This paper is a commentary on the target article by Lokendra Shastri & Venkat Ajjanagadde [S&A]: “From simple associations to systematic reasoning: A connectionist representation of rules, variables and dynamic bindings using temporal synchrony” in same issue of the journal, pp.417–451. -/- It puts S&A's temporal-synchrony binding method in a broader context, comments on notions of pointing and other ways of associating information - in both computers and connectionist systems - and mentions types of reasoning that are a challenge to (...) S&A's system (amongst many other connectionist systems, recognizing that S&A's is much more capable as regards reasoning than most other contemporary systems). (shrink)

L'informatique se définissant comme le traitement rationnel de l'information par machine automatique et l'intelligence se caractérisant par une même capacité de traitement rationnel, il était inévitable que l'on songe à associer l'intelligence au traitement automatique de l'information. C'est ce qu'a fait John McCarthy en forgeant le terme d'intelligence artificielle. Par «intelligence artificielle» on peut vouloir exprimer l'ambition de1. Recréer, transformer ou développer l'intelligence artificiellement2. Simuler l'intelligence en la reconstituant dans des modéles imitant certains aspects de notre intelligence dite naturelle.

In this paper a logical interpretation of semantic nets and graph grammars is proposed for modelling natural language understanding and creating language understanding computer systems. An example of parsing a Finnish question by graph grammars and inferring the answer to it by a semantic net representation is provided.

Situational irony concerns what it is about a situation that causes people to describe it as ironic. Although situational irony is as complex and commonplace as verbal and literary irony, it has received nowhere near the same attention from cognitive scientists and other scholars. This paper presents the bicoherence theory of situational irony, based on the theory of conceptual coherence (Kunda & Thagard, 1996; Thagard & Verbeurgt, 1998). On this theory, a situation counts as ironic when it is conceived as (...) having a bicoherent conceptual structure, adequate cognitive salience, and evokes an appropriate configuration of emotions. The theory is applied to a corpus of 250 examples of situational ironies gathered automatically from electronic news sources. A useful taxonomy of situational ironies is produced, new predictions and insights into situational irony are discussed, and extensions of the theory to other forms of irony are examined. (shrink)

An integrated statement is made concerning the semantic status of nodes in a propositional semantic network, claiming that such nodes represent only intensions. Within the network, the only reference to extensionality is via a mechanism to assert that two intensions have the same extension in same world. This framework is employed in three application problems to illustrate the nature of its solutions.The formalism used here utilizes only assertional information and no structural, or definitional, information. This restriction corresponds to many of (...) the psychologically motivated network models. Some of the psychological implications of network processes called node merging and node splitting are discussed. Additionally, it is pointed out that both our networks and the psychologically based networks are prone to memory confusions about knowing unless augmented by domain‐specific inference processes, or by structural information. (shrink)

This paper describes KRL, a Knowledge Representation Language designed for use in understander systems. It outlines both the general concepts which underlie our research and the details of KRL‐0, an experimental implementation of some of these concepts. KRL is an attempt to integrate procedural knowledge with a broad base of declarative forms. These forms provide a variety of ways to express the logical structure of the knowledge, in order to give flexibility in associating procedures (for memory and reasoning) with specific (...) pieces of knowledge, and to control the relative accessibility of different facts and descriptions. The formalism for declarative knowledge is based on structured conceptual objects with associated descriptions. These objects form a network of memory units with several different sorts of linkages, each having well‐specified implications for the retrieval process. Procedures can be associated directly with the internal structure of a conceptual object. This procedurul attachment allows the steps for a particular operation to be determined by characteristics of the specific entities involved.The control structure of KRL is based on the belief that the next generation of intelligent programs will integrate data‐directed and goal‐directed processing by using multiprocessing. It provides for a priority‐ordered multiprocess agenda with explicit (user‐provided) strategies for scheduling and resource allocation. It provides procedure directories which operate along with process frameworks to allow procedural parameterization of the fundamental system processes for building, comparing, and retrieving memory structures. Future development of KRL will include integrating procedure definition with the descriptive formalism. (shrink)

This paper studies the relationship of Artificial Intelligence to the study of language and the representation of the underlying knowledge which supports the comprehension process. It develops the view that intelligence is based on the ability to use large amounts of diverse kinds of knowledge in procedural ways, rather than on the possession of a few general and uniform principles. The paper also provides a unifying thread to a variety of recent approaches to natural language comprehension. We conclude with a (...) brief discussion of how Artificial Intelligence may have a radical impact on education if the principles which it utilizes to explore the representation and use of knowledge are made available to the student to use in his own learning experiences. (shrink)

Although the connectionist approach has lead to elegant solutions to a number of problems in cognitive science and artificial intelligence, its suitability for dealing with problems in knowledge representation and inference has often been questioned. This paper partly answers this criticism by demonstrating that effective solutions to certain problems in knowledge representation and limited inference can be found by adopting a connectionist approach. The paper presents a connectionist realization of semantic networks, that is, it describes how knowledge about concepts, their (...) properties, and the hierarchical relationship between them may be encoded as an interpreter‐free massively parallel network of simple processing elements that can solve an interesting class of inheritance and recognition problems extremely fast—in time proportional to the depth of the conceptual hierarchy. The connectionist realization is based on an evidential formulation that leads to principled solutions to the problems of exceptions and conflicting multiple inheritance situations during inheritance, and the best‐match or partial‐match computation during recognition. The paper also identifies constraints that must be satisfied by the conceptual structure in order to arrive at an efficient parallel realization. (shrink)

This study presents original evidence that abstract and concrete concepts are organized and represented differently in the mind, based on analyses of thousands of concepts in publicly available data sets and computational resources. First, we show that abstract and concrete concepts have differing patterns of association with other concepts. Second, we test recent hypotheses that abstract concepts are organized according to association, whereas concrete concepts are organized according to (semantic) similarity. Third, we present evidence suggesting that concrete representations are more (...) strongly feature-based than abstract concepts. We argue that degree of feature-based structure may fundamentally determine concreteness, and we discuss implications for cognitive and computational models of meaning. (shrink)

Human agents draw a variety of inferences effortlessly, spontaneously, and with remarkable efficiency – as though these inferences were a reflexive response of their cognitive apparatus. Furthermore, these inferences are drawn with reference to a large body of background knowledge. This remarkable human ability seems paradoxical given the complexity of reasoning reported by researchers in artificial intelligence. It also poses a challenge for cognitive science and computational neuroscience: How can a system of simple and slow neuronlike elements represent a large (...) body of systemic knowledge and perform a range of inferences with such speed? We describe a computational model that takes a step toward addressing the cognitive science challenge and resolving the artificial intelligence paradox. We show how a connectionist network can encode millions of facts and rules involving n-ary predicates and variables and perform a class of inferences in a few hundred milliseconds. Efficient reasoning requires the rapid representation and propagation of dynamic bindings. Our model (which we refer to as SHRUTI) achieves this by representing (1) dynamic bindings as the synchronous firing of appropriate nodes, (2) rules as interconnection patterns that direct the propagation of rhythmic activity, and (3) long-term facts as temporal pattern-matching subnetworks. The model is consistent with recent neurophysiological evidence that synchronous activity occurs in the brain and may play a representational role in neural information processing. The model also makes specific psychologically significant predictions about the nature of reflexive reasoning. It identifies constraints on the form of rules that may participate in such reasoning and relates the capacity of the working memory underlying reflexive reasoning to biological parameters such as the lowest frequency at which nodes can sustain synchronous oscillations and the coarseness of synchronization. (shrink)

Contemporary epistemology has assumed that knowledge is represented in sentences or propositions. However, a variety of extensions and alternatives to this view have been proposed in other areas of investigation. We review some of these proposals, focusing on (1) Ryle's notion of knowing how and Hanson's and Kuhn's accounts of theory-laden perception in science; (2) extensions of simple propositional representations in cognitive models and artificial intelligence; (3) the debate concerning imagistic versus propositional representations in cognitive psychology; (4) recent treatments of (...) concepts and categorization which reject the notion of necessary and sufficient conditions; and (5) parallel distributed processing (connectionist) models of cognition. This last development is especially promising in providing a flexible, powerful means of representing information nonpropositionally, and carrying out at least simple forms of inference without rules. Central to several of the proposals is the notion that much of human cognition might consist in pattern recognition rather than manipulation of rules and propositions. (shrink)

Some thoughts just come to mind together. This is usually thought to happen because they are connected by associations, which the mind follows. Such an explanation assumes that there is a particular kind of simple psychological process responsible. This view has encountered criticism recently. In response, this paper aims to characterize a general understanding of associative simplicity, which might support the distinction between associative processing and alternatives. I argue that there are two kinds of simplicity that are treated as characteristic (...) of association, and as a result three possible versions of associative processing. This provides a framework that informs our understanding of association as a current and historical concept, including how various specific versions in different parts of psychology relate to one another. This framework can also guide debates over normative evaluations of actions produced by processes thought to be associative. (shrink)

Conventional behaviors develop from practice for regularly occurring problems of coordination within a community of actors. Reusing and extending conventional methods for coordinating behavior is the task of everyday reasoning.The computational model presented in the paper details the emergence of convention in circumstances where there is no ruling body of knowledge developed by prior generations of actors within the community to guide behavior. The framework we assume combines social theories of cognition with human information processing models that have been developed (...) within Cognitive Science. The model presented reflects both elements of the framework. Conventional behaviors are partially coded in the predisposition of participants in a joint activity to expect certain points of coordination to develop during the course of the activity. The expected points of coordination that are commonly assumed form a design for an activity. Because of uncertainty, interruptions, and numerous other opportunities to get off‐track and out‐of‐synch, the participants must work jointly and continuously to achieve conventional coordination.One feature of the model is that the community improves its performance despite the fact that individual actors reason independently about their experiences. Another important feature of the model is that the mechanisms for improving behavior are tied to the memory function of individual actors. A third important feature is that the social interaction among the participants simplifies and drives the everyday reasoning processes. An analysis of a large set of computational experiments supports the theoretical position that is developed regarding everyday reasoning and convention. (shrink)

The demise of behaviorism has made ethologists more willing to ascribe mental states to animals. However, a methodology that can avoid the charge of excessive anthropomorphism is needed. We describe a series of experiments that could help determine whether the behavior of nonhuman animals towards dead conspecifics is concept mediated. These experiments form the basis of a general point. The behavior of some animals is clearly guided by complex mental processes. The techniques developed by comparative psychologists and behavioral ecologists are (...) able to provide us with the tools to critically evaluate hypotheses concerning the continuity between human minds and animal minds. (shrink)

Standard psychological scaling methods have been widely used as knowledge elicitation tools to uncover structural characteristics of a given domain. However, these methods traditionally rely on relatedness ratings from human experts, which is often time-consuming and tedious. We describe an integrated approach to knowledge elicitation and representation using Latent Semantic Analysis and Pathfinder Network Scaling techniques. The semantic structure of a subject domain can be automatically characterised from a collection of published documents in the domain. The method is illustrated with (...) an example of organising a digital library in accordance to latent semantic structures. (shrink)

The resolution of ambiguities is one of the central problems for Machine Translation. In this paper we propose a knowledge-based approach to disambiguation which uses Description Logics (dl) as representation formalism. We present the process of anaphora resolution implemented in the Machine Translation systemfast and show how thedl systemback is used to support disambiguation.The disambiguation strategy uses factors representing syntactic, semantic, and conceptual constraints with different weights to choose the most adequate antecedent candidate. We show how these factors can be (...) declaratively represented as defaults inback. Disambiguation is then achieved by determining the interpretation that yields a qualitatively minimal number of exceptions to the defaults, and can thus be formalized as exception minimization. (shrink)

Establishing reasonable, prior distributions remains a significant obstacle for the construction of probabilistic expert systems. Human assessment of chance is often relied upon for this purpose, but this has the drawback of being inconsistent with axioms of probability. This article advances a method for extracting a coherent distribution of probability from human judgment. The method is based on a psychological model of probabilistic reasoning, followed by a correction phase using linear programming.

The paper examines locative expressions and shows that an adequate account of their meaning must be based on two essential understandings: First, the simple spatial relation, often given as the meaning of the spatial prepositions, is only an “ideal” from which there are deviations in context; second, a level of “geometric conceptualization” mediates between “the world as it is” and language. Pragmatic “near principles” are formulated to explain some deviations from the ideal and several other apparent irregularities of prepositional use. (...) A set of “use types” of the ideal meaning is proposed to account for conventional aspects of locative meaning. The paper concludes with a discussion of the consequences of this description of locative expressions for artificial intelligence and linguistics. (shrink)

Starting with the facts that not everything that is understood is remembered, and that not everything that is remembered is understood. this paper urges that models of language processing should be able to make a distinction between comprehension and memory. To this end. a case is made for a spreading activation process as being the essential ingredient of the comprehension process. It is argued that concepts activated during comprehension not only restrict the search set for candidate concepts to be used (...) in a top‐down fashion, they also constitute part of an episodic representation that can come to be p e of long‐term memory. The way in which these representations atrophy is discussed, as is the way in which their idiosyncratic components are eliminated in producing representations in semantic memory. Some observations on the comprehension and memory of text are made and arguments are presented to show how intrusions and omissions in recall can be handled. Some existing experimental data is reanalyzed in terms of the proposed model and alternative interpretations consistent with the model are shown to be possible. (shrink)