We describe a computational model of how analogs are retrieved from memory using simultaneous satisfaction of a set of semantic, structural, and pragmatic constraints. The model is based on psychological evidence suggesting that human memory retrieval tends to favor analogs that have several kinds of correspondences with the structure that prompts retrieval: semantic similarity, isomorphism, and pragmatic relevance. We describe ARCS, a program that demonstrates how these constraints can be used to select relevant analogs by forming a network of hypotheses and attempting to satisfy the constraints simultaneously. ARCS has been tested on several data bases that display both its psychological plausibility and computational power.

Abstract not found

This paper proposes a method for measuring semantic similarity between words as a new tool for text analysis. The similarity is measured on a semantic network constructed systematically from a subset of the English dictionary, LDOCE (Longman Dictionary of Contemporary English). Spreading activation on the network can directly compute the similarity between any two words in the Longman Defining Vocabulary, and indirectly the similarity of all the other words in LDOCE. The similarity represents the strength of lexical cohesion or semantic relation, and also provides valuable information about similarity and coherence of texts. 1

Context-sensitivity is an important characteristic feature of every cognitive process and therefore should be reflected in every architecture pretending to explain human cognition. In this paper some experimental facts demonstrating context effects on various cognitive processes are reviewed and an attempt at context modeling is described. A hybrid (symbolic/connectionist) cognitive architecture, DUAL, is proposed. It consists of a multitude of agents having both a symbolic and a connectionist part. The symbolic part represents some knowledge structure, while the connectionist part represents its relevance to the current context. The performance of the cognitive system emerges as result of the work and interaction of the currently active agents, where the set of active agents is not predefined for a specific task but is dynamic and reflects the specific context. So particular symbolic operations and data structures may be supported or suppressed depending on the particu...

Hybrid Intelligent Systems that combine knowledge based and artificial neural network systems typically have four phases involving domain knowledge representation, mapping of this knowledge into an initial connectionist architecture, network training and rule extraction respectively. The final phase is important because it can provide a trained connectionist architecture with explanation power and validate its output decisions. Moreover, it can be used to refine and maintain the initial knowledge acquired from domain experts. In this paper, we present three rule extraction techniques. The first technique extracts a set of binary rules from any type of neural network. The other two techniques are specific to feedforward networks with a single hidden layer of sigmoidal units. Technique 2 extracts partial rules that represent the most important embedded knowledge with an adjustable level of detail, while the third technique provides a more comprehensive and universal approach. A rule eval...

This paper describes techniques for integrating neural networks and symbolic components into powerful hybrid systems. Neural networks have unique processing characteristics that enable tasks to be performed that would be di cult or intractable for a symbolic rule-based system. However, a stand-alone neural network requires an interpretation either by ahuman or a rulebased system. This motivates the integration of neural/symbolic techniques within a hybrid system. Anumber of integration possibilities exist: some systems consist of neural network components performing symbolic tasks while other systems are composed of several neural networks and symbolic components, each component acting as a self-contained module communicating with the others. Other hybrid systems are able to transform subsymbolic representations into symbolic ones and vice-versa. This paper providesanoverview and evaluation of the state of the artofseveral hybrid neural systems for rule-based processing. 1

The purpose of this book is to present a collection of papers that represents a broad spectrum of current research in learning methods for natural language processing, and to advance the state of the art in language learning and artificial intelligence. The book should bridge a gap between several areas that are usually discussed separately, including connectionist, statistical, and symbolic methods. In order to bring together new and different language learning approaches, we held a workshop at the International Joint Conference on Artificial Intelligence in Montreal in August 1995. Paper contributions were selected and revised after having been reviewed by at least twomembers of the international program committee as well as additional reviewers. This book contains the revised workshop papers and additional papers by members of the program committee. In particular this book focuses on current issues such as: -- How can we apply existing learning methods to language processing? -- What new learning methods are needed for language processing and why? -- What language knowledge should be learned and why?

This thesis is concerned with the development of an under-lying model of memory to support selective case retrieval for case-based reasoning. The major requirements are that retrieval should be highly flexible yet efficient. The traditional approach of "indexing" is rejected as being too restrictive while more flexible approaches in analogical reasoning are generally too computationally expensive. Several important organisational principles are developed in the memory model. A network representation is advocated with a number of required extensions; such as multi-granular representation, context-based segregation and a statistically-based grading of paths. The organisation of memory offers the potential for the serial performance of a number of retrieval tasks that have previously only been addressed by assuming a massively parallel implementation. The retrieval mechanism developed is a novel activation passing technique that creates a gradation of stored cases during retrieval. Empiri...

Introduction After a long and exhausting war between the representatives of the symbolic and connectionist approaches (this war stimulated, however, the clarification of the limitations and advantages of both approaches) a growing group of peace-makers emerged who tried to integrate the advantages of both approaches and to fill in the gap between them (Hendler, 1989a, Hinton, 1990, Barnden & Pollack, 1991, Thornton, 1991, Sun & Bookman, 1992, 1994, Dinsmore, 1992, Holyoak & Barnden, 1994). However, a mini-war started between the peace-makers themselves on the issue how to sign the peace treaty: with the surrender of one of the approaches or with their parity. Some researchers supported the connectionist-to-the-top view that symbol structures and symbol processing should emerge from the work of a neural network (called a unified approach in chapters 2 and 4 of this volume and connectionist symbol processing in (Pollack, 1990, Smolensky, 1990, Touretzky, 1990, Smolensky et al.,

We present a scheme for translating high-level descriptions of conceptual hierarchies into a neural network representation. The intuitive semantics of a conceptual hierarchy is provided by a Bayesian net, and the neural network implementation provably approximates the behaviour of this net under a stochastic simulation rule.