From NLG Systems Wiki

Jump to: navigation, search

Template stands for template-based generation, a catch-all for all pragmatic approaches to NLG that do not rely on “deep” linguistic processing but instead extend the mail-merge approach to text generation as needed.

For a more sophisticated discussion, please refer to [1]

  1. van Deemter, K., Theune, M., & Krahmer, E. (2005). Real versus Template-Based Natural Language Generation: A False Opposition? Computational Linguistics, 31(1), 15. Bib

This wiki believes that the following NLG systems are based on the Template framework:

System Worker Started Ended Description
Ecran Geldof
Van de Velde
24504501997 24504501997 generates descriptions of movies, using a model of the user's interests
GoalGetter Klabbers
De Pijper
24500841996 24515452000 GoalGetter generates spoken summaries of football (soccer) matches on the basis of tabular data
IDtension Szilas 24541022007 24541022007 System implementing many aspects of narrative theory in order to support interactive drama
Power Green
24508151998 24508151998 another virtual museum system dynamically generating descriptions of museum objects
TEMSIS Busemann
24504501997 24508151998 provides environmental information
TG/2 Busemann 24508151998 shallow generation component using generalized templates
TextPro Buchin
24508151998 24511801999
Tiddler 24511801999 Personalized travel guides
WEBCOOP Benamara 24530062004 24530062004 Logic-based model for question answering
XtraGen Stenzhorn 24522762002 Template-based generation with XML and Java interfaces
Personal tools