Supercharge Your Innovation With Domain-Expert AI Agents!

A method and system for semantic analysis and Chinese-English ordering based on the smallest semantic block

A semantic analysis and semantic block technology, which is applied in semantic analysis, natural language translation, natural language data processing, etc., can solve the problem of high applicability of word templates, no in-depth mining of noun complex partial semantic analysis and semantics Hierarchical tree, no specific scheme for Chinese-English ordering, etc.

Active Publication Date: 2022-05-24
BEIJING UNION UNIVERSITY
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this model is that it has high requirements for the applicability of word templates, and some BaseNPs are no longer BaseNPs or just a part of BaseNPs in some language environments, thus reducing the accuracy rate, and the system has no obvious syntactic features for the context The accuracy of BaseNP recognition is low
The system deals with semantic recognition at the sentence level, which is relatively general. It only recognizes complex noun chunks, but does not dig deep into the semantic analysis and semantic hierarchy tree inside complex noun chunks. There is no specific plan for the Chinese-English ordering of complex noun chunks, and there is no function for translating Chinese into English for complex noun chunks

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 method and system for semantic analysis and Chinese-English ordering based on the smallest semantic block
  • A method and system for semantic analysis and Chinese-English ordering based on the smallest semantic block
  • A method and system for semantic analysis and Chinese-English ordering based on the smallest semantic block

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0178] This embodiment provides a method for semantic analysis of complex and partial noun blocks based on minimal semantic blocks, and a method and system for ordering Chinese and English. The important meaning carriers in natural language are nouns, so it is necessary to modify the nouns from multiple angles and at multiple levels. In terms of semantic categories, modifiers mainly define one or more aspects of the noun's nature, state, feature, description, time, location, quantity, scope, function, and material. Based on translation needs, through comparison, it is found that there are a large number of language fragments with equivalent meanings, that is, semantic blocks, in Chinese and English noun complex and partial lexical blocks. The smallest semantic block is the smallest semantically equivalent word or a combination of several words based on the comparison of Chinese and English noun complex and partial words. The length is not fixed, it can be one word or several w...

Embodiment 2

[0273] The technical problem to be solved by the present invention is to identify the smallest semantic block inside the partial positive word block in the Chinese nominal complex partial positive word block, and on this basis to realize the translation of the nominal complex partial positive word block in the Chinese-English patent, it is necessary to investigate A certain scale of Chinese and English noun complex partial orthographic blocks determines the basis for dividing the smallest semantic block, and has a strong dependence on the field of the text.

[0274] In the present invention, the concept category is used as the reference for segmentation information extraction, and on this basis, the production rules are further used to identify the semantic nodes of the smallest semantic block. Remove and add semantic nodes to identify all the semantic nodes of the smallest semantic block and determine its level, design an algorithm for combining semantic nodes, identify all th...

Embodiment 3

[0276] In this embodiment, a specific application example of a method for semantic analysis of complex and partial noun blocks based on minimal semantic blocks and a method for Chinese-English ordering is given.

[0277] like image 3 shown, the Chinese sentence to be processed "two upper elevation views of the stretched scissor gears 18 in the open and closed states in the embodiment of the present invention". This example has 5 minimal semantic blocks, namely BK "Invention", BK "Embodiment", BK "Scissor Gear 18", BK "Open and Closed State", BK "Upper Elevation View", where KU " "Two" can be judged as a modified semantic block according to its concept category being quantitative concept and block head position. The semantic nodes of this example are L4 "in", DYMK "of", L1H "in", and L4 "in", and five smallest semantic blocks are generated from this semantic node. It should be noted that the "de" after "stretch" can be a pure verb according to the conceptual category of "str...

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 present invention provides a semantic analysis and Chinese-English sequence method and system based on the smallest semantic block, wherein the system includes a preprocessing and semantic acquisition unit, and also includes the following units: a semantic node identification unit, a semantic node level judgment unit, and a semantic node merge Unit, Sequence Unit, Logical Connective Translation Unit and Minimal Semantic Block Translation Unit. In the absence of a large number of syntactic resources, the present invention efficiently completes the formalized semantic expression of Chinese nominal complex partial language blocks on the basis of the smallest semantic block by using only semantic information, word positions, and collocation information application rules. The accuracy of semantic block recognition is high, which improves the accuracy of internal semantic analysis of nominal complex language blocks, improves the translation effect of English translation, and enhances the readability of English translation.

Description

technical field [0001] The invention relates to the technical field of natural language processing, in particular to a method and system for semantic analysis and Chinese-English ordering based on the smallest semantic block. Background technique [0002] Chinese information processing technologies for Chinese-English machine translation include rule-based methods, template-based methods, and statistics-based methods for words or phrases. Most of the work in recent years has focused on the identification of the longest noun phrase (MNP). Zhan Weidong (2000) used the phrase-based grammatical system proposed by Zhu Dexi to analyze the structure of modern Chinese phrases. phrase) description. It can be seen from the existing references that the analysis of the internal MNP has not been carried out. Li Sujian (2002) referred to the method of extracting English chunks and used the Chinese tree bank of the University of Pennsylvania to extract chunks from the tree bank. The no...

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): G06F40/58G06F40/289G06F40/30
CPCG06F40/289G06F40/30G06F40/58
Inventor 刘小蝶
Owner BEIJING UNION UNIVERSITY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com