@article{budanitsky2006evaluating, address = {Cambridge, MA, USA}, author = {Budanitsky, Alexander and Hirst, Graeme}, file = {budanitsky2006evaluating.pdf:budanitsky2006evaluating.pdf:PDF}, groups = {public}, interhash = {a259f21d89bdc61a64ce11a3aea0af06}, intrahash = {563138e890f4463f29c0324c95878129}, journal = {Computational Linguists}, number = 1, pages = {13--47}, publisher = {MIT Press}, timestamp = {2010-06-03 10:09:44}, title = {Evaluating WordNet-based Measures of Lexical Semantic Relatedness}, url = {http://ftp.cs.toronto.edu/pub/gh/Budanitsky+Hirst-2006.pdf}, username = {dbenz}, volume = 32, year = 2006 } @inproceedings{agirre2009study, abstract = {This paper presents and compares WordNet-based and distributional similarity approaches. The strengths and weaknesses of each approach regarding similarity and relatedness tasks are discussed, and a combination is presented. Each of our methods independently provide the best results in their class on the RG and WordSim353 datasets, and a supervised combination of them yields the best published results on all datasets. Finally, we pioneer cross-lingual similarity, showing that our methods are easily adapted for a cross-lingual task with minor losses.}, acmid = {1620758}, address = {Stroudsburg, PA, USA}, author = {Agirre, Eneko and Alfonseca, Enrique and Hall, Keith and Kravalova, Jana and Pa\c{s}ca, Marius and Soroa, Aitor}, booktitle = {Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics}, interhash = {35326b1cfd5cde92744c22b981c84b23}, intrahash = {e91cce045a1d323c0012027f04771733}, isbn = {978-1-932432-41-1}, location = {Boulder, Colorado}, numpages = {9}, pages = {19--27}, publisher = {Association for Computational Linguistics}, series = {NAACL '09}, title = {A study on similarity and relatedness using distributional and WordNet-based approaches}, url = {http://portal.acm.org/citation.cfm?id=1620754.1620758}, year = 2009 } @inproceedings{mchale1998comparison, abstract = { This paper presents the results of using Roget's International Thesaurus as the taxonomy in a semantic similarity measurement task. Four similarity metrics were taken from the literature and applied to Roget's The experimental evaluation suggests that the traditional edge counting approach does surprisingly well (a correlation of r=0.88 with a benchmark set of human similarity judgements, with an upper bound of r=0.90 for human subjects performing the same task.)}, author = {McHale, Michael}, booktitle = {Proceedings of the COLING/ACL Workshop on Usage of WordNet in Natural Language Processing Systems, August 16, 1998, Montreal, Canada}, editor = {Harabagiu, Sanda and Chai, Joyce Yue}, interhash = {3759256d578dcab653d72a42dc4a3f0e}, intrahash = {070f5400952a1847392ce7cd4522eacd}, publisher = {Association for Computational Linguistics, Morristown, NJ, USA}, title = {A Comparison of WordNet and Roget's Taxonomy for Measuring Semantic Similarity}, url = {http://www.citebase.org/abstract?id=oai:arXiv.org:cmp-lg/9809003}, year = 1998 } @incollection{haridas2009exploring, abstract = {The outgrowth of social networks in the recent years has resulted in opportunities for interesting data mining problems, such as interest or friendship recommendations. A global ontology over the interests specified by the users of a social network is essential for accurate recommendations. We propose, evaluate and compare three approaches to engineering a hierarchical ontology over user interests. The proposed approaches make use of two popular knowledge bases, Wikipedia and Directory Mozilla, to extract interest definitions and/or relationships between interests. More precisely, the first approach uses Wikipedia to find interest definitions, the latent semantic analysis technique to measure the similarity between interests based on their definitions, and an agglomerative clustering algorithm to group similar interests into higher level concepts. The second approach uses the Wikipedia Category Graph to extract relationships between interests, while the third approach uses Directory Mozilla to extract relationships between interests. Our results show that the third approach, although the simplest, is the most effective for building a hierarchy over user interests.}, address = {Berlin / Heidelberg}, affiliation = {Kansas State University Nichols Hall Manhattan KS 66502}, author = {Haridas, Mandar and Caragea, Doina}, booktitle = {On the Move to Meaningful Internet Systems: OTM 2009}, doi = {10.1007/978-3-642-05151-7_35}, editor = {Meersman, Robert and Dillon, Tharam and Herrero, Pilar}, file = {haridas2009exploring.pdf:haridas2009exploring.pdf:PDF}, groups = {public}, interhash = {2363d3cb1430a4b279692e1ff3413809}, intrahash = {982538ff1fd44d2c3296b700eac859b3}, pages = {1238-1245}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, timestamp = {2010-10-18 15:53:06}, title = {Exploring Wikipedia and DMoz as Knowledge Bases for Engineering a User Interests Hierarchy for Social Network Applications}, url = {http://dx.doi.org/10.1007/978-3-642-05151-7_35}, username = {dbenz}, volume = 5871, year = 2009 } @inproceedings{laniado2007using, abstract = {As the volume of information in the read-write Web increases rapidly, folksonomies are becoming a widely used tool to organize and categorize resources in a bottom up, flat and inclusive way. However, due to their very structure, they show some drawbacks; in particular the lack of hierarchy bears some limitations in the possibilities of searching and browsing. In this paper we investigate a new approach, based on the idea of integrating an ontology in the navigation interface of a folksonomy, and we describe an application that filters del.icio.us keywords through the WordNet hierarchy of concepts, to enrich the possibilities of navigation.}, author = {Laniado, David and Eynard, Davide and Colombetti, Marco}, booktitle = {Semantic Web Application and Perspectives - Fourth Italian Semantic Web Workshop}, file = {laniado2007using.pdf:laniado2007using.pdf:PDF}, groups = {public}, interhash = {20cfb04df242c1ab1c986128c9f5a9c9}, intrahash = {7f7ac73677841b4580461d408e83495a}, month = Dec, pages = {192--201}, timestamp = {2009-07-24 14:20:02}, title = {Using WordNet to turn a folksonomy into a hierarchy of concepts}, url = {http://home.dei.polimi.it/eynard/papers/swap2007.pdf}, username = {dbenz}, year = 2007 } @incollection{ruizcasado2005automatic, abstract = {This paper describes an automatic approach to identify lexical patterns which represent semantic relationships between concepts, from an on-line encyclopedia. Next, these patterns can be applied to extend existing ontologies or semantic networks with new relations. The experiments have been performed with the Simple English Wikipedia and WordNet 1.7. A new algorithm has been devised for automatically generalising the lexical patterns found in the encyclopedia entries. We have found general patterns for the hyperonymy, hyponymy, holonymy and meronymy relations and, using them, we have extracted more than 1200 new relationships that did not appear in WordNet originally. The precision of these relationships ranges between 0.61 and 0.69, depending on the relation.}, address = {Berlin / Heidelberg}, affiliation = {Computer Science Dep., Universidad Autonoma de Madrid, 28049 Madrid Spain}, author = {Ruiz-Casado, Maria and Alfonseca, Enrique and Castells, Pablo}, booktitle = {Natural Language Processing and Information Systems}, doi = {10.1007/11428817_7}, editor = {Montoyo, Andrés and Muñoz, Rafael and Métais, Elisabeth}, file = {ruizcasado2005automatic.pdf:ruizcasado2005automatic.pdf:PDF}, groups = {public}, interhash = {a05c644f18f451dc2bac7c4c97f63ccd}, intrahash = {53d9a5edc19dbc8b20705768b2518fd2}, pages = {233-242}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, timestamp = {2011-02-02 15:55:29}, title = {Automatic Extraction of Semantic Relationships for WordNet by Means of Pattern Learning from Wikipedia}, url = {http://dx.doi.org/10.1007/11428817_7}, username = {dbenz}, volume = 3513, year = 2005 }