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

Word vector correction method based on semantic relation constraint and computing system

A semantic relationship and computing system technology, applied in the field of natural language processing semantic computing, can solve the problems of affecting distributed semantic expression ability, lower semantic domain compatibility, and lower similarity between concepts, so as to achieve fast computing speed and vocabulary Semantic similarity judgment is effective and the effect of overcoming noise influence

Inactive Publication Date: 2021-06-15
SHANDONG JIANZHU UNIV
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If the hierarchical span between semantic concepts increases, the semantic domain compatibility of the concepts at both ends of the implication relationship will also decrease, and the similarity between concepts will also decrease. If it is injected into the neural network word embedding model as a semantic constraint, it will Affects distributed semantic expression ability

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
  • Word vector correction method based on semantic relation constraint and computing system
  • Word vector correction method based on semantic relation constraint and computing system
  • Word vector correction method based on semantic relation constraint and computing system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] Firstly, the concepts of semantic relationship constraint set, neural network word embedding vector and semantic transfer are explained.

[0037] Semantic relationship constraint set: Nouns, verbs, adjectives and adverbs in the semantic dictionary are organized into a network of synonyms with symmetrical relationships, and the words in the network form synsets in pairs (the same is true for antonyms and implication relations).

[0038] Neural network word embedding: Neural network word vector representation technology models the context and the relationship between the context and the target word through neural network technology, and represents discrete data as continuous low-dimensional vectors.

[0039] Semantic transfer: suppose there are concepts c1, c2, ... cn, cn+1, and there are semantic relations r1 (c1, c2), r2 (c2, c3), ..., rn (cn, cn+1) between concepts, when n≤ 2, it is called single-level semantic transfer; when n>2, it is called multi-level semantic tran...

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 provides a word vector correction method based on semantic relation constraint and a computing system. The method comprises the following steps: a synonym and antonym constraint set with a symmetric relation and a direct hypernym / hypernym constraint set with an asymmetric relation are extracted as an external knowledge source update word embedding vector from WordNet and Roget semantic dictionaries; and the similarity of the pair of vocabularies can be calculated by randomly inputting two vocabularies of which the similarity needs to be calculated. The vocabulary semantic similarity calculation system comprises an input unit, an initialization unit, a calculation unit and an output unit. According to the method, the existing neural network word embedding vector is updated based on the lexical semantic relationship constraint provided by the external knowledge source so as to be used for lexical semantic similarity calculation. The updating speed and the word embedding vector semantic updating effect are obviously better than those in the prior art, and the accuracy rate in calculating the word semantic similarity is higher.

Description

technical field [0001] The present invention relates to a method for correcting neural network word embedding vectors and a system for calculating lexical similarity using semantic relationship constraint sets in semantic dictionaries, especially using direct hypernyms / hyponyms with asymmetrical relationships in semantic hierarchies to constrain The invention relates to the semantic distance between word embedding vectors, and belongs to the field of natural language processing semantic calculation. Background technique [0002] Distributed representations are one of the important research contents of natural language processing. The distributed representation is based on Harris' distributed assumption that two words are similar if their contexts are similar. The type of context can be adjacent words, sentences or documents. In this way, we can represent words through the co-occurrence matrix of words and their contexts, that is, each row of the co-occurrence matrix is ​​r...

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
IPC IPC(8): G06F40/30G06F40/284G06F40/247G06F40/242G06K9/62G06N3/02
CPCG06F40/30G06F40/284G06F40/247G06F40/242G06N3/02G06F18/22
Inventor 杨东强阴艳芹
Owner SHANDONG JIANZHU UNIV
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