A method of automatic recognition of attributive clauses in Chinese language

摘要

Influenced by the grammatical system of western languages, there are more and more syntactic structures in modern Chinese that can be translated into English attributive clauses. But for the great differences of the syntactic structures, parsing Chinese by western grammatical rules usually does not lead to satisfactory results, which will result in poor translation performance in complex syntactic structures. This paper first attempts to recognize the attributive clauses by using conditional random fields (“CRFs”) theory by selecting representative features combined with grammatical information unique in Chinese language. The experiment proves that this method will produce a better result than simply by statistical machine translation method.