GenLeNa: Sistema para la construcción de Aplicaciones de Generación de Lenguaje Natural GenLeNa: Method to Develop Natural Language Generation (NLG) Systems

Authors

  • Gloria Johanna Chala T. Carvajal, S.A.
  • Rafael Armando Jordán O. Departamento de Ingeniería de la Computación, Universidad Javeriana, Cali
  • Diego Luis Linares Universidad Javeriana, Cali

DOI:

https://doi.org/10.18046/syt.v5i9.973

Keywords:

Natural language generation (NLG), content planning (CPP), document structuring (DEP), rhetorical structure theory (RST).

Abstract

In this article the proposal is made for the division of the process of construction of natural language generation (NLG) systems into two stages: content planning (CP), which is dependent on the mastery of the application to be developed, and document structuring (DS). This division allows people who are not expert in NLG to develop natural language generation systems, concentrating on building abstract representations of the information to be communicated (called messages). Specific architecture for the DS stage is also presented. This enables NLG researchers to work ortogonally on specific techniques and methodologies for the conversion of messages into text which is grammatically and syntactically correct.

Author Biographies

  • Gloria Johanna Chala T., Carvajal, S.A.
    Bio Statement is available in Spanish
  • Rafael Armando Jordán O., Departamento de Ingeniería de la Computación, Universidad Javeriana, Cali
    Bio Statement is available in Spanish
  • Diego Luis Linares, Universidad Javeriana, Cali
    Bio Statement is available in Spanish

Downloads

Published

2007-08-01

Issue

Section

Original Research