Between a Rock and a Hard Place : Cognitive Science Principles Meet AI Hard Problems

semanticscholar(2006)

引用 3|浏览1
暂无评分
摘要
Different notions of argument historically have played a central role in artificial intelligence to model the diagnostic reasoning and decision making of medical experts. However, it was beyond the scope of that research to address information needs of the layperson. It was assumed that a medical expert, trained to interpret explanations produced by a system, would mediate between system and layperson. The goal of this symposium was to investigate the role of argumentation in future intelligent health-care systems, especially focusing on systems designed to interact directly with health-care consumers. The symposium brought together researchers from a variety of subfields of AI such as decision support, multiagent systems, computational models of natural argument, embodied conversational agents, and natural language text generation, in addition to researchers in fields providing empiriThe American Association for Artificial Intelligence, in cooperation with Stanford University’s Computer Science Department, was pleased to present its 2006 Spring Symposium Series held March 27–29, 2006, at Stanford University, California. The titles of the eight symposia were (1) Argumentation for Consumers of Health Care (chaired by Nancy Green); (2) Between a Rock and a Hard Place: Cognitive Science Principles Meet AI Hard Problems (chaired by Christian Lebiere); (3) Computational Approaches to Analyzing Weblogs (chaired by Nicolas Nicolov); (4) Distributed Plan and Schedule Management (chaired by Ed Durfee); (5) Formalizing and Compiling Background Knowledge and Its Applications to Knowledge Representation and Question Answering (chaired by Chitta Baral); (6) Semantic Web Meets e-Government (chaired by Ljiljana Stojanovic); (7) To Boldly Go Where No Human-Robot Team Has Gone Before (chaired by Terry Fong); and (8) What Went Wrong and Why: Lessons from AI Research and Applications (chaired by Dan Shapiro). cal or theoretical foundations (including health communication, argumentation, social psychology, cognitive psychology, psycholinguistics, and human factors). One major theme of papers presented at the symposium was health behavior change support systems, interactive systems designed to encourage users in activities such as healthy eating and exercise. (These papers continued a major theme of the AAAI 2004 fall symposium on health dialog systems.) The symposium also included two invited talks on this theme. A talk given by Stacy Marsella (University of Southern California / Information Sciences Institute) focused on the use of behavioral theory and emotion modeling in design of pedagogical dialogue systems. A talk given by B. J. Fogg (Stanford University) outlined general principles of persuasion in human-computer interaction. Another major theme was normative argument in health care, from decision-support systems for medical experts to systems generating patient-tailored explanations designed for the health-care consumer. The papers on this theme described systems using a variety of models of argument (such as from argument theorists such as Toulmin and Walton). Several papers provided analyses of argument patterns found in actual medical discourse. Although the use of argument in such systems has a different purpose than in health behavior change systems, the symposium participants discussed the potential need to consider a patient’s emotional state in presenting normative arguments to patients. The third theme of the symposium was linguistic and cognitive factors in effective communication of medical information. These papers served to remind the participants that the language, layout, and graphics in which an argument is conveyed can affect the audience’s comprehension of the argument and that presentation factors can even be manipulated to prevent an audience from accurately assessing negative information. The symposium participants discussed how interest in argumentation is growing but is still fragmented among many fields and how the symAAAI 2006 Spring Symposium Reports
更多
查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要