E03-2016 text plan tree using the form of template-based generation described by Wilcock ( 2001 )
P01-1056 system utterances . The first is template-based generation , where utterances are produced
W01-1608 within the tem - plates . Unlike template-based generation systems where the templates are
P13-1123 rank their output equivalently to template-based generation . Further , our approach is related
W10-4219 lexical resources and discuss how template-based generation systems can benefit from them
W00-0306 ran two generation algorithms ( template-based generation and stochastic generation ) on
W10-4337 is sufficiently simple to use template-based generation techniques to produce the surface
H01-1013 presenting it to the user using template-based generation . The dialog manager formulates
W05-1603 that accommodates both shallow template-based generation and in-depth realization tasks
P02-1048 The generation process performs template-based generation for simple responses and updates
J09-3002 The generation process performs template-based generation for simple responses and updates
W09-2813 learning techniques combined with a template-based generation system to instantiate the briefing-worthy
P15-1005 then generating the text with a template-based generation model using the predicted VDR
P01-1056 Most current research systems use template-based generation because it is conceptually straightforward
W09-2813 part of the design phase for the template-based generation component , we identified a set
E03-2016 NLG techniques include a form of template-based generation , transformation of text plan
W00-0306 preferred stochastic generation over template-based generation , but a t-test shows no significant
P01-1056 compare SPOT to the hand-crafted , template-based generation component of the current system
P01-1056 we also evaluate a hand-crafted template-based generation component , two rule-based sentence
N04-1028 generation is done by a simple template-based generation module , and speech synthesis
hide detail