Badler et al. Natural Language Text Generation from Task Networks for Use in Automatic Generation of Technical Orders from DEPTH Simulations. Final Report to Air Force HRGA, March 1997. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Generating Effective Natural Language Instructions Based On Agent .. - Bourne (1999) (Correct)
....and can guide the generation process. 9 1. 2 Representing Action Information The Parameterized Action Representation (PAR) developed at the University of Pennsylvania, is meant as an intermediate representation that can support both the animation and Natural Language description of actions [Badler et al., 1997; Badler et al., 1998; Badler et al. 1998] As such a representation, PAR can represent actions at various levels of abstraction, from general action classes to specific action instances (i.e. sets of action performances) A PAR instance for an action consists of the features of the action, ....
....and Natural Language researchers, action information needed for both purposes emerged. Work by others in the area of verb semantics [Badler et al., 1998; Dang et al. 1997; Dang et al. 1998] as well as the informational requirements of simulating agents carrying out maintenance activities [Badler et al., 1997], along with the analysis of maintenance instructions, contributed to the development of the action representation described below. While this dissertation work does not take advantage of all the capabilities of the action representation, I present its full extent (so far) in order to hint 55 at ....
Badler et al. Natural Language Text Generation from Task Networks for Use in Automatic Generation of Technical Orders from DEPTH Simulations. Final Report to Air Force HRGA, March 1997.
Generating Effective Instructions: Knowing When To Stop - Bourne (1998) (3 citations) (Correct)
....be discussed in more detail in Chapter 5, which describes the implemented work. 2.3. 1 Action representation I use a Parameterized Action Representation (PAR) developed here at Penn as an intermediate representation that can support both the animation and Natural Language description of actions [Badler et al., 1997; Badler et al., 1998] As an intermediate representation, PAR must represent actions at various levels of abstraction, from general action classes to specific action instances (i.e. sets of action performances) A PAR instance for an action consists of the various features of the action. These ....
Badler et al. Natural Language Text Generation from Task Networks for Use in Automatic Generation of Technical Orders from DEPTH Simulations. Final Report to Air Force HRGA, March 1997.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC