Abstract
Human discourse is fraught with rhetorical devices such as contradictions, illustrations, and analogies. These rhetorical devices carry important information which a listener uses to speed up the comprehension process. In this paper, we present a taxonomy of rhetorical devices commonly used in tutoring environment, and model the meaning of a class of rhetorical devices in terms of their anticipated effect on a listener's knowledge. These predictions are then used in planning computer‐generated discourse. As a testbed for our ideas, a system called WISHFUL is being implemented to generate commentaries in the domain of high‐school algebra within the framework of an intelligent tutoring system.
| Original language | English |
|---|---|
| Pages (from-to) | 25-40 |
| Number of pages | 16 |
| Journal | Computational Intelligence |
| Volume | 6 |
| Issue number | 1 |
| DOIs | |
| Publication status | Published - 1 Jan 1990 |
Keywords
- discourse planning
- intelligent tutoring system
- listener model
- natural language
Cite this
}
A predictive approach for the generation of rhetorical devices. / Zukerman, Ingrid.
In: Computational Intelligence, Vol. 6, No. 1, 01.01.1990, p. 25-40.Research output: Contribution to journal › Article › Research › peer-review
TY - JOUR
T1 - A predictive approach for the generation of rhetorical devices
AU - Zukerman, Ingrid
PY - 1990/1/1
Y1 - 1990/1/1
N2 - Human discourse is fraught with rhetorical devices such as contradictions, illustrations, and analogies. These rhetorical devices carry important information which a listener uses to speed up the comprehension process. In this paper, we present a taxonomy of rhetorical devices commonly used in tutoring environment, and model the meaning of a class of rhetorical devices in terms of their anticipated effect on a listener's knowledge. These predictions are then used in planning computer‐generated discourse. As a testbed for our ideas, a system called WISHFUL is being implemented to generate commentaries in the domain of high‐school algebra within the framework of an intelligent tutoring system.
AB - Human discourse is fraught with rhetorical devices such as contradictions, illustrations, and analogies. These rhetorical devices carry important information which a listener uses to speed up the comprehension process. In this paper, we present a taxonomy of rhetorical devices commonly used in tutoring environment, and model the meaning of a class of rhetorical devices in terms of their anticipated effect on a listener's knowledge. These predictions are then used in planning computer‐generated discourse. As a testbed for our ideas, a system called WISHFUL is being implemented to generate commentaries in the domain of high‐school algebra within the framework of an intelligent tutoring system.
KW - discourse planning
KW - intelligent tutoring system
KW - listener model
KW - natural language
UR - http://www.scopus.com/inward/record.url?scp=84990619169&partnerID=8YFLogxK
U2 - 10.1111/j.1467-8640.1990.tb00127.x
DO - 10.1111/j.1467-8640.1990.tb00127.x
M3 - Article
VL - 6
SP - 25
EP - 40
JO - Computational Intelligence
JF - Computational Intelligence
SN - 0824-7935
IS - 1
ER -