Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ
Tải xuống
At least since Chomsky, the usual response to the projection problem has been to characterize knowledge of language as a grammar, and then proceed by restricting so severely the class of grammars available for acquisition that the induction task is greatly simplified - perhaps trivialized. The work reported here describes an implemented LISP program that explicitly reproduces this methodological approach to acquisitio,~ - but in a computational setting. | Computational Analogues of Constraints on Grammars A Model of Syntactic Acquisition Robert Cregar Berwick MIT Artificial Intelligence Laboratory Cambridge MA I. Introduction Constraints And Language Acquisition A principal goal of modern linguistics is to account for the apparently rapid and uniform acquisition of syntactic knowledge given the relatively impoverished input that evidently serves as the basis for the induction of that knowledge - the so-called projection problem. At least since Chomsky the usual response to the projection problem has been to characterize knowledge of language as a grammar and then proceed by restricting so severely the class of grammars available for acquisition that the induction task is greatly simplified - perhaps trivialized. The work reported here describes an implemented LISP program that explicitly reproduces this methodological approach to acquisition - but in a computational setting. It asks what constraints on a computational system are required to ensure the acquisition of syntactic knowledge given relatively plausible restrictions on input examples only positive data of limited complexity . The linguistic approach requires as the output of acquisition a representation of adult knowledge in the form of a grammar. In this research an existing parser for English Marcus PARSIFAL 1 acts as the grammar. PARSIFAL divides neatly into two parts an interpreter and the grammar rules that the interpreter executes. The grammar rules unwind the mapping between a surface string and an annotated surface structure representation of that string. In part this unraveling is carried out under the control of a base phrase structure component the base rules direct some grammar rules to build canonically-ordered structure while other grammar rules are used to detect deviations from canonical order. We mimic the acquisition process by fixing a stripped-down version of the PARSIFAL interpreter thereby assuming an initial set of abilities the basic
