Method and system for parsing dependency of noun phrases

Abstract

The invention relates to a method and a system for parsing dependency of noun phrases. The method includes the steps: 1 training a weight vector and an SVM (support vector machine) classifier based on a language material database to obtain a stable weight vector and a stable SVM classifier; 2 receiving and preprocessing the phrases to be analyzed to obtain at least two terms in specified formats; 3 analyzing all the terms to obtain a dependency parsing tree. The method can be decomposed into two steps: firstly, recognizing complicated noun phrases in a sentence and parsing dependency by the method; secondly, replacing the complicated noun phrases in the original sentence by an obtained substructure to reduce complexity of the sentence. As an algorithm is an improved simple side priority algorithm, high efficiency of the algorithm is kept. As the noun phrases are short and not obvious enough in characteristic, the SVM classifier is used for determining a dependency direction, and effectiveness of the algorithm is ensured.

Description

technical field [0001] The invention relates to a method and a system for performing dependency syntax analysis on noun phrases, belonging to the technical field of language processing. Background technique [0002] Dependency parsing has received more and more attention in the fields of natural language processing such as information extraction and machine translation in recent years. In theory, it is rooted in dependency grammar, focusing on the syntactic dependencies between words. [0003] For the research on the semantic structure of noun phrases, at present, it mainly focuses on the semantic interpretation of NN noun phrases, and the main task is to automatically obtain the implicit semantic relationship between modifiers and head words. There are generally two strategies: [0004] Top-down strategy (top-down strategy), this method first defines a good set of relations, and then assigns appropriate relations to each noun phrase. [0005] Bottom-up strategy (bottom-u...

AI Technical Summary

Problems solved by technology

[0011] The technical problem to be solved by the present invention is that, based on the traditional dependency syntax analysis algorithm, it focuses more on the analysis of the whole sentence, which leads to the inadequacy of the accuracy of the analysis when encountering a sentence with a complex structure; Based on the conversion method and the graph method, the method and system for analyzing the dependency syntax of noun phrases are improved on the basis of the simple edge-first algorithm

Images