An Optimizing Method for Structuring Inferentially Linked Discourse

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.

[1]  Sandra Carberry,et al.  Capturing high‐level structure of naturally occurring, extended explanations using bottom‐up strategies , 1991 .

[2]  Chris Mellish,et al.  Current research in natural language generation , 1990 .

[3]  Nils J. Nilsson,et al.  Principles of Artificial Intelligence , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Kathleen F. McCoy,et al.  Focus of attention: Constraining what can be said next , 1991 .

[5]  Earl David Sacerdoti,et al.  A Structure for Plans and Behavior , 1977 .

[6]  Eduard H. Hovy,et al.  Planning Coherent Multisentential Text , 1988, ACL.

[7]  L ParisCécile.  Tailoring object descriptions to a user's level of expertise , 1988 .

[8]  Alison Cawsey.  Generating explanatory discourse , 1990 .

[9]  William C. Mann,et al.  Computer Generation of Multiparagraph English Text , 1981, Am. J. Comput. Linguistics.

[10]  Johanna D. Moore,et al.  A Reactive Approach to Explanation , 1989, IJCAI.

[11]  INGRID ZUKERMAN,et al.  A predictive approach for the generation of rhetorical devices , 1990, Comput. Intell..

[12]  Bonnie Webber,et al.  So what can we talk about now , 1986 .

[13]  Farid Cerbah.  Generating Causal Explanations: From Qualitative Models to Natural Language Texts , 1992, ECAI.

[14]  William C. Mann,et al.  RHETORICAL STRUCTURE THEORY: A THEORY OF TEXT ORGANIZATION , 1987 .

[15]  Alison Cawsey,et al.  Using Plausible Inference Rules in Description Planning , 1991, EACL.

[16]  Helmut Horacek,et al.  Exploiting Conversational Implicature for Generating Concise Explanations , 1991, EACL.

[17]  Bonnie L. Webber,et al.  Living Up to Expectations: Computing Expert Responses , 1984, HLT.

[18]  Cécile Paris,et al.  Tailoring Object Descriptions to a User's Level of Expertise , 1988, Comput. Linguistics.

[19]  Alex Lascarides,et al.  Abducing Temporal Discourse , 1992, NLG.

[20]  Ingrid Zukerman,et al.  Generating Concise Discourse that Addresses a Users Inferences , 1993, IJCAI.

[21]  J. L. Weiner,et al.  BLAH, A System Which Explains its Reasoning , 1980, Artif. Intell..