作者: Aravind K. Joshi , B. Srinivas
关键词:
摘要: In a lexicalized grammar formalism such as Lexicalized Tree-Adjoining Grammar (LTAG), each lexical item is associated with at least one elementary structure (supertag) that localizes syntactic and semantic dependencies. Thus parser for must search large set of supertags to choose the right ones combine parse sentence. We present techniques disambiguating using local information preference The similarity between LTAG Dependency grammars exploited in dependency model supertag disambiguation. performance results various models disambiguation unigram, trigram dependency-based are presented.