A method and system for obtaining a dependency structure tree bank

Abstract

The invention discloses a dependency structure treebank acquisition method and system. The method comprises the steps of calling a first treebank and converting phrase structures in the first treebank into dependency structures by adopting a conversion tool of the first treebank; converting phrase structures of flat structures in the first treebank into dependency structures by utilizing a syntactic analyzer; and performing dependency relationship conversion on the dependency structures in the first treebank by utilizing a dependency relationship mapping model obtained by training to obtain a dependency structure treebank of a second treebank type. According to the method and the system, the treebank after the conversion can be combined with the original dependency structure treebank, so that the treebank scale is increased and the performance of the syntactic analyzer is improved.

Description

technical field [0001] The invention relates to tree bank conversion, in particular to a method and system for acquiring a tree bank of a dependency structure. Background technique [0002] Syntactic analysis is a very important research direction in the field of natural language processing. In the syntactic analysis method based on statistics, according to the different corpus used, it can be divided into guided method and unsupervised method. The guided method needs to manually mark some sentences as training data according to certain grammatical norms, and then obtain the knowledge required for syntactic analysis from the training data through various probability statistics methods or machine learning methods. The unguided method uses unlabeled data for training, and automatically learns grammatical rules according to a certain mechanism. [0003] Guided syntactic analysis is the mainstream method now, and it has achieved high accuracy in English and other languages. I...

AI Technical Summary

Problems solved by technology

[0014] In order to solve the problem that the system of the existing converted dependency tree bank is not unified, the present invention provides a method and system for obtaining a dependency structure tree bank, which converts the phrase structure tree bank into a dependency structure tree bank, and the converted tree bank can be quickly Conveniently merge with the original dependency structure tree library, thereby increasing the size of the tree library, and effectively improving the performance of the syntax analyzer

Images