This paper describes the Corinna system which integrates a theoretical approach to dialogue modeling with text generation techniques, to conduct cooperative dialogues in natural language. It is shown how the dialogue model COR can be augmented by adding discourse relations as an additional level of description which is particularly valuable for the generation of dialogue acts.

In this paper we present our research on identifying and modeling the strategies that human tutors use for integrating previous explanations into current explanations. We have used this work to develop a computational model that has been partially implemented in an explanation facility for an existing tutoring system known as SHERLOCK. We are implementing a system that uses case-based reasoning to identify previous situations and explanations that could potentially affect the explanation being constructed. We have identified heuristics for constructing explanations that exploit this information in ways similar to what we have observed in instructional dialogues produced by human tutors.

Patient compliance is a significant problem and is strongly correlated with the patients ’ understanding of their condition and prescribed treatment. Since doctors typically do not have large amounts of time to educate patients, and impersonal, voluminous patient handouts are largely ineffective, we propose the use of a sophisticated computer-based information system to generate tailored, interactive handouts to communicate with patients. Our system uses text planning and user modeling techniques to generate natural language descriptions of migraine, its symptoms, triggering factors and prescriptions. The system is capable of handling follow-up questions requesting further information, and generating responses in the context of previously supplied information – a capability unavailable in previous patient information systems. The system tailors its interaction to: (i) the class of migraine patients, (ii) the individual patient, and (iii) the previous dialogue. Preliminary evaluation of the system indicates that patients find it useful and informative. More extensive evaluation is in progress.

This paper investigates how the vision of the Semantic Web can be carried over to the realm of email. We introduce a general notion of semantic email, in which an email message consists of a structured query or update coupled with corresponding explanatory text. Semantic email opens the door to a wide range of automated, email-mediated applications with formally guaranteed properties. In particular, this paper introduces a broad class of semantic email processes. For example, consider the process of sending an email to a program committee, asking who will attend the PC dinner, automatically collecting the responses, and tallying them up. We define both logical and decision-theoretic models where an email process is modeled as a set of updates to a data set on which we specify goals via certain constraints or utilities. We then describe a set of inference problems that arise while trying to satisfy these goals and analyze their computational tractability. In particular, we show that for the logical model it is possible to automatically infer which email responses are acceptable w.r.t. a set of constraints in polynomial time, and for the decision-theoretic model it is possible to compute the optimal message-handling policy in polynomial time. In addition, we show how to automatically generate explanations for a process’s actions, and identify cases where such explanations can be generated in polynomial time. Finally, we discuss our publicly available implementation of semantic email and outline research challenges in this realm. 1

In this paper, we present a new approach to support the decision of selecting one object out of a set of alternatives. As compared to previous approaches, the distinctive feature of our approach is that neither the user, nor the system need to build a model of user's preferences. Our proposal is to integrate a system for interactive data exploration and analysis with a multimedia explanation facility. The explanation facility supports the user in understanding unexpected aspects of the data. The explanation generation process is guided by a causal model of the domain that is automatically acquired by the system. Introduction With the rapid increase in the amount of on-line, up-to-date information, more and more people, ranging from professional public-policy decision makers to common people, will base their decisions on on-line sources. Thus, there is an increasing need for software systems that support interactive, information-intensive decision making for different user populations ...

This proposal paper is being presented in partial fulfillment of the Ph.D. requirements of the Department of Computer and Information Sciences at the University of Delaware. In this paper, I discuss a user modeling architecture for ICICLE, a natural language system intended for use as a writing tutor for deaf learners of written English. This proposed design, intended to model dynamic aspects of a learner over the passage of time, the acquisition of new knowledge, and multiple sessions with the system, includes components to track the history of interaction with a given user as well as a very complex, dynamic model of user interlanguage grammar and domain knowledge. It has been based on research in language acquisition and in the acquisition of cognitive skills. The focus of the work described in this proposal is the development of the model of interlanguage status, which will be used in the analysis of user language production and in the generation of user-tailored explanations. Conte...

Adapting explanations to users with varying background knowledge and abilities is a difficult task: the explanation content, style, amount of details, terms used, etc. may be affected in various ways. We have used our analysis of the information seeking tasks of the users in one particular domain as a basis for adaptation. We structured the domain information into a set of information entities where each entity describes one aspect of a node in the information space. Each information entity is fitted to one or several information seeking tasks, and by combining entities we create an explanation adapted to the user's current task. We do not avoid concepts which are unknown to the user in our information entities. Instead we allow the users to ask follow-up questions on those concepts in order to cater the users' differences in background knowledge. Which follow-up questions are available also depends on the users' current task. Finally, we emphasise the need to make the difference betwe...

The development of intelligent agents is a key part of the Semantic Web vision, but how does an ordinary person tell an agent what to do? One approach to this problem is to use RDF templates that are authored once but then instantiated many times by ordinary users. This approach, however, raises a number of challenges. For instance, how can templates concisely represent a broad range of potential uses, yet ensure that each possible instantiation will function properly? And how does the agent explain its actions to the humans involved? This paper addresses these challenges in the context of a case study carried out on our fully-deployed system for semantic email agents. We describe how highlevel features of our template language enable the concise specification of flexible goals. In response to the first question, we show that it is possible to verify, in polynomial time, that a given template will always produce a valid instantiation.

Sharing and reuse of knowledge bases is recognized

Good communication is vital in healthcare, both among healthcare professionals, and between healthcare professionals and their patients. And well-written documents, describing and/or explaining the information in structured databases may be easier to comprehend, more edifying and even more convincing, than the structured data, even when presented in tabular or graphic form. Documents may be automatically generated from structured data, using techniques from the field of natural language generation. These techniques are concerned with how the content, organisation and language used in a document can be dynamically selected, depending on the audience and context. They have been used to generate health education materials, explanations and critiques in decision support systems, and medical reports and progress notes. Key words: natural language processing, communication, information systems, applications of medical informatics. Reprint requests and communication should be sent to: Alison ...