Using Plan Reasoning in the Generation of Plan Descriptions

Previous work on the generation of natural language descriptions of complex activities has indicated that the unwieldy amount of text needed to describe complete plans makes for ineffective and unnatural descriptions. We argue here that concise and effective text descriptions of plans can be generated by exploiting a model of the hearer's plan reasoning capabilities. We define a computational model of the hearer's interpretation process that views the interpretation of plan descriptions as refinement search through a space of partial plans. This model takes into account the hearer's plan preferences and the resource limitations on her reasoning capabilities to determine the completed plans she will construct from a given partial description.

[1]  W. Kintsch The role of knowledge in discourse comprehension : a construction-integration model , 1991 .

[2]  Robert Dale Generating referring expressions - constructing descriptions in a domain of objects and processes , 1992, ACL-MIT press series in natural language processing.

[3]  Daniel S. Weld,et al.  UCPOP: A Sound, Complete, Partial Order Planner for ADL , 1992, KR.

[4]  Austin Tate,et al.  Generating Project Networks , 1977, IJCAI.

[5]  Marilyn A. Walker,et al.  The Effect of Resource Limits and Task Complexity on Collaborative Planning in Dialogue , 1995, Artif. Intell..

[6]  Susan M. Haller Interactive generation of plan descriptions and justifications , 1995 .

[7]  Jennifer Chu-Carroll,et al.  Recognizing and Utilizing User Preferences in Collaborative Consultation Dialogues , 1994 .

[8]  J. M. Golding,et al.  Superordinate goal inferences: Are they automatically generated during comprehension? , 1993 .

[9]  Johanna D. Moore,et al.  Decomposition and Causality in Partial-order Planning , 1994, AIPS.

[10]  P. Dixon The structure of mental plans for following directions. , 1987 .

[11]  Alfred Kobsa,et al.  The Fourth International Conference on User Modeling , 1996 .

[12]  Cécile Paris,et al.  Expressing Procedural Relationships in Multilingual Instructions , 1994, INLG.

[13]  Keith Neil Vander Linden Speaking of actions: choosing rhetorical status and grammatical form in instructional text generation , 1993 .

[14]  T. Trabasso,et al.  Causal thinking and the representation of narrative events , 1985 .

[15]  Arthur C. Graesser,et al.  Incorporating inferences in narrative representations: A study of how and why , 1981, Cognitive Psychology.

[16]  Robert Dale,et al.  Computational Interpretations of the Gricean Maxims in the Generation of Referring Expressions , 1995, Cogn. Sci..

[17]  Martha E. Pollack,et al.  Decomposition and Causality in Partial Order Planning Decomposition and Causality in Partial-order Planning , 1994 .

[18]  A. Graesser,et al.  Question answering in the context of stories , 1991 .

[19]  Chris Mellish,et al.  Natural Language Generation from Plans , 1989, Comput. Linguistics.

[20]  Subbarao Kambhampati,et al.  Planning as Refinement Search: A unified framework for comparative analysis of Search Space Size and Performance , 1995 .