A Text-Dependent Syntactic Analysis Method
A technology that relies on syntax and analysis methods, applied in neural learning methods, instruments, biological neural network models, etc., can solve problems such as word segmentation and part-of-speech tagging error spread, dependency subtrees are not fully utilized, and historical decision-making information is not considered. , to achieve the effect of improving the accuracy
Active Publication Date: 2022-07-29
HARBIN ENG UNIV +1
View PDF10 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In summary, the major difficulties in dependency parsing are the error spread of word segmentation and part-of-speech tagging, the characteristics of the dependency subtree are not fully utilized in the transfer decision, and the historical decision information is not considered in the decision-making.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0079] The present invention proposes a new type of neural network model in order to support operations such as relation extraction necessary for building a knowledge graph in the field of four insurances and one gold, to help the construction of a dependency syntax tree. The purpose of the present invention is to perform dependency syntax analysis on the texts of policies and regulations in the field of four insurances and one housing fund. The construction of knowledge graph requires operations such as named entity recognition and relation extraction. To complete these operations efficiently, the sentence to be analyzed needs to be input in the form of a dependency tree. The present invention is to provide a dependency tree for these jobs.
[0080] 1) Use crawler technology to crawl the policies and regulations in the field of four insurances and one gold released by relevant departments from relevant websites in the field of four insurances and one gold as the data sets req...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention belongs to the technical field of dependency syntax analysis, and in particular relates to a text dependency syntax analysis method. The dependency syntax tree is an important basis for relation extraction work. The purpose of dependency syntax analysis is to build a dependency syntax tree. The accuracy of dependency syntax analysis directly affects the accuracy of upper-layer work such as relation extraction. In order to improve the accuracy of dependency syntax analysis, The present invention proposes a text dependency syntax analysis method based on the neural network model combining Pointer-Net and TreeLSTM. The method can take into account the semantic features of the context in the process of dependency analysis, and will take into account the decision-making process of each step. Generated dependency subtrees, thereby improving the accuracy of dependency syntax analysis.
Description
technical field [0001] The invention belongs to the technical field of dependency syntax analysis, and in particular relates to a text dependency syntax analysis method. Background technique [0002] Generally speaking, the rule-based analysis method, the statistical-based analysis method, and the method of syntactic analysis combining rules and statistics constitute the mainstream of dependency syntax analysis. The rule-based analysis method requires a lot of manual operations, such as building a grammar knowledge base and writing grammar rules. In order to realize the structure disambiguation in the syntactic analysis, the method of conditional constraints is also needed. Originally, people intended to place their hopes on the rules of syntactic analysis. They believed that the rules could contain all syntactic structures. However, practice has shown that this rule-based method has poor adaptability and is completely unsuitable for the environment where the amount of data ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F40/211G06F40/289G06N3/04G06N3/08
CPCG06F40/211G06F40/289G06N3/08G06N3/044G06N3/045
Inventor 黄少滨谷虹润申林山李熔盛程序严江范贺添吴汉瑜
Owner HARBIN ENG UNIV