@inproceedings{zhou2008unsupervised, abstract = {This paper deals with the problem of exploring hierarchical semantics from social annotations. Recently, social annotationservices have become more and more popular in Semantic Web. It allows users to arbitrarily annotate web resources, thus, largelylowers the barrier to cooperation. Furthermore, through providing abundant meta-data resources, social annotation might becomea key to the development of Semantic Web. However, on the other hand, social annotation has its own apparent limitations,for instance, 1) ambiguity and synonym phenomena and 2) lack of hierarchical information. In this paper, we propose an unsupervisedmodel to automatically derive hierarchical semantics from social annotations. Using a social bookmark service Del.icio.usas example, we demonstrate that the derived hierarchical semantics has the ability to compensate those shortcomings. We furtherapply our model on another data set from Flickr to testify our model’s applicability on different environments. The experimentalresults demonstrate our model’s efficiency.}, author = {Zhou, Mianwei and Bao, Shenghua and Wu, Xian and Yu, Yong}, file = {zhou2008unsupervised.pdf:zhou2008unsupervised.pdf:PDF}, groups = {public}, interhash = {e8397fd51d43531b91e81776c879f487}, intrahash = {ee6da1cc1300cf4fb68fc58d5e2bb819}, journal = {The Semantic Web}, pages = {680--693}, timestamp = {2009-09-24 23:27:32}, title = {An Unsupervised Model for Exploring Hierarchical Semantics from Social Annotations}, url = {http://dx.doi.org/10.1007/978-3-540-76298-0_49}, username = {dbenz}, year = 2008 } @article{ryu2009toward, abstract = {This paper describes new thesaurus construction method in which class-based, small size thesauruses are constructed and merged as a whole based on domain classification system. This method has advantages in that 1) taxonomy construction complexity is reduced, 2) each class-based thesaurus can be reused in other domain thesaurus, and 3) term distribution per classes in target domain is easily identified. The method is composed of three steps: term extraction step, term classification step, and taxonomy construction step. All steps are balanced approaches of automatic processing and manual verification. We constructed Korean IT domain thesaurus based on proposed method. Because terms are extracted from Korean newspaper and patent corpus in IT domain, the thesaurus includes many Korean neologisms. The thesaurus consists of 81 upper level classes and over 1,000 IT terms.}, author = {Ryu, P.M. and Kim, J.H. and Nam, Y. and Huang, J.X. and Shin, S. and Lee, S.M. and Choi, K.S.}, file = {ryu2009toward.pdf:ryu2009toward.pdf:PDF}, groups = {public}, interhash = {33037e9884a62f1994c9d45eb68c27e7}, intrahash = {bd4f375366e49a3eb31e60b268dca01c}, journal = {Relation}, journalpub = {1}, number = {1.129}, pages = 7396, publisher = {Citeseer}, timestamp = {2010-11-09 12:05:09}, title = {{Toward Domain Specific Thesaurus Construction: Divide-and-Conquer Method}}, url = {http://scholar.google.de/scholar.bib?q=info:4K_xIsqmea0J:scholar.google.com/&output=citation&hl=de&as_sdt=2000&ct=citation&cd=9}, username = {dbenz}, volume = 10, year = 2009 } @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 } @article{zhou2008unsupervised, abstract = {This paper deals with the problem of exploring hierarchical semantics from social annotations. Recently, social annotationservices have become more and more popular in Semantic Web. It allows users to arbitrarily annotate web resources, thus, largelylowers the barrier to cooperation. Furthermore, through providing abundant meta-data resources, social annotation might becomea key to the development of Semantic Web. However, on the other hand, social annotation has its own apparent limitations,for instance, 1) ambiguity and synonym phenomena and 2) lack of hierarchical information. In this paper, we propose an unsupervisedmodel to automatically derive hierarchical semantics from social annotations. Using a social bookmark service Del.icio.usas example, we demonstrate that the derived hierarchical semantics has the ability to compensate those shortcomings. We furtherapply our model on another data set from Flickr to testify our model’s applicability on different environments. The experimentalresults demonstrate our model’s efficiency.}, author = {Zhou, Mianwei and Bao, Shenghua and Wu, Xian and Yu, Yong}, file = {zhou2008unsupervised.pdf:zhou2008unsupervised.pdf:PDF}, interhash = {e8397fd51d43531b91e81776c879f487}, intrahash = {ee6da1cc1300cf4fb68fc58d5e2bb819}, journal = {The Semantic Web}, pages = {680--693}, title = {An Unsupervised Model for Exploring Hierarchical Semantics from Social Annotations}, url = {http://dx.doi.org/10.1007/978-3-540-76298-0_49}, year = 2008 } @article{cimiano2006ontologies, abstract = {Ontologies are nowadays used for many applications requiring data, services and resources in general to be interoperable and machine understandable. Such applications are for example web service discovery and composition, information integration across databases, intelligent search, etc. The general idea is that data and services are semantically described with respect to ontologies,which are formal specifications of a domain of interest, and can thus be shared and reused in a way such that the shared meaning specified by the ontology remains formally the same across different parties and applications. As the cost of creating ontologies is relatively high, different proposals have emerged for learning ontologies from structured and unstructured resources. In this article we examine the maturity of techniques for ontology learning from textual resources, addressing the question whether the state-of-the-art is mature enough to produce ontologies ‘on demand’.}, author = {Cimiano, Philipp and Völker, Johanna and Studer, Rudi}, file = {cimiano2006ontologies.pdf:cimiano2006ontologies.pdf:PDF}, groups = {public}, interhash = {aeb553dc2e190f0a5974dfdc709d450a}, intrahash = {fe4c2950b5be221b493e29e4339240e8}, journal = {Information, Wissenschaft und Praxis}, journalpub = {1}, month = OCT, note = {see the special issue for more contributions related to the Semantic Web}, number = {6-7}, pages = {315-320}, timestamp = {2008-07-23 11:47:29}, 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}}, username = {dbenz}, volume = 57, year = 2006 } @inproceedings{marinho2008folksonomybased, abstract = {The growing popularity of social tagging systems promises to alleviate the knowledge bottleneck that slows down the full materialization of the SemanticWeb since these systems allow ordinary users to create and share knowledge in a simple, cheap, and scalable representation, usually known as folksonomy. However, for the sake of knowledge workflow, one needs to find a compromise between the uncontrolled nature of folksonomies and the controlled and more systematic vocabulary of domain experts. In this paper we propose to address this concern by devising a method that automatically enriches a folksonomy with domain expert knowledge and by introducing a novel algorithm based on frequent itemset mining techniques to efficiently learn an ontology over the enriched folksonomy. In order to quantitatively assess our method, we propose a new benchmark for task-based ontology evaluation where the quality of the ontologies is measured based on how helpful they are for the task of personalized information finding. We conduct experiments on real data and empirically show the effectiveness of our approach.}, author = {Marinho, Leandro Balby and Buza, Krisztian and Schmidt-Thieme, Lars}, booktitle = {International Semantic Web Conference}, crossref = {conf/semweb/2008}, date = {2008-10-24}, editor = {Sheth, Amit P. and Staab, Steffen and Dean, Mike and Paolucci, Massimo and Maynard, Diana and Finin, Timothy W. and Thirunarayan, Krishnaprasad}, ee = {http://dx.doi.org/10.1007/978-3-540-88564-1_17}, file = {marinho2008folksonomybased.pdf:marinho2008folksonomybased.pdf:PDF}, groups = {public}, interhash = {d295e7d4615500c670e70ad240fada29}, intrahash = {cfa4c4520d4cf02e03dd3b84bb5c9578}, isbn = {978-3-540-88563-4}, pages = {261-276}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, timestamp = {2010-03-30 16:14:58}, title = {Folksonomy-Based Collabulary Learning.}, url = {http://dblp.uni-trier.de/db/conf/semweb/iswc2008.html#MarinhoBS08}, username = {dbenz}, volume = 5318, year = 2008 } @inproceedings{rattenbury2007towards, abstract = {We describe an approach for extracting semantics of tags, unstructured text-labels assigned to resources on the Web, based on each tag's usage patterns. In particular, we focus on the problem of extracting place and event semantics for tags that are assigned to photos on Flickr, a popular photo sharing website that supports time and location (latitude/longitude) metadata. We analyze two methods inspired by well-known burst-analysis techniques and one novel method: Scale-structure Identification. We evaluate the methods on a subset of Flickr data, and show that our Scale-structure Identification method outperforms the existing techniques. The approach and methods described in this work can be used in other domains such as geo-annotated web pages, where text terms can be extracted and associated with usage patterns.}, address = {New York, NY, USA}, author = {Rattenbury, Tye and Good, Nathaniel and Naaman, Mor}, booktitle = {SIGIR '07: Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval}, doi = {10.1145/1277741.1277762}, file = {rattenbury2007towards.pdf:rattenbury2007towards.pdf:PDF}, groups = {public}, interhash = {8b02d2b3fdbb97c3db6e3b23079a56e5}, intrahash = {bf6f73d2ef74ca6f1d355fb5688b673c}, isbn = {978-1-59593-597-7}, pages = {103--110}, publisher = {ACM Press}, timestamp = {2010-11-10 15:35:25}, title = {Towards automatic extraction of event and place semantics from flickr tags}, url = {http://dx.doi.org/10.1145/1277741.1277762}, username = {dbenz}, year = 2007 } @inproceedings{silva2009semiautomatic, abstract = {This paper introduces WikiOnto: a system that assists in the extraction and modeling of topic ontologies in a semi-automatic manner using a preprocessed document corpus derived from Wikipedia. Based on the Wikipedia XML Corpus, we present a three-tiered framework for extracting topic ontologies in quick time and a modeling environment to refine these ontologies. Using natural language processing (NLP) and other machine learning (ML) techniques along with a very rich document corpus, this system proposes a solution to a task that is generally considered extremely cumbersome. The initial results of the prototype suggest strong potential of the system to become highly successful in ontology extraction and modeling and also inspire further research on extracting ontologies from other semi-structured document corpora as well.}, author = {Silva, L. De and Jayaratne, L.}, booktitle = {Applications of Digital Information and Web Technologies, 2009. ICADIWT '09. Second International Conference on the}, doi = {10.1109/ICADIWT.2009.5273871}, file = {silva2009semiautomatic.pdf:silva2009semiautomatic.pdf:PDF}, groups = {public}, interhash = {c1996cb9e69de56e2bb2f8e763fe0482}, intrahash = {66bec053541e521fbe68c0119806ae49}, month = {Aug.}, pages = {446-451}, timestamp = {2010-02-23 12:54:40}, title = {Semi-automatic extraction and modeling of ontologies using Wikipedia XML Corpus}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?isnumber=5273826&arnumber=5273871&count=156&index=116}, username = {dbenz}, year = 2009 } @inproceedings{tane2003courseware, abstract = {Topics in education are changing with an ever faster pace. E-Learningresources tend to be more and more decentralised. Users need increasingly to be able touse the resources of the web. For this, they should have tools for finding and organizinginformation in a decentral way. In this, paper, we show how an ontology-based toolsuite allows to make the most of the resources available on the web.}, author = {Tane, Julien and Schmitz, Christoph and Stumme, Gerd and Staab, Steffen and Studer, R.}, booktitle = {Mobiles Lernen und Forschen - Beiträge der Fachtagung an der Universität}, editor = {David, Klaus and Wegner, Lutz}, file = {tane2003courseware.pdf:tane2003courseware.pdf:PDF}, groups = {public}, interhash = {7f33080bb78d089b24bf51c059f8f018}, intrahash = {850949481723b7dd03768ccd96b25cb9}, month = {November}, pages = {93-104}, publisher = {Kassel University Press}, timestamp = {2010-11-10 15:35:25}, title = {The Courseware Watchdog: an Ontology-based tool for finding and organizing learning material}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2003/tane2003courseware.pdf}, username = {dbenz}, year = 2003 } @inproceedings{wu2009learning, 0 = {http://portal.acm.org/citation.cfm?id=1526709.1526758}, 1 = {http://dx.doi.org/10.1145/1526709.1526758}, abstract = {Social tagging provides valuable and crucial information for large-scale web image retrieval. It is ontology-free and easy to obtain; however, irrelevant tags frequently appear, and users typically will not tag all semantic objects in the image, which is also called semantic loss. To avoid noises and compensate for the semantic loss, tag recommendation is proposed in literature. However, current recommendation simply ranks the related tags based on the single modality of tag co-occurrence on the whole dataset, which ignores other modalities, such as visual correlation. This paper proposes a multi-modality recommendation based on both tag and visual correlation, and formulates the tag recommendation as a learning problem. Each modality is used to generate a ranking feature, and Rankboost algorithm is applied to learn an optimal combination of these ranking features from different modalities. Experiments on Flickr data demonstrate the effectiveness of this learning-based multi-modality recommendation strategy.}, address = {New York, NY, USA}, at = {2009-04-23 17:01:03}, author = {Wu, Lei and Yang, Linjun and Yu, Nenghai and Hua, Xian S.}, booktitle = {WWW '09: Proceedings of the 18th international conference on World wide web}, doi = {10.1145/1526709.1526758}, file = {wu2009learning.pdf:wu2009learning.pdf:PDF}, groups = {public}, interhash = {8389ee83e70d619168c6e52bf499742d}, intrahash = {e58e20189ca9601b33007479478fbefe}, isbn = {978-1-60558-487-4}, location = {Madrid, Spain}, misc_id = {4387938}, pages = {361--370}, priority = {0}, publisher = {ACM}, timestamp = {2011-02-02 15:26:27}, title = {Learning to tag}, url = {http://dx.doi.org/10.1145/1526709.1526758}, username = {dbenz}, year = 2009 }