tailieunhanh - Báo cáo khoa học: "UNGRAMHATICALITY AND EXTRA-GRAMMATICALITY IN NATURAL LANGUAGE UNDERSTANDING SYSTEMS"

That are ill-formed with respect to the grammar will be received, both because p e o p l e regularly form ungra=cmatical utterances and because there are a variety of forms that cannot be readily included in current grammatical models and are hence "extra-grammatical". These might be rejected, but as Wilks stresses, ".understanding requires, at the very least, . some attempt to interpret, rather than merely reject, what seem to be ill-formed utterances." [WIL76] This paper i n v e s t i g a t e s several language phenomena commonly considered ungrammatical | UNGRAMMATICALITY AND EXTRA-GRAMMATICALITY IN NATURAL LANGUAGE UNDERSTANDING SYSTEMS By Stan c. Kwasny The Ohio state University Columbus Ohio I. Introduction Among the components Included in Natural Language Understanding NLU systems Is a grammar which specifies much of the linguistic structure of the utterances that can be expected. However it is certain that inputs that are Ill-formed with respect to the grammar will be received both because people regularly form ungrammatical utterances and because there are a variety of forms that cannot be readily Included In current grammatical models and are hence extra-grammatical . These might be rejected but as Wilks stresses .understanding requires at the very least . some attempt to interpret rather than merely reject what seem to be Ill-formed utterances. WIL76 This paper investigates several language phenomena commonly considered ungrammatical or extra-grammatical and proposes techniques directed at Integrating them as much as possible Into the conventional grammatical processing performed by NLU systems through Augmented Transition Network ATN grammars. For each NLU system a normative grammar is assumed which specifies the structure of well-formed Inputs. Rules that are both manually added to the original grammar or automatically constructed during parsing analyze the Ill-formed Input. The Ul-formedness Is shown at the completion of a parse by deviance from fully grammatical structures. We have been able to do this processing while preserving the structural characteristics of the original grammar and Its inherent efficiency. Some of the phenomena discussed have been considered previously In particular NLU systems see for example the ellipsis handling In LIFER HEN77 . Some techniques similar to ours have been used for parsing see for example the conjunction mechanism In LUNAR W0073J. On the linguistic side Chomsky CHOỖ4 and Katz KAT64 among others have considered the treatment of ungrammaticality In Transformational .