Grammar Compilation Method, Semantic Analysis Method and Corresponding Device

Abstract

The present invention provides a grammar compiling method, a semantic analysis method and a corresponding device. According to the common sentence expression of semantics, a grammar description file and a part-of-speech description file based on Logical Grammar Intuitive Language (LGML) are used to pre-define the corresponding grammar description file. In the grammar description file, there are Parts of speech, operators and functions constitute the description of commonly used sentences, and the part-of-speech description file is used to describe the specific value of the part of speech; the grammar description file and the part-of-speech description file are respectively generated according to the reduction method of the preset order to generate the syntax tree and part of speech of the grammar description file Describe the part-of-speech tree of the file, mount the part-of-speech tree to the position corresponding to the part-of-speech in the grammar tree, and form a semantic grammar tree, thereby realizing grammar compilation. Based on the semantic syntax tree established in this way, the semantic analysis is carried out by means of whole sentence matching, semantic mapping matching or a combination of whole sentence matching and semantic mapping matching.

Description

[0001] 【Technical field】 [0002] The present invention relates to the field of computer application technology, in particular to a syntax compiling method, a semantic analysis method and a corresponding device. [0003] 【Background technique】 [0004] Speech recognition and spoken semantic analysis are two important technologies of voice interactive products. Speech recognition is to convert the content of speech into text, and spoken semantic analysis is to understand the information carried by spoken voice signals. The speech recognition rate and the accuracy of spoken language semantic analysis directly affect the user experience. In order to improve the speech recognition rate and the accuracy of spoken language semantic analysis, two context-free grammars specified by the W3C (World Wide Web Consortium) are currently used to construct the recognition space, that is, using the grammar in the form of BNF (Backus-Naur Form) or based on XML ( Extensible Markup Language) form...

AI Technical Summary

Problems solved by technology

[0005] The way people speak is natural spoken language, and there are big differences in behavior, wording and text input. For example, there are loose grammar and word order reversal in spoken language. The BNF grammar recommended by W3C and the grammar in XML format are mainstream large-vocabulary continuous speech However, due to the deep interpretation levels of BNF and XML, the definition of semantic mapping and syntax understanding using these two grammars is very complicated, with the defects of poor readability and maintainability, and it is difficult to perform related grammar compilation and semantic analysis

Images