Main Article Content
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.
This journal is licensed under the terms of the CC BY 4.0 licence (https://creativecommons.org/licenses/by/4.0/legalcode).