2010 | OriginalPaper | Buchkapitel
Neural Networks Based Detection of Purpose Data in Text
verfasst von : P. Kiran Mayee, Rajeev Sangal, Soma Paul
Erschienen in: Information and Communication Technologies
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Purpose is an inherent relation in artifact-related text. This information is available as a pair of components, called ‘purpose-action’ and ‘purpose-upon’ in text. This paper presents the Neural Networks as a possible solution to detecting the existence of ‘purpose_action’ in corpus. Two types of Neural Networks, i.e., RBF Networks and Multilayer Perceptron Neural Network have been tried and compared with a Naïve Bayes approach to detection. The corresponding results have been tabulated. The MLP method is found to be more efficient among the two.