This paper argues that if phonological and phonetic phenomena found in language data and in experimental data all have to be accounted for within a single framework, then that framework will have to be based on neural networks. We introduce an artificial neural network model that can handle stochastic processing in production and comprehension. With the “inoutstar” learning algorithm, the model is able to handle two seemingly disparate phenomena at the same time: gradual category creation and auditory dispersion. As a result, two aspects of the transmission of language from one generation to the next are integrated in a single model. The model therefore addresses the hitherto unsolved problem of how symbolic-looking discrete language behavi...
The development of computer science in the middle of the twentieth century provided a valuable tool ...
Computational models of phonotactics share much in common with language models, which assign probabi...
Traditional ideas of dialect represent an essentially aesthetic view, in which evidence from languag...
We present a neural network model of phonetic and phonological acquisition that can handle two disti...
Currently, N-gram models are the most common and widely used models for statistical language modelin...
Newly born infants are able to finely discriminate almost all human speech contrasts and their phone...
This paper gives an analysis of an attractor neural network model dubbed the Phonological Latching N...
Currently, N-gram models are the most common and widely used models for statistical language modelin...
A number of experiments have demonstrated what seems to be a bias in human phonological learning for...
This paper gives an analysis of an attractor neural network model dubbed the Phonological Latching N...
A number of experiments have demonstrated what seems to be a bias in human phonological learning for...
The paper describes a neural network model of early language acquisition with an emphasis on how lan...
Currently, N-gram models are the most common and widelyused models for statistical language modeling...
This dissertation is an investigation of computational models for sensorimotor integration and word ...
The development of computer science in the middle of the twentieth century provided a valuable tool ...
The development of computer science in the middle of the twentieth century provided a valuable tool ...
Computational models of phonotactics share much in common with language models, which assign probabi...
Traditional ideas of dialect represent an essentially aesthetic view, in which evidence from languag...
We present a neural network model of phonetic and phonological acquisition that can handle two disti...
Currently, N-gram models are the most common and widely used models for statistical language modelin...
Newly born infants are able to finely discriminate almost all human speech contrasts and their phone...
This paper gives an analysis of an attractor neural network model dubbed the Phonological Latching N...
Currently, N-gram models are the most common and widely used models for statistical language modelin...
A number of experiments have demonstrated what seems to be a bias in human phonological learning for...
This paper gives an analysis of an attractor neural network model dubbed the Phonological Latching N...
A number of experiments have demonstrated what seems to be a bias in human phonological learning for...
The paper describes a neural network model of early language acquisition with an emphasis on how lan...
Currently, N-gram models are the most common and widelyused models for statistical language modeling...
This dissertation is an investigation of computational models for sensorimotor integration and word ...
The development of computer science in the middle of the twentieth century provided a valuable tool ...
The development of computer science in the middle of the twentieth century provided a valuable tool ...
Computational models of phonotactics share much in common with language models, which assign probabi...
Traditional ideas of dialect represent an essentially aesthetic view, in which evidence from languag...