{An associative lexical net is built up whose weights are computed on the basis of the co-occurrences of words using Hebb's rule. The co-occurrences of word pairs are determined by shifting a window over a large body of text. To estimate the associative response to a given stimulus word the corresponding node is activated and its activity is propagated in the net. Our model assumes that words w...

Descriptions of Groups using Formal Language Theory Gabriela Aslı Rino Nesin This work treats word problems of finitely generated groups and variations thereof, such as word problems of pairs of groups and irreducible word problems of groups. These problems can be seen as formal languages on the generators of the group and as such they can be members of certain well-known language classes, such...

The paper describes a language-independent approach for semiautomatic extension of lexical-semantic word nets and evaluates the method on CoreNet, the Korean version of word net. In a bootstrapping fashion, the socalled ‘Pendulum Algorithm’ operates on word sets obtained by co-occurrence statistics on a large un-annotated corpus and keeps error propagation low by a verification step. Results ar...

A three layer back propagation neural net is set up to study the functional dependency between the semantic class of a bisyllabic Chinese word and that of its two constituent Chinese characters. Simulations were performed using a three-layer back-propagation neural net with various combination of inputs. The inputs are (1) semantic classes of the constituent characters, (2) Entropy of the chara...

Die ontwikkeling van gemeenskapsgesondheidsdienste vir die Arabiese plattelandse bevolking in Israel sedert 1948 word bespreek. Daar word veral gekyk na die ervarings van die verpleegkundiges, geneeshere en sanitêre werkers in die veld. Hulle het nie net met gesondheidsprobleme te kampe gehad nie, maar ook met talle kulturele struikelblokke in die lewering van voorkomende, genesende en rehabili...

The need for fast and accurate text entry on small handheld computers has led to a resurgence of interest in on-line word recognition using artificial neural networks. Classical methods have been combined and improved to produce robust recognition of hand-printed English text. The central concept of a neural net as a character classifier provides a good base for a recognition system; long-stand...

Automaticpredictionof pitch accent assignmentis an important but challenging task in text-to-speech synthesis (TTS). Early work in accent prediction relied on simple word-class distinctions, but recentlymore sophisticatedinductive learningmodels using multiple features have been applied to the problem. For our neural network accent classifier, we developed a corpus that was labeled according to...