Improved Text Generation Using N-gram Statistics

Abstract. 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 providing a linguistically- rich input specification, and also by taking some of the generation decisions away from the surface realisation module, we expect to make NLG techniques accessible to a wider range of potential applications. Key words: Text Generation, Surface Realisation, Language Modelling

• Type: Journal
• Year: 2010
• Where: IBERAMIA
• Authors: Eder Miranda de Novais, Thiago Dias Tadeu, Ivandré Paraboni
• Keywords: Artificial Intelligence, Generalpurpose Surface Realisation, IBERAMIA 2010, Natural Language Generation, Surface Realisation Module