Inherent Biases of Recurrent Neural Networks for Phonological Assimilation and Dissimilation
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2017
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929364553170944 |
|---|---|
| author | Doucette, Amanda |
| author_facet | Doucette, Amanda |
| contents | A recurrent neural network model of phonological pattern learning is proposed. The model is a relatively simple neural network with one recurrent layer, and displays biases in learning that mimic observed biases in human learning. Single-feature patterns are learned faster than two-feature patterns, and vowel or consonant-only patterns are learned faster than patterns involving vowels and consonants, mimicking the results of laboratory learning experiments. In non-recurrent models, capturing these biases requires the use of alpha features or some other representation of repeated features, but with a recurrent neural network, these elaborations are not necessary. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_1702_07324 |
| institution | arXiv |
| publishDate | 2017 |
| record_format | arxiv |
| spellingShingle | Inherent Biases of Recurrent Neural Networks for Phonological Assimilation and Dissimilation Doucette, Amanda Computation and Language A recurrent neural network model of phonological pattern learning is proposed. The model is a relatively simple neural network with one recurrent layer, and displays biases in learning that mimic observed biases in human learning. Single-feature patterns are learned faster than two-feature patterns, and vowel or consonant-only patterns are learned faster than patterns involving vowels and consonants, mimicking the results of laboratory learning experiments. In non-recurrent models, capturing these biases requires the use of alpha features or some other representation of repeated features, but with a recurrent neural network, these elaborations are not necessary. |
| title | Inherent Biases of Recurrent Neural Networks for Phonological Assimilation and Dissimilation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/1702.07324 |