Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A bilingual unsupervised syntax analysis method and system

A technology of syntactic analysis and syntactic analysis tree, which is applied in special data processing applications, instruments, electrical digital data processing, etc.

Inactive Publication Date: 2017-08-08
INST OF COMPUTING TECH CHINESE ACAD OF SCI +1
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since the bilingual isomorphism hypothesis cannot explain the bilingual heteromorphic phenomenon and is very sensitive to the noise caused by automatic alignment errors, the syntactic structure of the output is very likely to be unreasonable

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 bilingual unsupervised syntax analysis method and system
  • A bilingual unsupervised syntax analysis method and system
  • A bilingual unsupervised syntax analysis method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] In order to make the purpose, technical solution and advantages of the invention clearer, the bilingual unsupervised syntax analysis method and system of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0050] Such as figure 1 as shown, figure 1 Be the flowchart of the bilingual unsupervised syntax analysis method based on relaxation isomorphism of the present invention, the method comprises the following steps:

[0051] Step 1: Establish random syntactic analysis treebanks on the source and target sides of the bilingual corpus. The algorithm for generating the random parsing tree is not limited.

[0052] Step 2: Separately train the monolingual unsupervised parsing model on the random parsing tree bank. Among them, the method of discriminative classification (see the content of "discriminative classification model" below for details) is used to train the single syntax analysis model. Th...

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 discloses bilingual unsupervised syntactic analysis method and system. The method comprises the following steps: 1 respectively building random syntactic analysis treebanks on a bilingual corpus source side and a target side; 2 individually training a monolingual unsupervised syntactic analysis model by computing the probability of a monolingual unsupervised syntactic analysis tree on the random syntactic analysis treebanks; 3 carrying out bilingual syntactic analysis on the monolingual unsupervised syntactic analysis model by computing the relaxation isomorphism similarity and a bilingual syntactic analysis algorithm, obtaining a bilingual syntactic analysis treebank which meets a relaxation isomorphism bilingual syntactic analysis target, so as to replace the random syntactic analysis treebanks; 4 repeating the steps 1 to 3 until the bilingual unsupervised syntactic analysis model is astringed; therefore, the better monolingual unsupervised syntactic analysis model is obtained, so as to be applied to all downstream application requiring syntactic analysis.

Description

technical field [0001] The invention belongs to the technical field of natural language processing, in particular to a bilingual unsupervised syntax analysis method and system based on the idea of ​​relaxation isomorphism. 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. The unsupervised syntactic analysis method can perform syntactic analysis on a given sentence sequence without labeling the tree bank, and obtain the corresponding syntactic structure for downstream natural language processing tasks, such as syntax-based machine translation tasks, information extraction tasks, The corresponding syntactic structures are widely used in tasks such as automatic question answering tasks. However, most of the traditional unsupervised syntactic analysis methods currently perfor...

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 刘凯姜文斌刘群
Owner INST OF COMPUTING TECH CHINESE ACAD OF SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com