This paper describes Rapture | a system for revising probabilistic rule bases that converts symbolic rules into a connectionist network, which is then trained via connectionist techniques. It uses a modiied version of backpropagation to reene the certainty factors of the rule base, and uses ID3's information-gain heuristic (Quinlan, 1986) to add new rules. Work is currently under way for nding ...

An attribute-oriented rough set method for knowledge discovery in databases is described. The method is based on information generalization, which examines the data at various levels of abstraction, followed by the discovery, analysis and simplification of significant data relationships. First, an attribute-oriented concept tree ascension technique is applied to generalize the information; this...

A Radial Basis Boltzmann Machine (RBBM) is a specialized Boltzmann Machine architecture that combines feed-forward mapping with probability estimation in the input space, and for which very efficient learning rules exist. The hidden representation of the network displays symmetry breaking as a function of the noise in the dynamics. Thus, generalization can be studied as a function of the noise ...

A general statistical model for the prediction of pronunciation given the orthographic transcript or the canonical pronunciation of a spoken utterance is described. The model is based on a Markov process that can be derived from a set of statistically weighted re-write rules. The automatic learning of such re-write rules based on annotated speech data is illustrated. One possible application of...

A new scheme of knowledge encoding in a fuzzy multilayer perceptron (MLP) using rough set-theoretic concepts is described. Crude domain knowledge is extracted from the data set in the form of rules. The syntax of these rules automatically determines the appropriate number of hidden nodes while the dependency factors are used in the initial weight encoding. The network is then refined during tra...

This paper applies type-based Markov Chain Monte Carlo (MCMC) algorithms to the problem of learning Synchronous Context-Free Grammar (SCFG) rules from a forest that represents all possible rules consistent with a fixed word alignment. While type-based MCMC has been shown to be effective in a number of NLP applications, our setting, where the tree structure of the sentence is itself a hidden var...

This paper reports two experiments on the implicit learning of second language word stress rules and presents a methodological innovation. In both experiments L1 Cantonese L2 English participants practised pronouncing two-syllable Spanish words. Learning of a hidden stress regularity was measured by a judgment task. We assessed participants’ awareness of the stress rule by verbal reports, confi...

As a side effect of unprecedented amount of digitization of data, classical retrieval tools found themselves unable to go further beyond the tip of the Iceberg. Data Mining in conjunction with the Formal Concept Analysis, is a clear promise to furnish adequate tools to do so and specially to be able to derive concise generic and easy understandable bases of ”hidden” knowledge, that can be relia...

To have learned the morphology of a natural language is to have the capacity both to recognize and to produce words consisting of novel combinations of familiar morphemes. Most recent work on the acquisition of morphology takes the perspective of production, but it is receptive morphology which comes first in the child. This paper presents a connectionist model of the acquisition of the capacit...