ABSTRACT
The corpus-based lexicon-construction interactive model corresponds to a system of Chinese linguistic knowledge. Since grammatical studies in the European sense were introduced into Chinese linguistics in the 18th century, a large number of comparative studies have been done between Chinese and Indo-European languages and extensive discussions have been undertaken to discover the defining feature of Chinese grammar. Two major lexicons and eight major knowledge bases are included in the lexicon-construction interactive model. These resources are useful for applications in natural language processing, including word sense disambiguation, concept recognition and automatic inference of implicit meanings in lexical combinations. Chinese Word Net (CWN) is a database of Chinese lexical concepts and their relations. CWN organises words according to their senses into a number of classes, including: noun, locative, temporal, spatial, numeral, classifier, quantifier, verb, adjective, descriptive, distinctive, pronoun, adverb, conjunction, preposition, auxiliary, modal particle, interjection and onomatopoeia.
