Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A Syntax Analysis Method Based on Sliding Semantic String Matching

A syntactic analysis and string matching technology, applied in special data processing applications, instruments, electronic digital data processing, etc., can solve the problems of the difficulty of further improving the level of phrase structure type syntactic analysis and the difficulty of choosing the correct chunking rules, so as to improve the Processing accuracy and operational efficiency, ease of improvement, and the effect of improving system performance

Inactive Publication Date: 2016-07-06
DALIAN UNIV OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0028] The present invention provides a syntactic analysis method based on sliding semantic string matching, thereby solving the problems that the level of probabilistic phrase structure syntactic analysis is difficult to further improve and the cascading block syntactic analysis is difficult to select the correct block rule, Improves the level of existing syntactic analysis

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Syntax Analysis Method Based on Sliding Semantic String Matching
  • A Syntax Analysis Method Based on Sliding Semantic String Matching
  • A Syntax Analysis Method Based on Sliding Semantic String Matching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0073] Embodiments of the present invention will be described in detail below in conjunction with technical solutions and accompanying drawings.

[0074] 1. Flat and hierarchical phrase structure syntax tree representation

[0075] The results of syntactic analysis are usually expressed in the form of syntactic trees. Currently, there are mainly phrase structure syntactic trees and dependency syntactic trees. The phrase structure syntax tree can be divided into multi-fork tree and binary tree representation according to the form of expression. Because the binary tree is easy for computer processing, it has been widely used. The syntax analysis result of the present invention is represented by a phrase structure binary tree, and the phrase syntax tree is transformed into a flat hierarchy for the convenience of explaining the principle. For example, the phrase structure tree of the example sentence "Mankind invented writing more than 5,000 years ago." figure 1 . A binary tre...

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

No PUM Login to View More

Abstract

The invention belongs to the field of computer natural language processing, and relates to a method for high-quality syntactic analysis of human natural language sentences, specifically a syntactic analysis method based on sliding semantic string matching. Its characteristic is that when building the rule base, firstly, the ordinary short syntax tree is flattened and transformed, and then the block information of each layer is semantically coded, so as to extract the block rules of the N-gram context-related grammar; During syntactic analysis, the sliding semantic string matching model is used to match the optimal chunking rules for cascading chunking analysis; errors in the high-level layer are found and corrected through error correction templates, and the heuristic in the cascading chunking syntactic analysis is realized Backtracking processing; by directly adding template information in the semantic template index, the machine can learn new syntactic rules in real time. The invention solves the difficult problem of further improving the parsing level of probabilistic context-free grammar (PCFG) type and the difficulty of selecting the correct block rules in syntactic analysis of stacked block type, and improves the existing syntactic analysis level.

Description

technical field [0001] The invention belongs to the field of computer natural language processing, and relates to a method for high-quality syntactic analysis of human natural language sentences, specifically a syntactic analysis method based on sliding semantic string matching. Background technique [0002] Syntactic analysis is a series of analysis of natural language sentences, mainly analyzing the syntactic components of sentences and the relationship between them, and the usual output is expressed in the form of syntax tree. [0003] Syntactic analysis is a crucial link in the process of natural language processing, and it is also a recognized difficult problem. Because it is the basis of many specific applications, such as automatic question answering systems, semantic retrieval, text summarization, story understanding, and even machine translation. If this link cannot analyze the given sentence correctly, then it is difficult to guarantee the performance of subsequen...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F17/27
Inventor 王伟黄德根
Owner DALIAN UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products