Abstract. We propose an approach to categorize real-world natural scenes based on a semantic typicality measure. The proposed typicality measure allows to grade the similarity of an image with respect to a scene category. We argue that such a graded decision is appropriate and justified both from a human’s perspective as well as from the image-content point of view. The method combines bottom-up information of local semantic concepts with the typical semantic content

this article. Address correspondence and reprint requests to Lera Boroditsky, Department of Psychology, Bldg. 420, Stanford University, Stanford, CA 94305-2130. E-mail to lera@psych. stanford.edu

Findings in recent research on the `conjunction fallacy ' have been taken as evidence that our minds are not designed to work by the rules of probability. This conclusion springs from the idea that norms should be content-blind Ð in the present case, the assumption that sound reasoning requires following the conjunction rule of probability theory. But content-blind norms overlook some of the intelligent ways in which humans deal with uncertainty, for instance, when drawing semantic and pragmatic inferences. In a series of studies, we ®rst show that people infer nonmathematical meanings of the polysemous term `probability' in the classic Linda conjunction problem. We then demonstrate that one can design contexts in which people infer mathematical meanings of the term and are therefore more likely to conform to the conjunction rule. Finally, we report evidence that the term `frequency ' narrows the spectrum of possible interpretations of `probability ' down to its mathematical meanings, and that this fact Ð rather than the presence or absence of `extensional cues ' Ð accounts for the low proportion of violations of the conjunction rule when people are asked for

Natural language processing will not be able to compete with traditional information retrieval unless high-coverage techniques are developed. It is commonly agreed that a poor encoding of the semantic lexicon is the bottleneck of many existing systems. A hand encoding of semantic knowledge on an extensive basis is not realistic; hence, it is important to devise methods by which such knowledge can be acquired in part or entirely by a computer. But what type of semantic knowledge could be automatically learned, from which sources, and by what methods? This paper explores the above issues and proposes an algorithm to learn syncategorematic concepts from text exemplars. What is learned about a concept is not its defining features, such as kinship, but rather its patterns of use. The knowledge acquisition method is based on learning by observations; observations are examples of word co-occurrences (collocations) in a large corpus, detected by a morphosyntactic analyzer. A semantic bias is used to associate collocations with the appropriate meaning relation, if one exists. Based upon single or multiple examples, the acquired knowledge is then generalized to create semantic rules on concept uses. Interactive human intervention is required in the training phase, when the bias is defined

A continuum between purely isolated and purely interrelated concepts is described. A concept is interrelated to the extent that it is influenced by other concepts. Methods for manipulating and identiying a concept's degree of interrelatedness are introduced. Relatively isolated concepts are empirically identified by a relatively large use of nondiagnostic features, and by better categorization performance for a concept's prototype than for a caricature of the concept. Relatively interrelated concepts are identified by minimal use of nondiagnostic features, and by better categorization performance for a caricature than a prototype. A concept is likely to be relatively isolated when: subjects are instructed to create images for their concepts rather than find discriminating features, concepts are given unrelated labels, and the categories that are displayed alternate rarely between trials. The entire set of manipulations and measurements supports a graded distinction between isolated and interrelated concepts. The distinction is applied to current models of category learning, and a connectionist framework for interpreting the empirical results is presented. Modern research on concept representation and learning has evolved from two traditions. One tradition connects concept acquisition with language in general and word learning in specific (Lakoff, 1986; Saussure, 1915/1959). Concepts are approximately equated with single words or phrases. In this tradition, for example, evidence that a child has acquired the adult concept of dog comes from the child's use of the word "dog" to designate dogs. The other tradition connects concept acquisition with object recognition (Biederman, 1987). From this perspective, concept learning involves learning to correctly cate...

Connectionist modeling offers a useful computational framework for exploring the nature of normal and impaired cognitive processes. The current work extends the relevance of connectionist modeling in neuropsychology to address issues in cognitive rehabilitation: the degree and speed of recovery through retraining, the extent to which improvement on treated items generalizes to untreated items, and how treated items are selected to maximize this generalization. A network previously used to model impairments in mapping orthography to semantics is retrained after damage. The degree of relearning and generalization varies considerably for different lesion locations, and has interesting implications for understanding the nature and variability of recovery in patients. In a second simulation, retraining on words whose semantics are atypical of their category yields more generalization than retraining on more typical words, suggesting a counterintuitive strategy for selecting items in patient therapy to maximize recovery. In a final simulation, changes in the pattern of errors produced by the network over the course of recovery is used to constrain explanations of the nature of recovery of analogous brain-damaged patients. Taken together, the findings demonstrate that the nature of relearning in damaged connectionist networks can make important contributions to a theory of rehabilitation in patients.

NUMERICAL -- REAL -- PHYSICAL -- NON-STATIONARY -- COLLECTIVE TEMPORAL -- RELATIONAL -- EVENT -- Table 1.

Abstract not found

A software system that automatically classifies MIDI files into hierarchically organized taxonomies of musical genres is presented. This extensible software includes an easy to use and flexible GUI. An extensive library of high-level musical features is compiled, including many original features. A novel hybrid classification system is used that makes use of hierarchical, flat and round robin classification. Both k-nearest neighbour and neural network-based classifiers are used, and feature selection and weighting are performed using genetic algorithms. A thorough review of previous research in automatic genre classification is presented, along with an overview of automatic feature selection and classification techniques. Also included is a discussion of the theoretical issues relating to musical genre, including but not limited to what mechanisms humans use to classify music by genre and how realistic genre taxonomies can be constructed.

The notion of type has played a double role in database systems in that it has been used both to describe values stored in the database and also concepts of the application domain. In the context of object data models, we argue for a clear separation of these two roles into typing and classification, respectively. Typing is concerned with database representation while classification is concerned with models of reality in terms of entity categories and their interdependencies. We discuss this distinction and the benefits that it affords in terms of both conceptual modelling and object data model genericity. 1 Introduction There has been much discussion on the role of "type" in the fields of Programming Languages, Data Models and Knowledge Representation (see for example [BMe84, BZ81]). The debate centres on such issues as whether "type" is an intensional or extensional notion. In the case where it is intensional, there are further differences as to whether it is definitional in that i...