Intelligent Dialogue Research Articles

Intelligent computer-based assessment and psychotherapy. An expert system for sexual dysfunction.

New and converging developments in the areas of artificial intelligence, intelligent tutoring systems, and cognitive therapy have made possible a new approach to computer-assisted assessment and psychotherapy. This new approach combines the capacity for intelligent therapeutic dialogue with the presentation of individualized therapeutic interventions. Previous attempts at computerized psychotherapy are reviewed to highlight a newly developed rule-based expert system, Sexpert, which assesses and treats sexual dysfunction. Preliminary observations concerning couples' reaction to and acceptance of Sexpert are presented.

Communicating With High-Level Plans

This paper provides support for the following points regarding the design of intelligent interfaces (or more generally, intelligent dialog systems): 1) Constraints of human dialog processing, including limited attention span and partial understanding, should be dealt with explicitly in design of intelligent dialog systems; 2) An intelligent dialog system should be a partly autonomous agent, though accountable to its users; 3) An intelligent dialog system should be designed to incorporate explicit active models of tasks, users, the system itself and the process of dialog with the user; 4) Models should be built and maintained both for types of tasks, users and dialog processes and for specific instances for tasks, users and dialogs. In particular, an intelligent dialog system should model users in terms of their individual human characteristics; 5) The configuration of models maintained by an intelligent interface should be self referencing. That is, the system's model of itself, which is a component of the model configuration, should be able to refer to the model configuration as a whole, and should be able to access the assertions in that configuration; and 6) Dialog processes should be modeled from a first-party (system) view and the system's second-party view of the user, rather than from a third-party (observer's) view.

Surveying projects on intelligent dialogue

Four projects developing intelligent dialogue systems are surveyed, including work at Bolt Beranek and Newman, at Carnegie Mellon University (the XCALIBUR project), at the University of Hamburg (the H AM-ANS project), and at SRI International (the KLAUS project). The projects are compared using an evaluation method involving eight aspects of intelligent dialogue: Control, Models, Connectivity, Modality, Form, Knowledge Representation and Inferencing, Knowledge Acquisition, and External Information Sources and Targets. The evaluation method used is proposed as a standard method for comparing and rating intelligent dialogue systems.

Toward intelligent dialogue with ISIS

A proposal for the design of intelligent dialogue systems is developed within the context of the work on SDBMS, a Spatial DataBase Management System, part of the ISIS project at the Canadian Defence and Civil Institute of Environmental Medicine. The approach uses the Models aspect of Edwards & Mason's (1988 a ) methodology as an organizing principle for design, including the two central notions of explicit-model design and a self-referencing model configuration . Further, a design space is presented that combines the aspects and dimensions of the methodology in order to provide clarity of focus for the developer who must consider a multitude of options in designing and implementing intelligent systems. Aspects of the methodology particularly important to the design and development of intelligent dialogue systems are discussed, namely, Connectivity, Control, Form and Modality. The design methodology is elaborated through discussions and recommendations for how it might be applied in building future versions of SDBMS.

ISIS: the interactive spatial information system

Spatial display, especially dynamic spatial display, may help the symbiosis between human intuition and computer logic. An interactive spatial information system (ISIS) can be designed to support this symbiosis. It can act as a decision support system both by aiding the user to discover options as well as by assisting in their evaluation. An ISIS should be able to perform intelligent operations on its data, detecting inconsistencies between new and old information, assisting in the evaluation of plans, and so forth. DCIEM has developed a miniature ISIS called SDBMS-1, using an extension of a commercial relational database management system. It allows the user to interact by keyboard, voice, or graphic gesture, and provides output alphanumerically or graphically. The information consists of topographic data from digitized standard maps and synthetic tactical data representing military operations. SDBMS-1 has been implemented using MASCOT technology, to permit easy modification as a consequence of experience. Development of an improved ISIS requires analysis of the nature of the human-computer dialogue and the potential contribution of artificial intelligence. Ideas on “intelligent dialogue”, and better methods for browsing are explored in the context of ISIS.

Talking to machines

Research has been in progress now for over 40 years to develop machines that will recognise natural speech. The author discusses the problems of speech coding, recognition and synthesis. Research aimed at improving the analysis of the original speech and subsequent synthesis, and progress to date are discussed. The use of intelligent conversational dialogue and future developments are also discussed. >

Design of Intelligent Dialogue in Decision Support Systems

This article deals with the question of the nature of the interactive dialogue which should take place in any good DSS, with the ways to easily design and implement it (actually leading to the idea of a dialogue generator) and with the features of such dialogues which require the use of Artificial Intelligence to fully play its role of effective interactivity. It stresses the opinion that in the short-term business oriented DSS will benefit less of Artificial Intelligence techniques at the level of its core functionalities than at the level of the interactive dialogue it offers

Toward intelligent product information systems for consumers

Telecommunication, video, and artificial intelligence technologies are supporting new product information systems capable of an increasingly intelligent dialog with consumers. The success of these new systems, just as with all past systems, depends on consumers' perceiving more benefits than costs from using them. Many of the new sophisticated systems may not succeed, and some have already failed, because their benefits cannot be made to exceed their costs. Especially important are nonmonetary costs like information processing effort and frustrating or tedious use experiences. The impact of the new technologies on information providers is discussed, as is the role of consumer-oriented policy makers in influencing the development of new product information systems.

Engineering an intelligent voice dialogue controller

This paper examines some of the practical difficulties faced by the engineer trying to develop machine intelligence for a commercial system — a voice-operated database inquiry system for the public telephone network. The decisions taken during this project are discussed to highlight some advantages and disadvantages of exploiting machine intelligence techniques.

Intelligent dialogue based on statistical models of clinical decision-making.

The independence Bayesian model has been used widely in computer programs designed to support clinical decision-making. A reasoning strategy has been developed to enable these programs to conduct clinically pertinent dialogue and explain their reasoning. It has been implemented in a program for the diagnosis of acute abdominal pain based on the Bayesian model of de Dombal et al. Several features of the dialogue design have been adopted from artificial intelligence research, including shared initiative and critiquing. The program adopts a flexible goal-driven strategy, attempting to confirm the clinician's diagnosis or rule out the likeliest alternative. Symptoms and signs are selected in order of their expected weights of evidence in favour of the hypothesized disease.

Intelligent help in a one-shot dialog

A database of 150 interactions conducted via electronic mail was analyzed. The database had been constructed as an on-line tool for users and advisors, but the interactions can also be regarded as modelling intelligent help dialog in which posing a query and providing a response are each accomplished in “one-shot”. The types of questions users ask and the advisory strategies employed for imcomplete queries without follow-up questioning are described. The goal is to understand this new on-line tool for advising and its implications as a model of one-shot intelligent help dialogs.

Intelligent help in a one-shot dialog

A database of 150 interactions conducted via electronic mail was analyzed. The database had been constructed as an on-line tool for users and advisors, but the interactions can also be regarded as modelling intelligent help dialog in which posing a query and providing a response are each accomplished in “one-shot”. The types of questions users ask and the advisory strategies employed for imcomplete queries without follow-up questioning are described. The goal is to understand this new on-line tool for advising and its implications as a model of one-shot intelligent help dialogs.

Designing a conversational speech interface

The implementation of conversational speech interfaces based on the use of an intelligent frame-based dialogue controller is described. This approach, in conjunction with the automatic generation of syntactic constraints and a simple semantic template grammar parser, is shown to allow practical user-friendly voice-based information inquiry systems to be built using current connected word speech recognition technology.

Conducting intelligent business dialog

Purposeful dialog is a fundamental management responsibility. The author defines the purpose of dialog as discussing problems and their solutions, and he offers ideas about the structure of intelligent dialog: defining the problem, gathering and interpreting facts, considering alternatives, and reaching decisions. Often reaching decisions depends not so much on our ability to change others' opinions as it does on our willingness to change our own. Effective dialog requires the ability to disagree without being disagreeable.

Citizen participation in the public policy issues involving acoustical science and technology

Citizen participation in scientific and technological decision making has only recently been recognized as an essential ingredient of the overall democratic governmental process, affecting millions of people in this country and abroad. Examples of significant national debates involving bureaucrats, professionals and public at large during the nineteen seventies on such major issues as nuclear power, DNA research and environmental pollution, provide the basis for similar dialogues in the future on other science and technology activities of regional and national concern, impact or controversy. Among these new candidates is the one involving acoustical science and technology. This paper attempts to identify and analyze those controversial programs and activities within the acoustics field that might have significant impact on the present and future course of governmental decision-making process. In addition, the author proposes a few models/mechanisms that might help facilitate intelligent and constructive dialog between the nontechnical community on one side and scientific/technological community on the other, hopefully resulting in realistic, acceptable, and manageable decisions at all levels of public/government interactions. The two acoustical science and technology areas specifically discussed are environmental/occupational noise and medical ultrasonics vis-a-vis their associated public policy issues of health, welfare, and safety.

TALKING TO TEACHERS ABOUT SOCIAL DIALECTS

Linguists have recently become aware of the agonizing problems faced by school children who speak non‐standard English. When these children learn to read, they must cope not only with a certain amount of linguistic interference, but also with the severely deprecatory attitudes of their teachers toward their dialect. Linguists have a responsibility to help teachers learn more about the nature of dialectical variability and, in particular, about non‐standard English. Helping teachers is often difficult, however, for they start with assumptions about language that differ so radically from the assumptions of linguists that it is sometimes difficult to achieve an intelligible dialogue. Linguists must find ways to make their knowledge meaningful to teachers. They must not bury teachers in technical complexities but offer their insights in ways that will strike the teacher as relevant to the practical concerns of their teaching. Some personal experiences are recounted that may help other linguists to avoid certain pitfalls as they try to enter into communication with teachers.