Abstract

Preparing a multi-purpose lexicon requires a systematic analysis of inter-conceptual relations. These relations are of two types, namely (i) syntactic and (ii) semantic, which can further be decomposed to capture the greater explanatory adequacy. But the exploration of the lexical structure becomes intricate because of the hidden dynamics of the context; since traditionally, language has been viewed as a totality of lexicon and computation system, and major emphasis has been given to the designing of the computational system, considering the designing of the lexicon internal domain ontology as a mere metaphysical game, when in reality it is a serious epistemic concern, because of having the capacity of licensing inferences. Therefore a lexical level representation should have enough scope to incorporate the contextual information. Designing domain ontology is important since it tells us about the conceptual constellation within the coherent whole of which the related terms are meaningful. Isolating a term from the corresponding constellation will results into the evaporation of meaning. Furthermore it provides the basis, upon which the entire linguistic structure rests. If so, then how is it possible to construct a lexicon, by divorcing the ontological issues? And at the same time, ontology by itself is not enough, again because of the reason that the higher order typifications of those (grounded) concepts and their corresponding interrelations among the types ultimately results into the consequent super-ordinating levels, containing the syntactic information pertinent to a symbol manipulating system. In this paper I would show that the representation of a lexical structure, should include both kind of information which are pertinent to the closed class and as well as the open class semantics, on the basis of examples, cited from English and Bengali.