Michael Gasser. Learning words in time: Towards a modular connectionist account of the ac- quisition of receptive morphology. Technical Report 384, Indiana University, Computer Science Department, Bloomington, 1993.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....speech data. The current availability of large speech corpora and pronunciation dictionaries has allowed us to connect rules and speech in much tighter ways. For example, a number of algorithms have recently been proposed which automatically induce phonological rules from dictionaries or corpora (Gasser 1993; Ellison 1992; Daelemans et al. 1994) While such algorithms have successfully induced syllabicity or harmony constraints, or simple oblig Currently at Voice Processing Corp, 1 Main St, Cambridge, MA 02142: tajchman vpro.com atory phonological rules, there has been much less work on ....

Gasser, Michael, 1993. Learning words in time: Towards a modular connectionist account of the acquisition of receptive morphology. Draft.

....Work Recent work in the machine learning of phonology includes algorithms for learning both segmental and non segmental information. Non segmental approaches include those of Daelemans, Gillis, and Durieux (1994) for learning stress systems, as well as approaches to learning morphology such as Gasser (1993) system for inducing Semitic morphology, and Ellison s (1992) extensive work on syllabicity, sonority, and harmony. Since our approach learns solely segmental structure, a more relevant comparison is with other algorithms for inducing segmental structure. Johnson (1984) gives one of the first ....

Gasser, Michael. 1993. Learning words in time: Towards a modular connectionist account of the acquisition of receptive morphology. Draft.

....8 Related Work Recent work in the machine learning of phonology includes algorithms for learning both segmental and non segmental information. Non segmental approaches include those of Daelemans et al. 1994) for learning stress systems, as well as approaches to learning morphology such as Gasser s (1993) system for inducing Semitic morphology, and Ellison s (1992) extensive work on syllabicity, sonority, and harmony. Since our approach learns solely segmental structure, a more relevant comparison is with other algorithms for inducing segmental structure; this includes SPE phonological rules as ....

GASSER, MICHAEL, 1993. Learning words in time: Towards a modular connectionist account of the acquisition of receptive morphology. Draft.

....speech data. The current availability of large speech corpora and pronunciation dictionaries has allowed us to connect rules and speech in much tighter ways. For example, a number of algorithms have recently been proposed which automatically induce phonological rules from dictionaries or corpora (Gasser 1993; Ellison 1992; Daelemans et al. 1994) While such algorithms have successfully induced syllabicity or harmony constraints, or simple obligatory phonological rules, there was been much less work on non obligatory (optional) rules. In part this is because optional rules like flapping, vowel ....

Gasser, Michael, 1993. Learning words in time: Towards a modular connectionist account of the acquisition of receptive morphology. Draft.

....of position that can be distorted with minimal consequences for word recognition and recall (p.309) Computational modelling of morphological comprehension has also illuminated the perceptual insalience of word medial position. In a connectionist model of the acquisition of receptive morphology, Gasser (1993) has shown that a network of simple processing units can encode the fine grained statistical regularities in a phonetic input stream, in order to distinguish affixes from root morphemes. The model has more difficulty recognizing infixes than prefixes or suffixes, however, because their position ....

Gasser, M. (1993). Learning words in time: towards a modular connectionist account of the acquisition of receptive morphology. Technical Report TR384, Indiana University Computer Science Department, Bloomington, IL.

....viewed the acquisition of morphology in this way, e.g. Cottrell and Plunkett, 1991] has taken the perspective of production. But a human language learner almost certainly learns to understand polymorphemic words before learning to produce them, and pro duction may need to build on perception [Gasser, 1993]. Thus it seems reasonable to begin with a model of the acquisition of receptive morphology. In this paper, I will deal with that component of receptive morphology which takes sequences of phones, each expressed as a vector of phonetic features, and identifies them as particular morphemes. This ....

Michael Gasser. Learning words in time: Towards a modular connectionist account of the ac- quisition of receptive morphology. Technical Report 384, Indiana University, Computer Science Department, Bloomington, 1993.

....meanings. Most work which has viewed the acquisition of morphology in this way, e.g. 1] has taken the perspective of production. But a human language learner almost certainly learns to understand polymorphemic words before learning to produce them, and production may need to build on perception [6]. Thus it seems reasonable to begin with a model of the acquisition of receptive morphology. In this paper, I will deal with that component of receptive morphology which takes sequences of phones, each expressed as a vector of phonetic features, and identifies them as particular morphemes. This ....

Michael Gasser. Learning words in time: Towards a modular connectionist account of the acquisition of receptive morphology. Technical Report 384, Indiana University, Computer Science Department, Bloomington, 1993.

No context found.

Michael Gasser. Learning words in time: Towards a modular connectionist account of the acquisition of receptive morphology. Technical Report TR385, Indiana University, 1993.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC