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)

Understanding novel phrases (e.g. upside‐down daisy) and classifying objects in categories named by phrases ought to have common properties, but you'd never know it from current theories. The best candidate for both jobs is the Theory Theory, but it faces difficulties when theories are impoverished. A potential solution is a dual approach that couples theories (representations‐about categories) with fixed mentalese expressions (representations‐of categories). Both representations combine information in parallel when understanding phrases. Although there are objections to the notion that theories (...) can combine, some of them lose their force when applied to a suitable dual model. (shrink)

Syntactic semantics is a holistic, conceptual-role-semantic theory of how computers can think. But Fodor and Lepore have mounted a sustained attack on holistic semantic theories. However, their major problem with holism (that, if holism is true, then no two people can understand each other) can be fixed by means of negotiating meanings. Syntactic semantics and Fodor and Lepore’s objections to holism are outlined; the nature of communication, miscommunication, and negotiation is discussed; Bruner’s ideas about the negotiation of meaning are explored; (...) and some observations on a problem for knowledge representation in AI raised by Winston are presented. (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)

It is almost universally acknowledged that first-order logic (FOL), with its clean, well-understood syntax and semantics, allows for the clear expression of philosophical arguments and ideas. Indeed, an argument or philosophical theory rendered in FOL is perhaps the cleanest example there is of “representing philosophy”. A number of prominent syntactic and semantic properties of FOL reflect metaphysical presuppositions that stem from its Fregean origins, particularly the idea of an inviolable divide between concept and object. These presuppositions, taken at face value, (...) reflect a significant metaphysical viewpoint, one that can in fact hinder or prejudice the representation of philosophical ideas and arguments. Philosophers have of course noticed this and have, accordingly, sought to alter or extend traditional FOL in novel ways to reflect a more flexible and egalitarian metaphysical standpoint. The purpose of this paper, however, is to document and discuss how similar “adaptations” to FOL—culminating in a standardized framework known as Common Logic —have evolved out of the more practical and applied encounter of FOL with the problem of representing, sharing, and reasoning upon information on the World Wide Web. (shrink)

KRISP is a representation system and set of interpretation protocols that is used in the Sparser natural language understanding system to embody the meaning of texts and their pragmatic contexts. It is based on a denotational notion of semantic interpretation, where the phrases of a text are directly projected onto a largely pre-existing set of individuals and categories in a model, rather than first going through a level of symbolic representation such as a logical form. It defines a small set (...) of semantic object types, grounded in the lambda calculus, and it supports the principle of uniqueness and supplies first class objects to represent partially-saturated relationships.KRISP is being used to develop a core set of concepts for such things as names, amounts, time, and modality, which are part of a few larger models for domains including Who''s News and joint ventures. It is targeted at the task of information extraction, emphasizing the need to relate entities mentioned in new texts to a large set of pre-defined entities and those read about in earlier articles or in the same article. (shrink)

We examine the problem of generating definite noun phrases that are appropriate referring expressions; that is, noun phrases that (a) successfully identify the intended referent to the hearer whilst (b) not conveying to him or her any false conversational implicatures (Grice, 1975). We review several possible computational interpretations of the conversational implicature maxims, with different computational costs, and argue that the simplest may be the best, because it seems to be closest to what human speakers do. We describe our recommended (...) algorithm in detail, along with a specification of the resources a host system must provide in order to make use of the algorithm, and an implementation used in the natural language generation component of the IDAS system. (shrink)

This article describes an ontological model of norms. The basic assumption is that a substantial part of a legal system is grounded on the concept of agency. Since a legal system aims at regulating a society, then its goal can be achieved only by affecting the behaviour of the members of the society. We assume that a society is made up of agents (which can be individuals, institutions, software programs, etc.), that agents have beliefs, goals and preferences, and that they (...) commit to intentions in order to choose a line of behaviour. The role of norms, within a legal system, is to specify how and when the chosen behaviour agrees with the basic principles of the legal system. In this article, we show how a model based on plans can be the basis for the ontological representation of norms, which are expressed as constraints on the possible plans an agent may choose to guide its behaviour. Moreover, the paper describes how the proposed model can be linked to the upper level of a philosophically well-founded ontology (DOLCE); in this way, the model is set in a wider perspective, which opens the way to further developments. (shrink)

Computational models of meaning trained on naturally occurring text successfully model human performance on tasks involving simple similarity measures, but they characterize meaning in terms of undifferentiated bags of words or topical dimensions. This has led some to question their psychological plausibility (Murphy, 2002;Schunn, 1999). We present here a fully automatic method for extracting a structured and comprehensive set of concept descriptions directly from an English part‐of‐speech‐tagged corpus. Concepts are characterized by weighted properties, enriched with concept–property types that approximate classical (...) relations such as hypernymy and function. Our model outperforms comparable algorithms in cognitive tasks pertaining not only to concept‐internal structures (discovering properties of concepts, grouping properties by property type) but also to inter‐concept relations (clustering into superordinates), suggesting the empirical validity of the property‐based approach. (shrink)

Computational models of meaning trained on naturally occurring text successfully model human performance on tasks involving simple similarity measures, but they characterize meaning in terms of undifferentiated bags of words or topical dimensions. This has led some to question their psychological plausibility (Murphy, 2002;Schunn, 1999). We present here a fully automatic method for extracting a structured and comprehensive set of concept descriptions directly from an English part‐of‐speech‐tagged corpus. Concepts are characterized by weighted properties, enriched with concept–property types that approximate classical (...) relations such as hypernymy and function. Our model outperforms comparable algorithms in cognitive tasks pertaining not only to concept‐internal structures (discovering properties of concepts, grouping properties by property type) but also to inter‐concept relations (clustering into superordinates), suggesting the empirical validity of the property‐based approach. (shrink)

We describe a knowledge representation and inference formalism, based on an intensional propositional semantic network, in which variables are structures terms consisting of quantifier, type, and other information. This has three important consequences for natural language processing. First, this leads to an extended, more natural formalism whose use and representations are consistent with the use of variables in natural language in two ways: the structure of representations mirrors the structure of the language and allows re-use phenomena such as pronouns and (...) ellipsis. Second, the formalism allows the specification of description subsumption as a partial ordering on related concepts (variable nodes in a semantic network) that relates more general concepts to more specific instances of that concept, as is done in language. Finally, this structured variable representation simplifies the resolution of some representational difficulties with certain classes of natural language sentences, namely, donkey sentences and sentences involving branching quantifiers. The implementation of this formalism is called ANALOG (A NAtural LOGIC) and its utility for natural language processing tasks is illustrated. (shrink)