Intelligent educational systems:
1. Task ontology based authoring system for training systems1.1 Task ontology based authoring system
1.2 An intelligent training system: SmartTrainer2. Framework for group learning: FITS/CSCL
3. General framework for ITS: FITS
4. Nonmonotonic inductive student modeling algorithms
1. Task ontology based authoring
system for training systems
Recently much attention has been paid to the notion of "ontology" in the expectation that it can serve as the new, strong foundation of knowledge engineering. In the conventional approach to theory of knowledge, to give the operational semantics of knowledge representation has been regarded as of major importance and the analysis of contents of knowledge has been considered to be subordinate to it. To solidify the foundation of knowledge engineering, however, the many researchers , especially in the field of knowledge sharing and reuse, has strongly felt necessity of the change of such a way of thinking. The key to the problem is to understand the essential interaction between "form" and "contents" on equal importance. This implies that deep understanding of "content" will give us new insight into design of knowledge representation. The notion of "ontology" can be key to this issue.
The ultimate goal of research on ontology is to give the full picture of theory of knowledge. To make improvements in the study of this difficult issue, of course, it is important to accumulate huge amount of "contents", and develop sophisticated ontology representation language as fundamental "form" of knowledge.
The same thing applies to the field of intelligent educational systems (IES). Building an IES requires a lot of work. At the present situation, however, it is always built from scratch. Little functional components are reusable and we cannot compare or assess the existing systems. Only existing contribution to the solution of the problem can be found in study of the authoring tools for educational systems. However, it is considered questionable whether substantial benefit for the authors engaged in the complex task may be expected or not, since most of existing authoring tools do not satisfy the requirements for the authoring tools as shown below.
We think the key to the solution of the problem is intelligent support based on "task ontology" which serves as a theory of vocabulary/concepts used as building blocks for knowledge-based systems. The issues here also include how to represent what we know about the fundamental characteristics of an IES as "task ontology" and how to integrate it into intelligent authoring tools. Our solution is integration of an ontology construction environment CLEPE as a part of the authoring tool we have developed. CLEPE provides us with all the functions needed to satisfy the requirements shown above.
The most important role of CLEPE is to lay the theoretical foundation for IES development process. It maintains continuity from authorﾕs conceptual understanding of educational task to the computational semantics of IESs. It provides human friendly vocabulary for authors to describe the educational task. For the authoring tools, on the other hand, it specifies the computational semantics of vocabulary and also provides a set of components represented in terms of both conceptual primitives and object-oriented code fragments.
The goals of our research on task ontology are to exemplify the benefits of task ontology through the development of an ontology based authoring tool for Computer Based Training (CBT) systems. In this paper, we will discuss the basic issues on the concept of task ontology and then describe the design principle of an ontology-based authoring tool for Computer Based Training (CBT) systems.
Major publications
To the list of all publications
SmartTrainer is a Computer Based Training System including a set of simulators in the area of Electric Power System. The target task of SmartTrainer is mainly to recover the accidents of substations in the electric power system. When an accident happens, the electric power transmission will be interrupted, and the operators should recover it as quickly as possible. The operators should find the spot of the accident, continue to supply the electric power to some special places such as hospital, police station at once by borrowing some power from the other substations, find the causes of the accident and recover it within the limited time.
The goal of the training oriented by SmartTrainer is to improve capability of not only skill-based or rule-based reasoning but also knowledge-based reasoning. The set of the scenarios incorporated into SmartTrainer has been designed by the experienced trainers.In order to let the trainee master the principled knowledge, SmartTrainer let them do practice first and then teach them the first principle behind it adaptively to their mistakes, and finally, check their learning result by practice(training) again. With the cycle of practice->knowledge->practice, teaching process is going forward. This is a form of ﾒlearning by doingﾓ.
Here we want to emphasize that the training we give to the trainee has the time-limitation just like in real accidents. Multi-media technique has been widely used in SmartTrainer to attain high fidelity, including the sound processor to create mock buzzer when an accident happens, the movie display to show the accident scene when the repairing man needs, the picture processor to create the static graphics of the various equipment, and so on.
SmartTrainer is composed of five parts, those are human interface, authoring, training model based on the training ontology, teaching materials model based on the teaching materials ontology and simulator. Here we will discuss the designing of authoring environment based on task ontology in SmartTrainer mainly
Major publications
To
the list of all publications
2.
Framework for group learning: FITS/CSCL
Computer Supported Collaborative Learning(CSCL) has recently been gathering much attention of many researchers. It is based on the idea that knowledge should not be simply transferred from a teacher to a learner but be built in a learner's head while interacting with each other in group activities. Although collaborative learning is not a new concept which has been carried out in classrooms for long time, it is expected to be a new promising paradigm in AI in ED community.
The advantages of CSCL are summarized as follows:
Although all of them are equally important, computers have nothing new to do with the first one. The last issue is interesting, but it is very ambitious, since it requires almost complete natural language understanding capability of computers in order to build an operational system. According to this observation, we take the second one as a target to realize in our research. Our research is mainly concerned with the following three major goals:
In order to achieve these goals, we do need a sophisticated vocabulary in terms of which we can describe objectives and modes of communication, decision models, knowledge for decision making, etc. This implies we first design ontology for CSCL. Needless to say, AI techniques based on symbolism need primitives or a set of basic vocabulary for representing knowledge and objects. They reflect conceptualization of systems under consideration. One might think that ontological issues must be far into domain and hence it is domain-specific and loses generality. By ontology, however, we mean a system of basic vocabulary usable across various domain knowledge, that is, "generic task". Working hypothesis of this research is that we can find a good ontology for CSCL task by looking at the task carefully from generic task point of view. What should be notice is to design a good ontology to represent the domain knowledge, the communication model, and the learning process model from the educational point of view. We are currently engaged in developing the intelligent support system for collaborative learning of physics domain.
Major publications
To the list of all publications
A large number of useful techniques which contribute to realization of educational activities have been proposed for the development of ITS. Those achievements contributed not only to the promotion of ITS research itself but also to the establishment of various fundamental techniques in artificial intelligence. It is only in recent years, however, that there have been discussions on the general problems in the design of ITS.
The major objective of this research is the enumeration of the computational agents needed for implementing reactive behavior of tutoring systems. The design and development of a domain-independent framework for ITS posing a number of questions such as "What kinds of inference schema are needed in ITS?", "What can be the framework to control the system?" , "There exist a domain-independent tutoring strategy?" and "What kind of role each domain knowledge should play? To answer these questions, it is necessary to view the problem in a top-down way based on the concept of gentric task. By generic task, we mean a system of domain-independent but task-dependent vocabulary, which is defined in both knowledge level and symbol level. The symbol level constructs of the generic task are referred to as building blocks. The final goal of this research is to provide the sophisticated building blocks for implementing integrated environments for teaching/learning systems.
In the current implementation, FITS , which stands for Framework for ITS, is composed of six building blocks, each of which covers an essential task for teaching. The functionality needed for the student model module, for example, is realized as a domain-independent inductive inference algorithm and that for the tutoring module is realized as twenty tutoring strategies, in which Socratic tutoring is included. FITS has been implemented successfully in Common ESP(Extended Self-contained Prolog) on a SPARC station. Two prototype systems concerning geography and chemical reactions have been implemented in the framework.
Major publications:
To the list of all publications
Student modeling is one of the most important topics of ITS research, because the behavior of an ITS largely depends on a student model which represents a snapshot of the student's knowledge. In this research, we formulate the student modeling problem as an inductive inference problem, i.e., a problem of constructing a model explaining observed data which are, in our case, student's answers to the problems given.
Tutoring is to guide students toward a better understanding of teaching material. This means that the learning process is essentially attained through the change of their minds and hence the consistency of student's answers can be easily lost. Therefore, student modeling methods should be able to automatically manage the consistency of student's answers in order to follow the student's change. Contradictions which a modeling system should cope with are classified into the following two types:
(1)contradictions which should be resolved by revising the student model, and
(2)contradictions which should be captured as they are.
Generally speaking, an ITS should follow a student's nonmonotonic change. A student modeling system should realize flexible modeling behavior and construct reasonable student models from didactic viewpoints by embodying a teacher's insight, e.g., the ability to capture her student's status by asking fewer questions. In order to cope with contradictions of type (1) which inevitably appear in the student modeling process, a student modeling system is required to have the ability to cope with various kinds of nonmonotonicities by making belief revisions to keep data for inference consistent.
HSMIS
We have been attacking this issue and developing an inductive student model inference algorithm HSMIS (Hypothetical Student Model Inference System) which employs the ATMS (Assumption-based Truth Maintenance System) (deKleer, 1986) to maintain consistency of the student modeling process (Ikeda et al,1988). The architecture of HSMIS is based on a logic-based inductive inference algorithm SMIS (Ikeda et al,1989), whose model description language is also a logic-based language called SMDL (Student Model Description Language) which takes four truth values to represent a student's understanding. Thus HSMIS realizes relatively high model representation power and modeling ability.
THEMIS
The second problem, that is, to capture a student's contradictory knowledge as it is, seems more important from educational viewpoints. The Socratic method, for example, is a contradiction-based tutoring strategy which teachers use especially to help students in the first stage of learning. In order to generate sophisticated tutoring behavior like the Socratic method, student modeling methods should be able to cover a student's contradictory knowledge.
THEMIS is a new nonmonotonic and inductive model inference system which incorporates de Kleer's ATMS as a vehicle for formulating both nonmonotonicities (contradictions). Two types of contradictions are formulated. Type (1) is named "single world contradiction" which is dealt with by HSMIS and type (2) is named "multi-world contradiction" which is dealt with by the structure of a concept discrimination tree. In the newly formulated THEMIS, ATMS plays another important role of managing multiple worlds which enable the modeling of students with contradictions.
Major publications:
To the list of all publications