A fundamental difficulty faced by groups of agents that work together is how to efficiently coordinate their efforts. This paper presents techniques that allow heterogeneous agents to more efficiently solve coordination problems by acquiring procedural knowledge. In particular, each agent autonomously learns coordinated procedures that reflect her contributions towards successful past joint beh...

This paper depicts theoretical results obtained in the line of projects related to constructing dialogue applications based on a formal cognitive model of a human-machine dialogue. One of the aims of the paper is to propose an appropriate model of question-answering dialogue, which can be used in designing relevant computer software. The theory proposes formal descriptions of declarative and pr...

We propose how to extract procedural knowledge rather than declarative knowledge utilizing machine learning method with deep language processing features in scientific documents, as well as how to model it. We show the representation of procedural knowledge in PubMed abstracts and provide experiments that are quite promising in that it shows 82%, 63%, 73%, and 70% performances of purpose/soluti...

This study provides conceptual and empirical arguments why an assessment of applicants' procedural knowledge about interpersonal behavior via a video-based situational judgment test might be valid for academic and postacademic success criteria. Four cohorts of medical students (N = 723) were followed from admission to employment. Procedural knowledge about interpersonal behavior at the time of ...

Many of the knowledge representation schemes developed in the past have concentrated on declarative knowledge. Many have provided assertional mechanisms for deductive retrieval and some give terminological mechanisms for classification and abstraction. However, none present the system developer with similar sophistication, at a high level of representation, in procedural knowledge. Often the de...

This paper proposes a methodology for learning joint probability estimates regarding the effect of sensorimotor features on the predicated quality of desired behavior. These relationships can then be used to choose actions that will most likely produce success. relational dependency networks are used to learn statistical models of procedural task knowledge. An example task expert for picking up...

User generatedWeb content includes large amounts of procedural knowledge (also called how to knowledge). This paper is on a comparison of two extraction methods for procedural knowledge from the Web. Both methods create workflow representations automatically from text with the aim to reuse the Web experience by reasoning methods. Two variants of the workflow extraction process are introduced an...

A ssessment is an indispensable aspect of academic life a natural partner to curriculum and a central component in medical education (1). Aside from its core objective of gauging student performance, assessment is also crucial for documenting the attainment of learning outcomes, verifying medical competence and, ultimately, minimizing risks to patients arising from an unsatisfactory knowledge b...

We introduce an adversarial planning algorithm based on game tree search, which is applicable in large-scale multiplayer domains. In order to tackle the scalability issues of game tree search, the algorithm utilizes procedural knowledge capturing how individual players tend to achieve their goals in the domain; the information is used to limit the search only to the part of the game tree that i...

Since the l a s t I JCAI , the PLANNER problem s o l v i n g fo rma l i sm has con t i nued to deve lop . Our ep ls temo lgy f o r the f ounda t i ons f o r problem s o l v i n g has been ex tended . An overv iew of the f o rma l i sm Is g iven from an I n f o r m a t i o n p rocess ing v i e w p o i n t . A s imp le example Is e x p l a i n e d us ing snapshots of the s t a t e of the problem ...