rudolph2007supporting.pdf:rudolph2007supporting.pdf:PDF}, groups = {public}, interhash = {95939c2e69ef57fcf65e93df6010fe60}, intrahash = {582e9add98a452d5cc6d4d0788d6e6d9}, pages = {488-491}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, timestamp = {2010-11-10 11:28:57}, title = {Supporting Lexical Ontology Learning by Relational Exploration}, url = {http://dx.doi.org/10.1007/978-3-540-73681-3_41}, username = {dbenz}, volume = 4604, year = 2007 } @article{sanchez2009domain, abstract = {Ontology Learning is defined as the set of methods used for building from scratch, enriching or adapting an existing ontology in a semi-automatic fashion using heterogeneous information sources. This data-driven procedure uses text, electronic dictionaries, linguistic ontologies and structured and semi-structured information to acquire knowledge. Recently, with the enormous growth of the Information Society, the Web has become a valuable source of information for almost every possible domain of knowledge. This has motivated researchers to start considering the Web as a valid repository for Information Retrieval and Knowledge Acquisition. However, the Web suffers from problems that are not typically observed in classical information repositories: human oriented presentation, noise, untrusted sources, high dynamicity and overwhelming size. Even though, it also presents characteristics that can be interesting for knowledge acquisition: due to its huge size and heterogeneity it has been assumed that the Web approximates the real distribution of the information in humankind. The present work introduces a novel approach for ontology learning, introducing new methods for knowledge acquisition from the Web. The adaptation of several well known learning techniques to the web corpus and the exploitation of particular characteristics of the Web environment composing an automatic, unsupervised and domain independent approach distinguishes the present proposal from previous works. With respect to the ontology building process, the following methods have been developed: i) extraction and selection of domain related terms, organising them in a taxonomical way; ii) discovery and label of non-taxonomical relationships between concepts; iii) additional methods for improving the final structure, including the detection of named entities, class features, multiple inheritance and also a certain degree of semantic disambiguation. The full learning methodology has been implemented in a distributed agent-based fashion, providing a scalable solution. It has been evaluated for several well distinguished domains of knowledge, obtaining good quality results. Finally, several direct applications have been developed, including automatic structuring of digital libraries and web resources, and ontology-based Web Information Retrieval.}, author = {S{\'a}nchez, D.}, file = {sanchez2009domain.pdf:sanchez2009domain.pdf:PDF}, groups = {public}, interhash = {958a2cf02d6bdad93c5a61fd952385e6}, intrahash = {1d6ef9dbccf2f21c8395427fefa8a8a9}, issn = {0269-8889}, journal = {The Knowledge Engineering Review}, journalpub = {1}, number = 04, pages = {413--413}, publisher = {Cambridge Univ Press}, timestamp = {2010-11-10 11:09:12}, title = {Domain ontology learning from the web}, url = {http://scholar.google.de/scholar.bib?q=info:1b5eMmkxoXoJ:scholar.google.com/&output=citation&hl=de&as_sdt=2000&ct=citation&cd=45}, username = {dbenz}, volume = 24, year = 2009 }