High-precision Chinese predicate identification method

Abstract

The invention relates to a predicate identification method based on a combination of rules and statistics, and belongs to the field of natural language processing and machine learning. The identification method aims at achieving high-precision and high-efficiency predicate identification. The stepped identification method identifies predicates from morphology and syntax labeled sentences, and comprises the steps of conducting morphological analysis on the sentences to be detected, obtaining suspicious predicates and a number thereof, preliminarily identifying the predicates by using preliminary identification judgment conditions, extracting relevant morphological and syntactic characteristics of the suspicious predicates dissatisfying the preliminary identification judgment conditions, judging the predicates with a decision-making tree judgment model obtained from C4.5 training, and finally summarizing identification results in the two steps to present the predicates of the sentences to be detected. The identification method has the characteristics of high accuracy rate, identification speed and identification rate for the non-verbal predicates, and the like, is applicable to the field requiring high-precision Chinese predicate identification, greatly promotes development of sentence meaning analysis, and has high application and popularization values.

Description

technical field [0001] The invention relates to a Chinese predicate recognition method based on the combination of rules and statistics, belonging to the fields of natural language processing and machine learning. Background technique [0002] Significant progress has been made in the research of lexical and syntactic research in natural language processing technology. In comparison, the research on semantics, pragmatics and contextual knowledge has always been a bottleneck that is difficult to overcome. Semantic analysis is the only way for computers to truly understand natural language. Predicate recognition is the basis for further semantic analysis and plays a key role in the follow-up work of semantic analysis. Therefore, a high-accuracy and high-efficiency predicate recognition method is particularly important. [0003] Chinese predicate recognition needs to solve two basic problems: 1. How to extract representative and highly differentiated rules or feature combinati...

AI Technical Summary

Problems solved by technology

[0007] (2) Predicate recognition for scientific and technological papers: This method is a predicate recognition proposed for the syntactic analysis research of a specific style of scientific and technological papers. It only recognizes the case where the verb is the central predicate (limited to the predicate of the first layer of the sentence). The specific recognition accuracy of the experiment is not given

[0018] Summarizing the above several predicate recognition methods, it can be concluded that: (1) the accuracy of predicate recognition obtained by various methods generally does not exceed 90%, and there is still a lot of room for improvement in accuracy; (2) most of the features used for predicate recognition are only Lexical features are used, and other more advanced features are rarely used; (3) Most methods only recognize verbal predicates, and there are few studies on other parts of speech such as adjectives and idioms as predicates

Images