The Lumi`ere Project centers on harnessing probability and utility to provide assistance to computer software users. We review work on Bayesian user models that can be employed to infer a user's needs by considering a user's background, actions, and queries. Several problems were tackled in Lumi`ere research, including (1) the construction of Bayesian models for reasoning about the time-varying goals of computer users from their observed actions and queries, (2) gaining access to a stream of events from software applications, (3) developing a language for transforming system events into observational variables represented in Bayesian user models, (4) developing persistent profiles to capture changes in a user's expertise, and (5) the development of an overall architecture for an intelligent user interface. Lumi`ere prototypes served as the basis for the Office Assistant in the Microsoft Office '97 suite of productivity applications. 1 Introduction Uncertainty is...

Abstract not found

Abstract. This paper describes the student modeling component of ANDES, an Intelligent Tutoring System for Newtonian physics. ANDES ’ student model uses a Bayesian network to do long-term knowledge assessment, plan recognition and prediction of students ’ actions during problem solving. The network is updated in real time, using an approximate anytime algorithm based on stochastic sampling, as a student solves problems with ANDES. The information in the student model is used by ANDES ’ Help system to tailor its support when the student reaches impasses in the problem solving process. In this paper, we describe the knowledge structures represented in the student model and discuss the implementation of the Bayesian network assessor. We also present a preliminary evaluation of the time performance of stochastic sampling algorithms to update the network. 1

Abstract. When a tutoring system aims to provide students with interactive help, it needs to know what knowledge the student has and what goals the student is currently trying to achieve. That is, it must do both assessment and plan recognition. These modeling tasks involve a high level of uncertainty when students are allowed to follow various lines of reasoning and are not required to show all their reasoning explicitly. We use Bayesian networks as a comprehensive, sound formalism to handle this uncertainty. Using Bayesian networks, we have devised the probabilistic student models forAndes, a tutoring system forNewtonian physics whose philosophy is to maximize student initiative and freedom during the pedagogical interaction. Andes’ models provide long-term knowledge assessment, plan recognition, and prediction of students’ actions during problem solving, as well as assessment of students ’ knowledge and understanding as students read and explain worked out examples. In this paper, we describe the basic mechanisms that allow Andes ’ student models to soundly perform assessment and plan recognition, as well as the Bayesian network solutions to issues that arose in scaling up the model to a full-scale, ¢eld evaluated application. We also summarize the results of several evaluations of Andes which provide evidence on the accuracy of its student models.

We present an approach to keyhole plan recognition which uses a dynamic belief (Bayesian) network to represent features of the domain that are needed to identify users' plans and goals. The application domain is a Multi-User Dungeon adventure game with thousands of possible actions and locations. We propose several network structures which represent the relations in the domain to varying extents, and compare their predictive power for predicting a user's current goal, next action and next location. The conditional probability distributions for each network are learned during a training phase, which dynamically builds these probabilities from observations of user behaviour. This approach allows the use of incomplete, sparse and noisy data during both training and testing. We then apply simple abstraction and learning techniques in order to speed up the performance of the most promising dynamic belief networks without a significant change in the accuracy of goal predictions. Our experi...

We discuss the construction of probabilistic models centering on temporal patterns of query refinement. Our analyses are derived from a large corpus of Web search queries extracted from server logs recorded by a popular Internet search service. We frame the modeling task in terms of pursuing an understanding of probabilistic relationships among temporal patterns of activity, informational goals, and classes of query refinement. We construct Bayesian networks that predict search behavior, with a focus on the progression of queries over time. We review a methodology for abstracting and tagging user queries. After presenting key statistics on query length, query frequency, and informational goals, we describe user models that capture the dynamics of query refinement.

We describe representation, inference strategies, and control procedures employed in an automated conversation system named the Bayesian Receptionist. The prototype is focused on the domain of dialog about goals typically handled by receptionists at the front desks of buildings on the Microsoft corporate campus. The system employs a set of Bayesian user models to interpret the goals of speakers given evidence gleaned from a natural language parse of their utterances. Beyond linguistic features, the domain models take into consideration contextual evidence, including visual findings. We discuss key principles of conversational actions under uncertainty and the overall architecture of the system, highlighting the use of a hierarchy of Bayesian models at different levels of detail, the use of value of information to control question asking, and application of expected utility to control progression and backtracking in conversation.

One of the most important problems for an intelligent tutoring system is deciding how to respond when a student asks for help. Responding cooperatively requires an understanding of both what solution path the student is pursuing, and the student's current level of domain knowledge. Andes, an intelligent tutoring system for Newtonian physics, refers to a probabilistic student model to make decisions about responding to help requests.

This paper presents the details of a student model that enables an open learning environment to provide tailored feedback on a learner’s exploration. Open learning environments have been shown to be beneficial for learners with appropriate learning styles and characteristics, but problematic for those who are not able to explore effectively. To address this problem, we have built a student model capable of detecting when the learner is having difficulty exploring and of providing the types of assessments that the environment needs to guide and improve the learner’s exploration of the available material. The model, which uses Bayesian Networks, was built using an iterative design and evaluation process. We describe the details of this process, as it was used to both define the structure of the model and to provide its initial validation.

Bayesian networks have been successfully applied to the assessment of user properties which remain unchanged during a session. However, many properties of a person vary over time, thus raising new questions of network modeling. In this paper we characterize different types of dependencies that occur in networks that deal with the modeling of temporally variable user properties. We show how existing techniques of applying dynamic probabilistic networks can be adapted for the task of modeling the dependencies in dynamic Bayesian networks. We illustrate the proposed techniques using examples of emergency calls to the fire department of the city of Saarbr ucken. The fire department officers are experienced in dealing with emergency calls from callers whose available working memory capacity is temporarily limited. We develop a model which reconstructs the officers' assessments of a caller's working memory capacity.