Explaining and repairing plans that fail

Hammond, Kristian J.

doi:10.1016/0004-3702(90)90040-7

Cited by 113 publications

(69 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In complex domains, planning is interleaved with evaluation to assess whether goals are fully satisfied or whether the achieved state contains 'objectionable results': in this case, a replanning step is needed, to avoid the undesirable effects or, as for Hammond's CHEF [22], to apply some repair heuristics to the plan. At the end of the planning process, a simulation step produces a detailed final state description: for example in CHEF's domain (cooking recipes) the state description involves the states of ingredients employed, compounds created and final products.…”

Section: Limitations Of Knowledge Representationmentioning

confidence: 99%

Refining instructional text generation after evaluation

Rosis

Grasso

Berry

1999

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

In this paper, we describe how user-adapted explanations about drug prescriptions can be generated from already existing data sources. We start by illustrating the two-step approach employed in the first version of the natural language generator and the limitations of generated texts, that we discovered through analytical and empirical evaluations. We claim that, although style refinement would be needed in these texts, particular care should be devoted to implementing some of the persuasion techniques that doctors employ in their explanations. This would require either thoroughly revising the text planning techniques employed or converting to a multistep generation architecture. We justify why we selected this second alternative and propose some heuristics to repair problems found in the first version of the generator. Some final considerations about the advantages of this approach and the possibility of generalizing it to other domains conclude the paper.

show abstract

Section: Limitations Of Knowledge Representationmentioning

confidence: 99%

Refining instructional text generation after evaluation

Rosis

Grasso

Berry

1999

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

show abstract

“…Other approaches, like "critics" in the CHEF system, are able to detect failures on a recipe and apply repair strategies (e.g. add or remove steps in the recipe [8]). This approach is based on analyzing the failure of the plan being executed (in the real world or a simulated world).…”

Section: Automatic Story Generationmentioning

confidence: 99%

Argument-Based Case Revision in CBR for Story Generation

Ontañón

Plaza

Zhu

2015

Case-Based Reasoning Research and Development

View full text Add to dashboard Cite

Abstract. This paper presents a new approach to case revision in casebased reasoning based on the idea of argumentation. Previous work on case reuse has proposed the use of operations such as case amalgamation (or merging), which generate solutions by combining information coming from different cases. Such approaches are often based on exploring the search space of possible combinations looking for a solution that maximizes a certain criteria. We show how Revise can be performed by arguments attacking specific parts of a case produced by Reuse, and how they can guide and prevent repeating pitfalls in future cases. The proposed approach is evaluated in the task of automatic story generation.

show abstract

“…There are currently no other alternatives. However, in other environments, simulators are also possible [26].…”

Section: Revise Modulementioning

confidence: 99%

eXiT*CBR: A framework for case-based medical diagnosis development and experimentation

López

Pous

Plà

et al. 2011

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

Objective: Medical applications have special features that require the development of particular tools. The eXiT*CBR framework is proposed to support the development of and experimentation with new case-based reasoning (CBR) systems for medical diagnosis. Email addresses: beatriz.lopez@udg.edu (Beatriz López), carles.pous@udg.edu (Carles Pous), pgay@eia.udg.edu (Pablo Gay), apla@eia.udg.edu (Albert Pla), juditsanzbuxo@gmail.com (Judith Sanz), jbrunet@iconcologia.net (Joan Brunet) Preprint submitted to Artificial Intelligence in MedicineApril 15, 2010 is managed automatically by the system. Used as a plug-in on the same interface, eXiT*CBR can work with any data mining technique such as learning the relevance of features. Results:The results show that eXiT*CBR is a user-friendly tool that facilitates physicians to use the CBR method to determine a diagnoses in the field of breast cancer, dealing with different patterns implicit in the data.

show abstract

Explaining and repairing plans that fail

Cited by 113 publications

References 7 publications

Refining instructional text generation after evaluation

Refining instructional text generation after evaluation

Argument-Based Case Revision in CBR for Story Generation

eXiT*CBR: A framework for case-based medical diagnosis development and experimentation

Contact Info

Product

Resources

About