Long Short-Term Memory Description and its Application in Text Processing

The paper describes the state-of-the-art of Long Short-Term Memory (LSTM) neural networks with fixation to context utilization in text documents. Context in text documents is utilized mainly in the natural language processing, machine reading, but also in other areas, for example in the information retrieval. In the areas where the context is taken into account, the LSTM finds wide appliance because it is able to remember preceding states and on the base of them to evaluate the required task. Preceding states is not needed to place on the input again.