Phonological constraint induction in a connectionist network: learning OCP-Place constraints from data
Abstract: A significant problem in computational language learning is that of inferring the content of well-formedness constraints from input data. In this article, we approach the constraint induction problem as the gradual adjustment of subsymbolic constraints in a connectionist network. In partic...
| Publicado en: | Language Sciences Vol. 37; pp. 52 - 70 |
|---|---|
| Autores principales: | , , |
| Formato: | Artículo |
| Publicado: |
Elsevier B.V.
May2013
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=85280448&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 85280448 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 03880001 JM3 jtl: Language Sciences issn: 03880001 maglogo: N pubinfo: dt: May2013 vid: 37 pid: 2410 pub: Elsevier B.V. artinfo: ui: 85280448 10.1016/j.langsci.2012.10.002 ppf: 52 ppct: 18 formats: tig: atl: Phonological constraint induction in a connectionist network: learning OCP-Place constraints from data aug: au: Alderete, John Tupper, Paul Frisch, Stefan A. affil: Simon Fraser University, Department of Linguistics, 8888 University Ave., Burnaby, BC, Canada V5A 1S6 Simon Fraser University, Department of Mathematics, 8888 University Ave., Burnaby, BC, Canada V5A 1S6 University of South Florida, Department of Communication Sciences and Disorders, 4202 E. Fowler Ave., PCD1017, Tampa, FL 33620-8100, USA su: Phonology Learning Constraints (Linguistics) Foreign language education Psycholinguistics Qualitative research sug: subj: Phonology Learning Constraints (Linguistics) Foreign language education Psycholinguistics Qualitative research keyword: Arabic Connectionism Constraint induction Dissimilation Optimality Theory Parallel distributed processing ab: Abstract: A significant problem in computational language learning is that of inferring the content of well-formedness constraints from input data. In this article, we approach the constraint induction problem as the gradual adjustment of subsymbolic constraints in a connectionist network. In particular, we develop a multi-layer feed-forward network that learns the constraints that underlie restrictions against homorganic consonants, or ‘OCP-Place constraints’, in Arabic roots. The network is trained using standard learning procedures in connection science with a representative sample of Arabic roots. The trained network is shown to classify actual and novel Arabic roots in ways that are qualitatively parallel to a psycholinguistic study of Arabic. Statistical analysis of network behavior also shows that activations of nodes in the hidden layer correspond well with violations of symbolic well-formedness constraints familiar from generative phonology. In sum, it is shown that at least some constraints operative in phonotactic grammar can be learned from data and do not have to be stipulated in advance of learning. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y dt: @attributes: year: 2013 holdings: @attributes: islocal: N |
|---|