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

Language meaning understanding method fusing semantic information

A technology of original information and language, applied in the field of language meaning understanding, it can solve the problems of high complexity of language modeling method and inability to take into account the effect and so on.

Active Publication Date: 2021-03-09
HARBIN ENG UNIV
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The present invention aims to solve the problems of high complexity and inability to take into account the effects of existing language modeling methods

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
  • Language meaning understanding method fusing semantic information
  • Language meaning understanding method fusing semantic information
  • Language meaning understanding method fusing semantic information

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0047] Sememe is a unique concept in HowNet. Its design purpose is to use a fixed part of words to represent basic semantic information, so that any other words can be represented by these sememes. These representations are defined by the authors of HowNet, have a large vocabulary and rich structure, and contain a large amount of human experience information. However, as a database defined by people, limited by the growth of expert level and total knowledge, there are inevitably some problems related to subjectivity and timeliness. Although the errors caused by these problems may not be obvious to the current deep learning methods, the integration of them with deep learning methods can complement each other and combine the advantages of different methods.

[0048] The meaning mentioned here was designed and constructed by Dong Zhendong, Dong Qiang and his son. It uses the concept (Sense) represented by English and Chinese words (Word) as the description object to explain the r...

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 a semantic meaning understanding method fusing semantic information, and belongs to the technical field of language information processing. The problem that an existing language modeling method is high in complexity and cannot give consideration to the effect is solved. The method comprises the following steps of: firstly, processing a language by taking each word as a unitaccording to two paths, wherein the left path is a word encoder + RNN + word decoder, and the output of the left path is recorded as wl; the right path comprises a synonym encoder+RNN + synonym decoder+a word decoder + sigmoid, and the output of the right path is recorded as wr; and then fusing the outputs of the two paths. The method is mainly for language meaning understanding.

Description

technical field [0001] The invention relates to a language meaning understanding method, which belongs to the technical field of language information processing. Background technique [0002] Language modeling (LM) is a central task in natural language processing (NLP) and language understanding. The purpose of language modeling is to display the probability distribution of a sequence of words. LMs play a key role in text generation tasks such as machine translation and document summarization. [0003] The model always predicts words based on context. In a simple N-gram language model, it assumes that each word is only relative to the previous N-1 words. In recent years, more and more neural network models have been established. They've got state-of-the-art performances and are still making progress. A classic neural network language model consists of an encoder and a decoder. In the encoder, the NN takes in a language sequence and encodes the left context of each word...

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 Applications(China)
IPC IPC(8): G06F40/30G06F40/216
CPCG06F40/30G06F40/216Y02D10/00
Inventor 王念滨汪先慈张耘周连科王红滨张毅崔琎
Owner HARBIN ENG 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