Connectionist learning of natural language words and their phonetic regularities is presented. The Neural Network (NN) model we employ in this problem is the Simple Recurrent Network, trained with the Backpropagation Through Time (BPTT) learning algorithm. During the training, it was assigned the task of predicting the next phoneme given one phoneme at each moment and keeping information of the...

For a language learner, any new word is a pseudoword. A pseudoword is a string of of letters or phonemes that sounds like an existing word in a language, though it has no meaning in the lexicon. On the other hand, speakers are well aware of permissible phonemes, their frequencies and collocations in their language due to the phonotactics inherent in the language. For example, saktal is a pseudo...

This paper investigates the perception of phonotactics by Saudi English majors, beginners and advanced. Due to significance pronunciation consonant clusters, which are almost absent from Arabic, this work attempts find extent beginner advanced majors accept or reject permissible impermissible sounds combinations in onset position. It also whether there any intervening factors that could influen...

We discuss experiments with neural networks being trained in a phonotactic processing task. A recurrent network not only learns to predict the next letter given a partial processed word, but also learns to represent the letters in a manner meaningful to the processing task. To this end, we use Miikkulainen’s (1993) FGREP, augmented with an algorithm we call dispersion, to improve distinctness a...

The statistical patterns of language are systematic linguistic data which must be accounted for in linguistic theory. The phonotactics of the Arabic verbal roots are presented as a case study. In Arabic, the acceptability of a verbal root is gradiently dependent on the similarity of homorganic consonant pairs within the root. We propose the stochastic constraint model of phonological patterning...

Similarity and Frequency in Phonology Stefan Frisch This thesis focuses upon parallels between phonology and phonological processing. I study phonological speech errors and a phonotactic dissimilarity constraint, demonstrating they have analogous similarity and frequency effects. In addition, I show that abstract phonological constraints are influenced by the phonological encoding of lexical it...