This paper examines the issues that arise in the control of blackboard systems for applications with large and complicated search spaces by analyzing the evolution of blackboard control architectures. We feel that the issues addressed here apply more generally to AI application domains involving complex multi-dimensional search, in which control knowledge is as important to successful problem solving as domain knowledge. Evolution is viewed largely from the context of the Hearsay-II (HSII) speech understanding system. The appeal of the blackboard model is that it provides great flexibility in structuring problem solving. On the other hand, many of the features that are responsible for this flexibility make effective control difficult because they complicate the process of estimating the expected value of potential actions. Among the key themes in the evolution of blackboard control is the development of mechanisms that support more sophisticated goal-directed reasoning. In the basic co...

One of the major deterrents to productivity in industry today is the inability to effectively manage and control production. The problem is particularly acute in job shop environments where plant operation is routinely characterized by high

A text-based and spoken language processing framework based on the Constraint Dependency Grammar (CDG) developed by Maruyama [24, 25] is discussed. The scope of CDG is expanded to allow for the analysis of sentences containing lexically ambiguous words, to allow feature analysis in constraints, and to efficiently process multiple sentence candidates that are likely to arise in spoken language processing. The benefits of the CDG parsing approach are summarized. Additionally, the development of CDG grammars using our grammar tools and parser is discussed.

Abstract not found

Conventional behaviors develop from practice for regularly occurring problems of coordination within a community of actors. Re-using and extending conventional methods for coordinating behavior is the task of everyday reasoning. The

The question of how to integrate language models with speech recognition systems is becoming more important as speech recognition technology matures. For the purposes of this paper, we have classified the level of integration of current and past approaches into three categories: tightly-coupled, loosely-coupled, or semicoupled systems. We then argue that loose coupling is more appropriate given the current state of the art and given that it allows one to measure more precisely which components of the language model are most important. We will detail how the speech component in our approach interacts with the language model and discuss why we chose our language model. 1 Introduction State of the art speech recognition systems achieve high recognition accuracies only on tasks that have low perplexities. The perplexity of a task is, roughly speaking, the average number of choices at any decision point. The perplexity of a task is at a minimum when the true language model is known and co...

Distributed planning requires both architectures for structuring multiple planners and techniques for planning, communication, and cooperation. We describe a family of systems for distributed control of multiple aircraft, in which each aircraft plans its own flight path and avoids collisions with other aircraft. AUTOPILOT, the kernel planner used by each aircraft, comprises several processing "experts " that share a common world model. These experts sense the world, plan and evaluate flight paths, communicate with other aircraft, and control plan execution. We discuss four architectures for the distribution of airspace management and planning responsibility among the several aircraft occupying the airspace at any point in time. The architectures differ in the extent of cooperation and communication among aircraft. 1.

This paper investigates the effects of parallelism on blackboard system scheduling. A parallel blackboard system is described that allows multiple knowledge source instantiations to execute in parallel using a shared-memory blackboard approach. New classes of control knowledge are defined that use information about the relationships between system goals to schedule tasks — this control knowledge is implemented in the DVMT application on a Sequent multiprocessor using BBl-style control heuristics. The usefulness of the heuristics is examined by comparing the effectiveness of problem-solving with and without the heuristics (as a group and individually). Problem solving with the new control knowledge results in increased processor utilization and decreased total execution time. 1

The focus of this thesis proposal is to improve the ability of a computational system to understand spoken utterances in a dialogue with a human. Available computational methods for word recognition do not perform as well on spontaneous speech as we would hope. Even a state of the art recognizer achieves slightly worse than 70% word accuracy on (nearly) spontaneous speech in a conversation about a specific problem. To address this problem, I will explore novel methods for post-processing the output of a speech recognizer in order to correct errors. I adopt statistical techniques for modeling the noisy channel from the speaker to the listener in order to correct some of the errors introduced there. The statistical model accounts for frequent errors such as simple word/word confusions and short phrasal problems (one-to-many word substitutionsand many-to-one word concatenations). To use the model, a search algorithm is required to find the most likely correction of a given word sequence ...

This paper is an initial foray into the surprising range of exotic forms that composition may take. We list six key issues in thinking about kinds of compositionality. We do not pretend that our list is complete, and each of the issues raised could be explored in much greater detail. Nevertheless, even as it stands the list provides a healthy new perspective on compositional representation in cognitive science. It turns out that there is, in fact, a wide range of kinds of compositional representation. We prefer to speak, in a metaphorical fashion, of a large space of forms of compositional representation, a space whose dimensions are the fundamental properties that give rise to different forms of compositionality. For the most part, cognitive scientists building models of cognitive functioning have utilized representations drawn only from one narrow region of this space, a region centered on static, concatenative kinds of representation such as printed sentences and LISP data structures. Recently, various connectionists have been exploring some other regions, building models with representations exhibiting very different kinds of compositionality. But there are vast tracts of the space of possible compositional representations which remain almost totally unexplored in cognitive modeling.