http://www.bibsonomy.org/burst/user/wnpxrz/discoveryBibSonomy BuRST Feed for /user/wnpxrz/discovery2008-07-21T01:59:32+02:00Knowledge Discovery across Documents through Concept Chain Querieshttp://www.bibsonomy.org/bibtex/20342ecf31eb2c143344d6ecc213b507f/wnpxrzwnpxrz2007-12-03T17:39:23+01:00query knowledge imported document discovery concept <span style="color:#555555;">Wei <a href="http://www.bibsonomy.org/author/Jin">Jin</a> and Rohini K. <a href="http://www.bibsonomy.org/author/Srihari">Srihari</a> </span><em>ICDMW '06: Proceedings of the Sixth IEEE International Conference on Data Mining - Workshops, </em><em>page448--452. </em><em>Washington, DC, USA, </em><em>IEEE Computer Society, </em>(<em>2006</em>)Mon Dec 03 17:39:23 CET 2007Washington, DC, USAICDMW '06: Proceedings of the Sixth IEEE International Conference on Data Mining - Workshops448--452Knowledge Discovery across Documents through Concept Chain Queries2006query knowledge imported document discovery concept This paper focuses on detecting links between two concepts across text documents (e.g. two persons). We interpret such a query as finding the most meaningful evidence trail across documents that connect these two concepts. Here we propose a fast and efficient algorithm to perform this task. It is based on the idea of hypothesis generation originated by Swanson called "complementary structures in disjoint literatures" (CSD). We adapted the technique by (i) developing an alternate method of generating semantic profiles and (ii) extending the technique to generate concept chains. Counterterrorism corpus is used to evaluate the performance of this approach and demonstrates the effectiveness of our algorithm.Automated Concept Discovery from Web Resourceshttp://www.bibsonomy.org/bibtex/21384077d8e5be99f79a855015d1e39cf/wnpxrzwnpxrz2007-10-14T10:49:05+02:00concept web discovery imported <span style="color:#555555;">Michael <a href="http://www.bibsonomy.org/author/Dittenbach">Dittenbach</a> and Helmut <a href="http://www.bibsonomy.org/author/Berger">Berger</a> and Dieter <a href="http://www.bibsonomy.org/author/Merkl">Merkl</a> </span><em>WI '06: Proceedings of the 2006 IEEE/WIC/ACM International Conference on Web Intelligence, </em><em>page309--312. </em><em>Washington, DC, USA, </em><em>IEEE Computer Society, </em>(<em>2006</em>)Sun Oct 14 10:49:05 CEST 2007Washington, DC, USAWI '06: Proceedings of the 2006 IEEE/WIC/ACM International Conference on Web Intelligence309--312Automated Concept Discovery from Web Resources2006concept web discovery imported The task of researching information on a particular topic using the Web is mainly accomplished by using keyword-based search engines. Although this approach provides a good starting point, it remains a tedious task to collect additional information that puts this topic in greater context. In this paper we present ConceptWorld, an instrument to automatically discover various facets of a topic of interest by extracting concepts from Web documents. The result materializes as a network of semantic concepts with their various contextual interrelations and provides a holistic view on the topic of interest.dblphttp://www.bibsonomy.org/bibtex/269b669fd56e418721db7145659781e35/wnpxrzwnpxrz2007-06-28T13:58:20+02:00discovery search web collaborative <span style="color:#555555;">Maurice <a href="http://www.bibsonomy.org/author/Coyle">Coyle</a> and Barry <a href="http://www.bibsonomy.org/author/Smyth">Smyth</a> </span><em>ECIR, </em><em>volume4425ofLecture Notes in Computer Science, </em><em>page356-367. </em><em>Springer, </em>(<em>2007</em>)Thu Jun 28 13:58:20 CEST 2007ECIRconf/ecir/2007356-367Lecture Notes in Computer ScienceInformation Recovery and Discovery in Collaborative Web Search.44252007discovery search web collaborative