The Implications of Linguistic Characteristics in the Definition of a Learning Model

Abstract

In recent years, powerful deep learning models have emerged yielding state-of-the-art results in fields such as image recognition and natural language processing. In the particular case of text processing, various neural architectures have been defined to cope with the necessity of memory to process previous elements in a sequence text. This article makes use of quantitative methods and complexity indicators to provide empirical evidence for the adequacy of recurrent neural models and their corresponding variants. In other words, in this article we show how to determine the linguistic characteristics from text is fundamental to define the deep learning model to be used.