Abstract:

This paper studies a Dynamic Memory Network, which is the key component for a Question Answering System. For the training of the initial model of the deep neural network, the system uses a collection of data created in an artificial way, to improve the attention mechanism towards the right answers. Furthermore, the changes made are implemented in the two sections of the network, the input module and the episodic memory module. The system is part of cutting-edge research in the field of natural language processing and provides results that are used for intelligent user interaction with digital books.