Abstract
In recent times, there has been an increase in the number of Natural Language Generation systems that take into consideration a user's inferences. The statements generated by these systems are typically connected by inferential links, which are opportunistic in nature. In this paper, we describe a discourse structuring mechanism which organizes inferentially linked statements as well as statements connected by certain prescriptive links. Our mechanism first extracts relations and constraints from the output of a discourse planner. It then uses this information to build a directed graph whose nodes are rhetorical devices, and whose links are the relations between these devices. The mechanism then applies a search procedure to optimize the traversal through the graph. This process generates an ordered set of linear discourse sequences, where the elements of each sequence are maximally connected. Our mechanism has been implemented as the discourse organization component of a system called WISHFUL which generates concept explanations.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the National Conference on Artificial Intelligence |
| Publisher | Publ by AAAI |
| Pages | 202-207 |
| Number of pages | 6 |
| ISBN (Print) | 0262510715 |
| Publication status | Published - 1 Dec 1993 |
| Event | Proceedings of the 11th National Conference on Artificial Intelligence - Washington, United States of America Duration: 11 Jul 1993 → 15 Jul 1993 |
Conference
| Conference | Proceedings of the 11th National Conference on Artificial Intelligence |
|---|---|
| Country | United States of America |
| City | Washington |
| Period | 11/07/93 → 15/07/93 |
Cite this
}
Optimizing method for structuring inferentially linked discourse. / Zukerman, Ingrid; McConachy, Richard.
Proceedings of the National Conference on Artificial Intelligence. Publ by AAAI, 1993. p. 202-207.Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review
TY - GEN
T1 - Optimizing method for structuring inferentially linked discourse
AU - Zukerman, Ingrid
AU - McConachy, Richard
PY - 1993/12/1
Y1 - 1993/12/1
N2 - In recent times, there has been an increase in the number of Natural Language Generation systems that take into consideration a user's inferences. The statements generated by these systems are typically connected by inferential links, which are opportunistic in nature. In this paper, we describe a discourse structuring mechanism which organizes inferentially linked statements as well as statements connected by certain prescriptive links. Our mechanism first extracts relations and constraints from the output of a discourse planner. It then uses this information to build a directed graph whose nodes are rhetorical devices, and whose links are the relations between these devices. The mechanism then applies a search procedure to optimize the traversal through the graph. This process generates an ordered set of linear discourse sequences, where the elements of each sequence are maximally connected. Our mechanism has been implemented as the discourse organization component of a system called WISHFUL which generates concept explanations.
AB - In recent times, there has been an increase in the number of Natural Language Generation systems that take into consideration a user's inferences. The statements generated by these systems are typically connected by inferential links, which are opportunistic in nature. In this paper, we describe a discourse structuring mechanism which organizes inferentially linked statements as well as statements connected by certain prescriptive links. Our mechanism first extracts relations and constraints from the output of a discourse planner. It then uses this information to build a directed graph whose nodes are rhetorical devices, and whose links are the relations between these devices. The mechanism then applies a search procedure to optimize the traversal through the graph. This process generates an ordered set of linear discourse sequences, where the elements of each sequence are maximally connected. Our mechanism has been implemented as the discourse organization component of a system called WISHFUL which generates concept explanations.
UR - http://www.scopus.com/inward/record.url?scp=0027706954&partnerID=8YFLogxK
M3 - Conference Paper
SN - 0262510715
SP - 202
EP - 207
BT - Proceedings of the National Conference on Artificial Intelligence
PB - Publ by AAAI
ER -