Feed-Forward Network Model for Multi-Document Relation Classification
|
| Title | Feed-Forward Network Model for Multi-Document Relation Classification |
| Authors | |
| Abstract | Using feed-forward artificial neural network to classify multi-document relation is the subject of this paper. Sentences across topically related documents can often be linked by means of relations that exist between them. In this study, we aim to identify four types of relations, namely, Identity, Subsumption, Description and Overlap. We propose to use neural network learning model for the task of classification; multi-class classification, in this case. The performance of our proposed approach was measured using Precision, Recall and F-measure. The experimental findings demonstrate that better results can be obtained by using the proposed approach when compared with the widely used SVM classifier. |
| Publisher | Faculty of Computing, Universiti Teknologi Malaysia |
| Date | 2013-06-10 |
| Source | International Journal of Innovative Computing Vol 3, No 1 (2013): Jun 2013 |
| Rights | Copyright PermissionsAuthors submitting articles to the Journal are responsible for obtaining permissions for reproduction of any previously published figures, tables, any other objects or textual materials included in the manuscript from the original copyright owners. They should submit any copyright or other permission at the time of article submission. Failure to do so could lead to a delay in publication of accepted articles. The Publisher or the Journal will not be liable for infringement of anyoneââ¬â¢s copyright or other rights by the authors. A willful neglect of copyright by the authors may lead to retraction of their article.àCopyright Ownership of Published ArticlesAuthors retain copyright of their published articles. However, they will be required to grant an unrestricted worldwide licence allowing anyone to copy, print and distribute their work in a lawful manner, for non-commercial purposes only, except that the users fully and appropriately acknowledge the original source of publication as the International Journal of Innovative Computing and the authorship of the work with correct citation details. In addition, the authors will also be required to grant an unrestricted, exclusive, royalty-free licence to Universiti Teknologi Malaysia and its any successors to store, print, copy and distribute their article(s) in any form ââ¬â printed, electronic or any other media invented hereafter, for the entire period of the copyright and its any extensions. Authors will also be required to give an exclusive, royalty-free licence to Universiti Teknologi Malaysia and its any successors to transfer any permissions to a third party to store, print, copy and distribute their article(s) in any form ââ¬â printed, electronic or any other media invented hereafter, for the entire period of the copyright and its any extensions. |