Linguistic knowledge generator

Though re-usability of linguistic knowledge is currently and intensively prescribed, the contention is that the adaptation of existing knowledge requires processes beyond mere re-use.

Abstract

Introduction The difficulties in current NLP applications are seldon, due to the lack of appropriate frameworks for encoding our linguistic or extra-linguistic knowledge, but rather to the fact that we do not know in advance what actual instances of knowledge should be, even though we know in advance what types of knowledge are required. It normally takes a long time and requires painful trial and error processes to adapt knowledge, for ex ample, in existing MT systens in order to translate documents of a new text-type and of a new subject domain. Semantic dsification schenes for wods, for example, usually reflect ontologics of subject domains so that we cannot expect a single ctsific- tion scheme to be effective across different domains. qB treat different suManguages requires different word clsification schemes. We have to construct apprm priate schenes for given sublanguages from scratch It bas also been reported that not only knowledge concerned with extra-linguistic donnains