The Workshop on Future Directions in NLP was held at Bolt Beranek and Newman, Inc. (BBN), in Cambridge, Massachusetts, from 29 November to 1 December 1989. The workshop was organized and hosted by Madeleine Bates and Ralph Weischedel of the BBN Speech and Natural Language Department and sponsored by BBN's Science Development Program. Thirty-six leading researchers and government representatives gathered to discuss the direction of the field of natural language processing (NLP) over the next 5 to 10 years. The intent of the symposium was "to make the conference and resulting volume an intellectual landmark for the field of NLP." This brief article summarizes the invited papers and strategic planning discussions of the workshop.

As Hofstadter points out, analogies are fluid, meaning that the analogy between two entities can be drawn differently depending on how these entities are represented. The analogy that is drawn, in turn, can change the representation of the entities being compared. Thus, the analogy between Hofstadter and Sagan can be seen as positive: Both have explained important concepts in their fields to a wide audience and transmitted the excitement of these ideas. Both have inspired a number of people within their fields. Unfortunately, a more negative analogy between Sagan and Hofstadter is possible.

The Third International Workshop on Human and Machine Cognition was held in Seaside, Florida, on 13-15 May 1993. Each paper session included presentations on cognitive research, educational research, AI theory and logic, and particular knowledge engineering projects. This mixture encouraged the participants from diverse disciplines to listen and respond to one another. These international workshops are held to allow leading scientists, scholars, and practitioners to discuss current issues and research in particular topics in AI and cognitive science. These international workshops are held every other year to allow leading scientists, scholars, and practitioners to discuss current issues and research in particular topics in AI and cognitive science. This third workshop was supported by the University of West Florida; the West Florida Regional Medical Center; Taylor and Francis Publishing; John Wiley and Sons Publishers; the American Association for Artificial Intelligence; and the ...

Articulating thought in computerbased media is a powerful means for humans to develop their understanding of phenomena. We have created DynaLearn, an intelligent learning environment that allows learners to acquire conceptual knowledge by constructing and simulating qualitative models of how systems behave. DynaLearn uses diagrammatic representations for learners to express their ideas. The environment is equipped with semantic technology components that are capable of generating knowledge-based feedback and virtual characters that enhance the interaction with learners. Teachers have created course material, and successful evaluation studies have been performed.

A variety of proposals for preferred methodological approaches has been advanced in the recent artificial intelligence (AI) literature Rather than advocating a particular approach, this article attempts to explain the apparent confusion of efforts in the field in terms of differences among underlying methodological perspectives held by practicing researchers The article presents a review of such perspectives discussed in the existing literature and then considers a descriptive and relatively specific typology of these differing research perspectives. Studies are reported in a wide range of publications. While some focus on the field (e.g., Artzficial Intelligence), others are concerned with different research areas (e.g., Behavzoral and Brain Sczences). Perhaps, as others have pointed out, "there are undoubtedly some views AI simply adds to the prevailing sense of confusion. AI research, which have been previously reported in .

This article summarizes a workshop entitled "Detecting, Repairing, and Preventing Human-Machine Miscommunication," held on 4 August 1996 in Portland, Oregon. The author presents the significant issues raised during the four specific workshop sessions. Research related to achieving robust interaction is an important subarea in AI. Early work concerned the correction of spelling or grammatical errors in a user's utterance so that the system could more easily match them against a fixed linguistic model; work has also been done in the area of speech recognition, attempting to find the best fit of a sound signal to legal sequences of linguistic objects. All these approaches have assumed that the system's model is always correct.

This article proposes connectionism as an alternative to classical cognitivism in understanding design. The goals of design research are varied, and the sources of its methods of inquiry are diverse, calling on such areas as history, hermeneutics, sociology, psychology, philosophy, and computing. This article proposes connectionism as an alternative to classical cognitivism in understanding design. It also considers the difficulties encountered within a particular view of the role of explanations and typologies. Connectionism provides an alternative model that does not depend on the articulation of explanations and typologies.

Although there are designers who claim design is a mysterious activity not amenable to scientific examination, research into design continues Although there are publications by designers on how to design dating back to Roman times, notably by Vitruvius, the nineteenthcentury design thinkers actually began work on articulating design as a process (Durand 1802). However, it was not until the 1960s that major research programs were initiated. These programs were originally founded on the systems view and used concepts from operations research (Jones and Thornley 1963). More recently, information-processing models founded on AI concepts have provided an impetus for renewed research into design in its various aspects (Simon 1969; Coyne et al. 1990). Many foundational ideas in AI are proving to be useful in developing formal models of design as an activity.

Design problem solving is a complex activity involving a number of subtasks and a number of alternative methods potentially available for each subtask. The structure of tasks has been a key concern of recent research in task-oriented methodologies for knowledge-based systems (Chandrasekaran 1986; Clancey 1985; Steels 1990; McDermott 1988). One way to conduct a task analysis is to develop a task structure (Chandrasekaran 1989) that lays out the relation between a task, applicable methods for it, the knowledge requirements for the methods, and the subtasks set up by them. I propose a task structure for design by analyzing a general class of methods that I call proposecritique-modify methods. The task structure is constructed by identifying a range of methods for each task.

In this editorial introduction to this special issue of AI Magazine on qualitative reasoning, we briefly discuss the main motivations and characteristics of this branch of AI research. We also summarize the contributions in this issue and point out challenges for future research. Successful application areas include autonomous spacecraft support, failure analysis and on-board diagnosis of vehicle systems, automated generation of control software for photocopiers, and intelligent aids for learning about thermodynamic cycles. Qualitative reasoning is thus relevant for researchers who are interested in important AI issues as well as for managers, developers, and engineers who are looking for potential industrial benefits of AI. A decade has passed since the publication of three collections of papers and a book covering the foundations of the field (Weld and de Kleer 1990), the status at that time (Faltings and Struss 1992; Williams and de Kleer 1991), and a comprehensive treatment of qualitative simulation (Kuipers 1994).