Christiansen:M. H., & Devlin, J. T. (1997). Recursive inconsistencies are hard to learn: A connectionist perspective on universal word order correlations. In Proceedings of the 19th Annual Cognitive Science Society Conference (pp. 113--118). Mahwah, NJ: Erlbaum.  Home/Search   Document Details and Download   Summary   Related Articles   Check

.... the sequential structure of word forms (e.g. exhibit phonological exchange errors) Ultimately, we believe that connectionist models of the acquisition of the skills of speaking (and comprehending) will contribute to explanations of the nature of language why it is the way it is (see, e.g. Christiansen Devlin, 1997; Hare Elman, 1995; Gupta Dell, 1999) Moreover, we believe the PDP approach offers the best chance to explain 539 LANGUAGE PRODUCTION production as a skill, as something that one learns to do over years of experience. Perhaps most importantly, a PDP approach to language production expresses ....

Christiansen:M. H., & Devlin, J. T. (1997). Recursive inconsistencies are hard to learn: A connectionist perspective on universal word order correlations. In Proceedings of the 19th Annual Cognitive Science Society Conference (pp. 113--118). Mahwah, NJ: Erlbaum.

....as a finite state machine, this can be handled by network lexicon learning using devices like RAAM, SRN and the like. Part of the interest of this proposal lies in the possibility that such learning might capture word order generalizations over the lexical categories, a point that is made by Christiansen and Devlin 1997. It is also important to note that any assumption of a covering grammar, not transparent to semantics in this way, such as the Finite State Machine implicit in the SRN, complicates the task of associating meanings with categories very greatly, and appears to pose equally serious difficulties for ....

Christiansen, Morten and Devlin, Joseph, 1997. "Recursive Inconsistencies Are Hard to Learn: A Connectionist Perspective on Universal Word Order Correlations." In Proceedings of the 19th Annual Cognitive Science Society Conference. Mahwah, NJ: Lawrence Erlbaum Associates, 113--118, 113--118.

....many of the cognitive constraints that have shaped the evolution of language are still at play in our current language ability. If this is correct, it should be possible to uncover the source of some linguistic universal in human performance on sequential learning tasks. Christiansen (2000; Christiansen Devlin, 1997) has previously explored this possibility in terms of a sequential learning explanation of basic word order universals. He presented converging evidence from theoretical considerations regarding rule interactions, connectionist simulations, typological language analyses, and artificial ....

....arising from sequential learning, we present a set of connectionist simulations of our human data. Networks For the simulations, we used simple recurrent networks (SRNs; Elman, 1991) because they have been successfully applied in the modeling of both non linguistic sequential learning (e.g. Christiansen Devlin, 1997; Cleeremans, 1993) and language processing (e.g. Christiansen, 1994; Elman, 1991) SRNs are standard feed forward neural networks equipped with an extra layer of so called context units. The SRNs used in our simulations had 7 input output units (corresponding to each of the 6 letters plus an end ....

[Article contains additional citation context not shown here]

Christiansen, M.H. & Devlin, J.T. (1997). Recursive Inconsistencies Are Hard to Learn: A Connectionist Perspective on Universal Word Order Correlations. In Proceedings of the 19th Annual Cognitive Science Society Conference (pp. 113-118). Mahwah, NJ: Lawrence Erlbaum Associates.

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