@misc{turney2010frequency, abstract = { Computers understand very little of the meaning of human language. This profoundly limits our ability to give instructions to computers, the ability of computers to explain their actions to us, and the ability of computers to analyse and process text. Vector space models (VSMs) of semantics are beginning to address these limits. This paper surveys the use of VSMs for semantic processing of text. We organize the literature on VSMs according to the structure of the matrix in a VSM. There are currently three broad classes of VSMs, based on term-document, word-context, and pair-pattern matrices, yielding three classes of applications. We survey a broad range of applications in these three categories and we take a detailed look at a specific open source project in each category. Our goal in this survey is to show the breadth of applications of VSMs for semantics, to provide a new perspective on VSMs for those who are already familiar with the area, and to provide pointers into the literature for those who are less familiar with the field. }, author = {Turney, Peter D. and Pantel, Patrick}, interhash = {397ead0766aba687b471395729a263d1}, intrahash = {917bb6b225b8c844b1a15b6577b3845b}, note = {cite arxiv:1003.1141}, title = {From Frequency to Meaning: Vector Space Models of Semantics}, url = {http://arxiv.org/abs/1003.1141}, year = 2010 } @inproceedings{trabelsi2010bridging, abstract = {Social book marking tools are rapidly emerging on the Web as it can be witnessed by the overwhelming number of participants. In such spaces, users annotate resources by means of any keyword or tag that they find relevant, giving raise to lightweight conceptual structures \emph{aka} folksonomies. In this respect, needless to mention that ontologies can be of benefit for enhancing information retrieval metrics. In this paper, we introduce a novel approach for ontology learning from a \textit{folksonomy}, which provide shared vocabularies and semantic relations between tags. The main thrust of the introduced approach stands in putting the focus on the discovery of \textit{non-taxonomic} relationships. The latter are often neglected, even though they are of paramount importance from a semantic point of view. The discovery process heavily relies on triadic concepts to discover and select related tags and to extract and label non-taxonomically relationships between related tags and external sources for tags filtering and non-taxonomic relationships extraction. In addition, we also discuss a new approach to evaluate obtained relations in an automatic way against WordNet repository and presents promising results for a real world \textit{folksonomy}.}, acmid = {1934438}, address = {Washington, DC, USA}, author = {Trabelsi, Chiraz and Jrad, Aicha Ben and Yahia, Sadok Ben}, booktitle = {Proceedings of the 2010 IEEE International Conference on Data Mining Workshops}, doi = {10.1109/ICDMW.2010.72}, interhash = {4f2f573b32d29f76b348ee18d49c9ec4}, intrahash = {26c469e5c064f050f35e4448d0224886}, isbn = {978-0-7695-4257-7}, numpages = {11}, pages = {369--379}, publisher = {IEEE Computer Society}, series = {ICDMW '10}, title = {Bridging Folksonomies and Domain Ontologies: Getting Out Non-taxonomic Relations}, url = {http://dx.doi.org/10.1109/ICDMW.2010.72}, year = 2010 } @inproceedings{suchanek2008social, abstract = {This paper aims to quantify two common assumptions about social tagging: (1) that tags are "meaningful" and (2) that the tagging process is influenced by tag suggestions. For (1), we analyze the semantic properties of tags and the relationship between the tags and the content of the tagged page. Our analysis is based on a corpus of search keywords, contents, titles, and tags applied to several thousand popular Web pages. Among other results, we find that the more popular tags of a page tend to be the more meaningful ones. For (2), we develop a model of how the influence of tag suggestions can be measured. From a user study with over 4,000 participants, we conclude that roughly one third of the tag applications may be induced by the suggestions. Our results would be of interest for designers of social tagging systems and are a step towards understanding how to best leverage social tags for applications such as search and information extraction.}, acmid = {1458114}, address = {New York, NY, USA}, author = {Suchanek, Fabian M. and Vojnovic, Milan and Gunawardena, Dinan}, booktitle = {Proceeding of the 17th ACM conference on Information and knowledge management}, doi = {10.1145/1458082.1458114}, interhash = {1bca5a66a6a562258e0c0357545fed34}, intrahash = {ff31cf8541004adc7cd712ed715706b3}, isbn = {978-1-59593-991-3}, location = {Napa Valley, California, USA}, numpages = {10}, pages = {223--232}, publisher = {ACM}, series = {CIKM '08}, title = {Social tags: meaning and suggestions}, url = {http://doi.acm.org/10.1145/1458082.1458114}, year = 2008 } @inproceedings{kipp2006exploring, abstract = {This paper examines the results of a study of the three groups involved in creating index keywords or tags: users, authors and intermediaries. Keywords from each of the three groups were compared to determine similarities and differences in term use. Comparisons suggested that there were important differences in the contexts of the three groups that should be taken into account when assigning keywords or designing systems for the organisation of information.}, author = {Kipp, Margaret E. I.}, booktitle = {ASIS\&T 2006 Information Architecture Summit}, citeulike-article-id = {581353}, citeulike-linkout-0 = {http://iasummit.org/2006/conferencedescrip.htm\#109}, interhash = {cc95302ec99e70ffae810ee377ae98e6}, intrahash = {904d826cdf2349f8b6ec802eddd6d0c4}, month = mar, posted-at = {2006-04-11 03:32:13}, priority = {3}, title = {Exploring the context of user, creator and intermediate tagging}, url = {http://iasummit.org/2006/conferencedescrip.htm\#109}, year = 2006 } @inproceedings{conf/kcap/EcharteACVL11, author = {Echarte, Francisco and Astrain, José Javier and Córdoba, Alberto and Villadangos, Jesús E. and Labat, Aritz}, booktitle = {K-CAP}, crossref = {conf/kcap/2011}, editor = {Musen, Mark A. and Corcho, Óscar}, ee = {http://doi.acm.org/10.1145/1999676.1999712}, interhash = {e23258881917fe03d4acb056df50c4da}, intrahash = {7b4d79039426f7dea2559bde5d6b9e92}, isbn = {978-1-4503-0396-8}, pages = {175-176}, publisher = {ACM}, title = {A self-adapting method for knowledge management in collaborative and social tagging systems.}, url = {http://dblp.uni-trier.de/db/conf/kcap/kcap2011.html#EcharteACVL11}, year = 2011 } @inproceedings{costa2009social, author = {Costa, Ricardo Araujo and Silva, Edeilson M. and Neto, Mario G. and Delgado, Diego B. and Ribeiro, Rafael A. and Meira, Silvio R. L.}, booktitle = {CRIWG}, crossref = {conf/criwg/2009}, editor = {Carriço, Luís and Baloian, Nelson and Fonseca, Benjamim}, ee = {http://dx.doi.org/10.1007/978-3-642-04216-4_8}, interhash = {3ef53699a4c17a0b3362ccf0bf3df0c0}, intrahash = {f37184a2bf0e5a1b3092a2e7a5870ba7}, isbn = {978-3-642-04215-7}, pages = {94-109}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Social Knowledge Management in Practice: A Case Study.}, url = {http://dblp.uni-trier.de/db/conf/criwg/criwg2009.html#CostaSNDRM09}, volume = 5784, year = 2009 } @inproceedings{afsharchi2006automated, abstract = {This research addresses the formation of new concepts and their corresponding ontology in a multi-agent system where individual autonomous agents try to learn new concepts by consulting several other agents. In this research individual agents create and learn their distinct conceptualization and rather than a commitment to a common ontology they use their own ontologies. In this paper multi-agent supervised learning of concepts among individual agents with diverse conceptualization and different ontologies is introduced and demonstrated through an intuitive example in which supervisors are other agents rather than a human.}, acmid = {1146863}, address = {New York, NY, USA}, articleno = {16}, author = {Afsharchi, Mohsen and Far, Behrouz H.}, booktitle = {Proceedings of the 1st international conference on Scalable information systems}, doi = {10.1145/1146847.1146863}, interhash = {3614f61a4bddc48c0eeb7eecf6e7adee}, intrahash = {b5528a701397b534b3b0e5a24e37e7e2}, isbn = {1-59593-428-6}, location = {Hong Kong}, publisher = {ACM}, series = {InfoScale '06}, title = {Automated ontology evolution in a multi-agent system}, url = {http://doi.acm.org/10.1145/1146847.1146863}, year = 2006 } @inproceedings{barla2009deriving, author = {Barla, Michal and Bielikov�, M�ria}, booktitle = {Computational Collective Intelligence. Semantic Web, Social Networks and Multiagent System}, editor = {Nguyen, Ngoc Thanh and Kowalczyk, Ryszard and Chen, Shyi-Ming}, interhash = {ff65905d1c79503920fa46c013c2861c}, intrahash = {98c5b4c0cdbc9344773f9867f90a6a3a}, isbn = {978-3-642-04440-3}, pages = {309-320}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {On Deriving Tagsonomies: Keyword Relations Coming from Crowd.}, url = {http://dx.doi.org/10.1007/978-3-642-04441-0_27}, volume = 5796, year = 2009 } @incollection{radelaar2011improving, affiliation = {Erasmus University Rotterdam, PO Box 1738, NL-3000 Rotterdam, The Netherlands}, author = {Radelaar, Joni and Boor, Aart-Jan and Vandic, Damir and van Dam, Jan-Willem and Hogenboom, Frederik and Frasincar, Flavius}, booktitle = {Web Engineering}, editor = {Auer, Sören and Díaz, Oscar and Papadopoulos, George}, interhash = {48fe306f42bc405a5f8ae0f4a8885f3a}, intrahash = {77bc7f7e46481b47c11dd9e53d5741e0}, note = {10.1007/978-3-642-22233-7_19}, pages = {274-288}, publisher = {Springer Berlin / Heidelberg}, series = {Lecture Notes in Computer Science}, title = {Improving the Exploration of Tag Spaces Using Automated Tag Clustering}, url = {http://dx.doi.org/10.1007/978-3-642-22233-7_19}, volume = 6757, year = 2011 } @inproceedings{venetis2011selection, abstract = {We examine the creation of a tag cloud for exploring and understanding a set of objects (e.g., web pages, documents). In the first part of our work, we present a formal system model for reasoning about tag clouds. We then present metrics that capture the structural properties of a tag cloud, and we briefly present a set of tag selection algorithms that are used in current sites (e.g., del.icio.us, Flickr, Technorati) or that have been described in recent work. In order to evaluate the results of these algorithms, we devise a novel synthetic user model. This user model is specifically tailored for tag cloud evaluation and assumes an "ideal" user. We evaluate the algorithms under this user model, as well as the model itself, using two datasets: CourseRank (a Stanford social tool containing information about courses) and del.icio.us (a social bookmarking site). The results yield insights as to when and why certain selection schemes work best.}, acmid = {1935855}, address = {New York, NY, USA}, author = {Venetis, Petros and Koutrika, Georgia and Garcia-Molina, Hector}, booktitle = {Proceedings of the fourth ACM international conference on Web search and data mining}, doi = {10.1145/1935826.1935855}, interhash = {fc7ea4080c46677eeda3a69b67e89d77}, intrahash = {c3ccbbcd57d5c65a03f6f4e8b1eccd02}, isbn = {978-1-4503-0493-1}, location = {Hong Kong, China}, numpages = {10}, pages = {835--844}, publisher = {ACM}, series = {WSDM '11}, title = {On the selection of tags for tag clouds}, url = {http://doi.acm.org/10.1145/1935826.1935855}, year = 2011 }