kNarrator: A Model For Authors To Simplify Authoring Process Using Natural Language Processing To Portuguese

In this paper, we propose a model to help writers to produce narratives or text fragments using only few words as input. The proposed model uses pseudo-text as input and returns full fluid text as output. The facts described in the pseudo-text can be transcribed with a different level of detail set by the user, from a simple sentence to an expanded description, adding details according to a user-defined semantic dictionary. This allows authors to visualize ideas and concepts of narratives. Our model can also be used in games as a tool to generate narratives and descriptions in natural language text. In order to evaluate our approach, we performed a comparative study with some authoring models and results are further discussed.