Method and system for transferring tree bank

Abstract

The invention discloses a transforming method of a treebank and the method comprises: the PennChineseTreebank phase structure is transformed into the dependancy structure; the part of speech tagging set of the PennChineseTreebank is transformed into the part of speech tagging set of 863; the dependency relation of the flat phase structure of the PennChineseTreebank dependency relation is analyzedby a syntactic analyzer of HIT-IR-CDT; a mapping model with the dependency relation is trained by establishing an HIT-IR-CDT treebank in advance and the PennChineseTreebank is transformed by the denpendency relation, thus forming a transformed dependency structure tree. The invention also discloses a treebank transforming system; the invention provides a transforming method of the treebank and a system thereof, which leads the transformed treebank to be merged with the original HIT-IR-CDT, thus increasing the scale of the treebank and improving the performance of the syntactic analyzer.

Description

technical field [0001] The invention relates to tree bank transformation, especially a method and system for transforming Chinese phrase structure tree bank. 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. In ...

AI Technical Summary

Problems solved by technology

[0015] In order to solve the problem that the system of the existing converted dependency tree bank is not unified, and the conversion of the part-of-speech tagging set is not considered in the conversion process, the present invention provides a tree bank The transformation method and system of the library convert PennChinese Treebank into HIT-IR-CDT, and the converted treebank can be easily merged with the original HIT-IR-CDT, thereby increasing the size of the treebank and effectively improving the syntax Profiler performance

Images