Improved Text Generation Using N-gram Statistics

  title={Improved Text Generation Using N-gram Statistics},
  author={Eder Miranda de Novais and Thiago Dias Tadeu and Ivandr{\'e} Paraboni},
In Natural Language Generation (NLG) systems, a generalpurpose surface realisation module will usually require the underlying application to provide highly detailed input knowledge about the target sentence. As an attempt to reduce some of this complexity, in this paper we follow a traditional approach to NLG and present a number of experiments involving the use of n-gram language models as an aid to an otherwise rule-based text generation approach. By freeing the application from the burden of… CONTINUE READING