Learning the Logic of Simple Phonotactics

Learning Lexical Phonotactics With Simple Recurrent Networks

Learning Phonotactics Using ILP

This paper describes experiments on learning Dutch phonotactic rules using Inductive Logic Programming, a machine learning discipline based on inductive logical operators. Two different ways of approaching the problem are experimented with, and compared against each other as well as with related work on the task. The results show a direct correspodence between the quality and informedness of th...

Exploring Phonotactics with Simple Recurrent Networks

Stoianov, Nerbonne and Bouma (1998) trained Simple Recurrent Networks (SRNs) on graphotactics of Dutch monosyllabic words, overcoming shortcomings of previous implementations. The current report is a continuation of our earlier research, but using phonetic data representations instead of orthographic, that is, learning phonotactics. In addition, we conducted further analysis of neural network p...

Connectionist Learning of Natural Language Lexical Phonotactics

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...

Gradual Learning and Gradient Phonotactics

Gradual learning as gradual adjustment of constraint values (Rosenblatt 1962, Boersma 1998) automatically yields weighting values that can be used in an account of gradient phonotactics, if the grammar is formulated in terms of Harmonic Grammar (HG; Legendre, Smolensky and Miyata 1990). I propose a new metric for gradient acceptability in HG, and show how a complex case of gradient phonotactics...