BibSonomyburst/user/hotho/topicBibSonomy RSS feed for /user/hotho/topic2012-02-16T01:57:47+01:00http://www.bibsonomy.org/bibtex/2f8a5a3958ae264d19c7f5415eb7f0bce/hothohotho2011-09-14T08:20:38+02:00mining model text tm topic toread <span class="authorEditorList"><a href="/author/Rubin">Timothy N. Rubin</a>, <a href="/author/Chambers">America Chambers</a>, <a href="/author/Smyth">Padhraic Smyth</a>, and <a href="/author/Steyvers">Mark Steyvers</a> </span>(<em>2011</em>)<em>cite arxiv:1107.2462 . </em>Wed Sep 14 08:20:38 CEST 2011cite arxiv:1107.2462Statistical Topic Models for Multi-Label Document Classification2011mining model text tm topic toread Machine learning approaches to multi-label document classification have (to date) largely relied on discriminative modeling techniques such as support vector machines. A drawback of these approaches is that performance rapidly drops off as the total number of labels and the number of labels per document increase. This problem is amplified when the label frequencies exhibit the type of highly skewed distributions that are often observed in real-world datasets. In this paper we investigate a class of generative statistical topic models for multi-label documents that associate individual word tokens with different labels. We investigate the advantages of this approach relative to discriminative models, particularly with respect to classification problems involving large numbers of relatively rare labels. We compare the performance of generative and discriminative approaches on document labeling tasks ranging from datasets with several thousand labels to datasets with tens of labels. The experimental results indicate that generative models can achieve competitive multi-label classification performance compared to discriminative methods, and have advantages for datasets with many labels and skewed label frequencies. Statistical Topic Models for Multi-Label Document Classificationhttp://www.bibsonomy.org/bibtex/27b335f08a288a79eb70eff89f1ec7630/hothohotho2009-12-23T18:06:56+01:00folksonomy learning model ol tagging taggingsurvey topic toread <span class="authorEditorList"><a href="/author/Tang">Jie Tang</a>, <a href="/author/fung Leung">Ho fung Leung</a>, <a href="/author/Luo">Qiong Luo</a>, <a href="/author/Chen">Dewei Chen</a>, and <a href="/author/Gong">Jibin Gong</a> </span><em>IJCAI&#039;09: Proceedings of the 21st international jont conference on Artifical intelligence, </em><em>page 2089--2094. </em><em>San Francisco, CA, USA, </em><em>Morgan Kaufmann Publishers Inc., </em>(<em>2009</em>)Wed Dec 23 18:06:56 CET 2009San Francisco, CA, USAIJCAI'09: Proceedings of the 21st international jont conference on Artifical intelligence2089--2094Towards ontology learning from folksonomies2009folksonomy learning model ol tagging taggingsurvey topic toread 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.Towards ontology learning from folksonomieshttp://www.bibsonomy.org/bibtex/234dcb1eee3ffa31ff4eb77087343c146/hothohotho2009-04-10T19:01:21+02:00analysis extraction keyword statistical text tm topic toread <span class="authorEditorList"><a href="/author/Carpena">P. Carpena</a>, <a href="/author/Bernaola-Galván">P. Bernaola-Galván</a>, <a href="/author/Hackenberg">M. Hackenberg</a>, <a href="/author/Coronado">A. V. Coronado</a>, and <a href="/author/Oliver">J. L. Oliver</a> </span><em>Physical Review E Statistical, Nonlinear, and Soft Matter Physics</em> <em>79(3):035102</em> (<em>2009</em>)Fri Apr 10 19:01:21 CEST 2009Physical Review E (Statistical, Nonlinear, and Soft Matter Physics)3035102Level statistics of words: Finding keywords in literary texts and symbolic sequences792009analysis extraction keyword statistical text tm topic toread Level statistics of words: Finding keywords in literary texts and symbolic sequenceshttp://www.bibsonomy.org/bibtex/257f8241941ed979455c3dbb90893020f/hothohotho2008-07-01T15:19:39+02:00classification concept model tc text topic wordnet <span class="authorEditorList"><a href="/author/Ifrim">Georgiana Ifrim</a>, <a href="/author/Theobald">Martin Theobald</a>, and <a href="/author/Weikum">Gerhard Weikum</a> </span><em>Proceedings of the 22nd International Conference on Machine Learning - Learning in Web Search LWS 2005, </em><em>page 18--26. </em><em>Bonn, Germany, </em>(<em>2005</em>)Tue Jul 01 15:19:39 CEST 2008Bonn, GermanyProceedings of the 22nd International Conference on Machine Learning - Learning in Web Search (LWS 2005)18--26Learning Word-to-Concept Mappings for Automatic Text Classification2005classification concept model tc text topic wordnet D5 MPI-INF Publications: Proceedings Article: Learning Word-to-Concept Mappings for Automatic Text Classificationhttp://www.bibsonomy.org/bibtex/2c056611effc0d18aae71a6d535ff6c5a/hothohotho2006-11-02T10:06:26+01:00pagerank toread topic <span class="authorEditorList"><a href="/author/Haveliwala">Taher H. Haveliwala</a> </span><em>Proceedings of the Eleventh International World Wide Web Conference, </em><em>Honolulu, Hawaii, </em>(<em>May 2002</em>)Thu Nov 02 10:06:26 CET 2006Honolulu, HawaiiProceedings of the Eleventh International World Wide Web ConferenceMayTopic-sensitive PageRank2002pagerank toread topic Topic-Sensitive PageRank - Haveliwala (ResearchIndex)http://www.bibsonomy.org/bibtex/2004dd97a2b2e71fa2cfe6820c74c9701/hothohotho2006-09-12T09:28:58+02:00crawling focused topic <span class="authorEditorList"><a href="/author/Chakrabarti">S. Chakrabarti</a>, <a href="/author/van den Berg">M. van den Berg</a>, and <a href="/author/Dom">B. Dom</a> </span><em>Computer Networks</em> (<em>1999</em>)Tue Sep 12 09:28:58 CEST 2006Computer Networks1623--1640Focused Crawling: A New Approach to Topic-Specific Web Resource Discovery311999crawling focused topic http://www.bibsonomy.org/bibtex/29c57003d80b81eab2f66b2faf02acb27/hothohotho2006-02-11T13:42:47+01:00techniques topic survey data detection stream **** analysis temporal trend <span class="authorEditorList"><a href="/author/Kleinberg">J. Kleinberg</a> </span><em>Springer, </em>(<em>2006</em>)Sat Feb 11 13:42:47 CET 2006Data Stream Management: Processing High-Speed Data StreamsTemporal Dynamics of On-Line Information Streams2006techniques topic survey data detection stream **** analysis temporal trend http://www.bibsonomy.org/bibtex/2cbfda2e50bd63357890b9181d8883826/hothohotho2006-02-09T13:03:23+01:00topic time detection trend series ml <span class="authorEditorList"><a href="/author/Griffiths">Thomas L. Griffiths</a>, and <a href="/author/Steyvers">Mark Steyvers</a> </span> (<em>2004</em>)Thu Feb 09 13:03:23 CET 2006Finding scientific topics2004topic time detection trend series ml http://www.bibsonomy.org/bibtex/2cc72df61f4c0de369a4018ec02edffcb/hothohotho2005-12-20T20:21:42+01:00web maps topic semantic mining xml <span class="authorEditorList"><a href="/author/Grand">B. Le Grand</a>, and <a href="/author/Soto">M. Soto</a> </span><em>WS_SHB01, </em><em>page 67--83. </em>(<em>2001</em>)Tue Dec 20 20:21:42 CET 2005\cite{WS_SHB01}67--83XML Topic Maps and Semantic Web Mining2001web maps topic semantic mining xml