WeKnowIt D3.3 Report on mass classification and clustering tools
Author | Maciej Janik, Symeon Papadopoulos, Börkur Sigurbjörnsson |
Domain | |
Task | |
Publisher | |
Event | |
Project | WeKnowIt |
Dataset Used | |
Published | 19/07/2010 |
Copyright | The research leading to these results has received funding from the European Community’s Seventh Framework Programme (FP7) under grant agreement n° 215453 |
DOI |
Abstract
This report describes new methods developed within the mass classification and clustering task. Proposed solutions were driven by the requirements from project scenarios – emergency response and consumer social group. These include approaches to tag network analysis and community detection, hybrid approach to image clustering, named entity recognition and classification with use of ontology, discovery of facets for improving image search and navigation, and geo-positioning of Wikipedia articles based on their content. This document includes detailed description of developed methods together with their evaluation and applications within the WeKnowIt project. Each method is described in details in separate section. Proposed solutions not only demonstrate new ideas developed within WP3, but also present integration and collaboration with other work packages in the project.
Authors
Main Author(s) : Maciej Janik (UoKob), Symeon Papadopoulos (CERTH), Börkur Sigurbjörnsson (Yahoo)
Citations
Links
Link to Deliverable : http://www.weknowit.eu/sites/default/files/D3.3.pdf Project Website : http://www.weknowit.eu/