A parsing algorithm of natural language based on operator precedence

To deal with the problems in the current parsing method of natural language, a language model based on purely typed binary relations is proposed in this paper, which is quite different from classical context-free grammar, Chomsky normal form and dependency grammar. The completeness of language structure coverage is easily captured using the proposed language model, so long as the binary relations can be recognized thoroughly. The parsing process is considered as the manipulation of binary operations of words, which is similar to the computation of arithmetic expressions in terms of the proposed language model, where operands are words and operators are the typed relations. And thereafter, a parsing algorithm based on operator precedence is proposed in the paper, with the algorithm formalized and the complexity analyzed. The proposed ideas have been proved valid and realistic through the application to parsing Chinese sentences. Further researches are needed to put it into the effective and practical usages in large scale to make it developed as a powerful theoretical way for parsing natural language.