Roger C. Schank

Tell me a story : a new look at real and artificial memory

Schank takes a look at the human side of intelligence: thinking, memory, imagination, imagery, and mythology. A bold attempt at showing how the mind assimilates knowledge and how that knowledge is retrieved--a process similar in both humans and machines.

The structure of episodes in memory

Publisher Summary This chapter discusses that the process of understanding is, in large part, the assigning of new input conceptualizations to causal sequences and the inference of remembered conceptualizations that will allow for complete causal chains. Information is organized within episodic sequences and these episodic sequences serve to organize understanding. The simplest kind of episodic sequence is the script that organizes information about everyday causal chains that are part of a shared knowledge of the world. Human understanding, then, is a process by which new information gets treated in terms of the old information already present in memory. The chapter presents an argument for a combination of the notions of semantic memory and episodic memory. The basis of human memory is the conceptualization. Internally, the conceptualization is action-based with certain specified associative links between actions and objects. Externally, conceptualizations can relate to other conceptualizations within a context or episodic sequence.

Language and memory

This paper outlines some of the issues and basic philosophy that have guided my work and that of my students in the last ten years. It describes the progression of conceptual representational theories developed during that time, as well as some of the research models built to implement those theories. The paper concludes with a discussion of my most recent work in the area of modelling memory. It presents a theory of MOPs (Memory Organization Packets), which serve as both processors and organizers of information in memory. This enables effective categorization of experiences in episodic memory, which in turn enables better predictive understanding of new experiences.

Interestingness: Controlling inferences☆

Abstract : The problem of controlling inference is one of the most serious in Artificial Intelligence. New types of goal and plan inferences seriously compound the problem. This paper attempts to outline one possible solution to controlling inferences, namely following what is interesting and ignoring what is not. (Author)

Transcending inductive category formation in learning

The inductive category formation framework, an influential set of theories of learning in psychology and artificial intelligence, is deeply flawed. In this framework a set of necessary and sufficient features is taken to define a category. Such definitions are not functionally justified, are not used by people, and are not inducible by a learning system. Inductive theories depend on having access to all and only relevant features, which is not only impossible but begs a key question in learning. The crucial roles of other cognitive processes (such as explanation and credit assignment) are ignored or oversimplified. Learning necessarily involves pragmatic considerations that can only be handled by complex cognitive processes. We provide an alternative framework for learning according to which category definitions must be based on category function. The learning system invokes other cognitive processes to accomplish difficult tasks, makes inferences, analyses and decides among potential features, and specifies how and when categories are to be generated and modified. We also examine the methodological underpinnings of the two approaches and compare their motivations.

Creativity and learning in a case-based explainer

Abstract Explanation-based learning (EBL) is a very powerful method for category formation. Since EBL algorithms depend on having good explanations, it is crucial to have effective ways to build explanations, especially in complex real-world situations where complete causal information is not available. When people encounter new situations, they often explain them by remembering old explanations, and adapting them to fit. We believe that this case-based approach to explanation holds promise for use in AI systems, both for routine explanation and to creatively explain situations quite unlike what the system has encountered before. Building new explanations from old ones relies on having explanations available in memory. We describe explanation patterns (XPs), knowledge structures that package the reasoning underlying explanations. Using the SWALE system as a base, we discuss the retrieval and modification process, and the criteria used when deciding which explanation to accept. We also discuss issues in learning XPs: what generalization strategies are appropriate for real-world explanations, and which indexing strategies are appropriate for XPs. SWALEs explanations allow it to understand nonstandard stories, and the XPs it learns increase its efficiency in dealing with similar anomalies in the future.

Active learning through multimedia

As a child, did you learn how to walk by taking a walking class? No. Children learn by doing. Then why force them into passivity in school? Properly designed educational software on multimedia computers supports active participation and puts the student in control. Such software demands the right teaching architecture, as explained here.<<ETX>>

Rules and Topics in Conversation

Rules of conversation are given that specify what can follow what. A system for deciding what makes a reasonable subject for a conversation is shown. Topics are discussed and rules for topic shift are presented.

What's the Point?*

We present a theory of conversation comprehension in which a line of the conversation is “understood” by relating it to one of seven possible “points”. We define these points, and present examples where it seems plausible that the failure to “get the point” would indeed constitute a failure to understand the conversation. We argue that the recognition of such points must proceed in both a top down and bottom up fashion, and thus is likely to be quite complicated. Finally, we see the processing of information in the conversation to be dependent upon which point classification the user decides upon.

Inference and the computer understanding of natural language.

The notion of computer understanding of natural language is examined relative to inference mechanisms designed to function in a language-free deep conceptual base (Conceptual Dependency). The conceptual analysis of a natural language sentence into this conceptual base, and the nature of the memory which stores and operates upon these conceptual structures are described from both theoretical and practical standpoints. The various types of inferences which can be made during and after the conceptual analysis of a sentence are defined, and a functioning program which performs these inference tasks is described. Actual computer output is included.