Chinese humor classification model based on reverse translation

A classification model, Chinese technology, applied in the direction of text database clustering/classification, natural language translation, biological neural network model, etc., can solve the problem that machine learning cannot obtain meaning well

Pending Publication Date: 2021-05-18
DALIAN NATIONALITIES UNIVERSITY
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, compared with English humorous language, the humorous form and characteristics of Chinese have some differences in syntactic structure and grammatical form, so that machine learning cannot better obtain the meaning and select features to judge text corpus in a targeted manner. Is it a humorous statement

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
  • Chinese humor classification model based on reverse translation
  • Chinese humor classification model based on reverse translation
  • Chinese humor classification model based on reverse translation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] 1.1 Solve the problem

[0046] This invention proposes a Chinese humor classification model based on reverse translation. Under the background of the rapid development of artificial intelligence and human-computer interaction in today's society, it is urgent to make machines have emotions and a sense of humor, and the task of humor classification has emerged as the times require. The present invention analyzes the tendency of Chinese text humor, systematically analyzes the relevant research on text humor classification, and explores the different influence capabilities of different deep learning deep representations in humor classification tasks. Using deep learning technology to study and extract the salient features of the data set of the present invention, based on the method based on reverse translation technology combined with linguistic humor theory, a basic model BERT-BiGRU-Softmax is proposed to classify Chinese text humor , and gradually add different humorous ...

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 Chinese humor classification model based on reverse translation, and belongs to the field of natural language processing, and comprises S1 a text input layer, S2, a BERT embedding layer; s3, a Chinese phonetic alphabet feature embedding layer; s4, a text part-of-speech feature embedding layer; s5, a feature fusion layer; s6, a BiGRU layer; s7, a full-connection layer, wherein the full-connection layer finally completes classified output of Chinese text humor. The method has the beneficial effects that on the basis of a method of combining a reverse translation technology with a linguistic humor theory, a basic model BERT-BiGRU-Softmax is proposed to perform classification research on Chinese text humor, different humor features are gradually added into the model, a feature fusion model BERT + POS + Homophony-BiGRU-Softmax is realized, and the model has an effect on finally judging whether the Chinese text is humor or not.

Description

technical field [0001] The invention belongs to the field of natural language processing and relates to a Chinese humor classification model based on reverse translation. Background technique [0002] Humor, one of the important ways of emotional expression, has always been with people's lives. With the rapid development of national science and technology and the large-scale popularization of the Internet and communication equipment, the application of the Internet and artificial intelligence is undergoing a drastic change from "reading" to "interactive". Humorous "interactive" also came into being. Humor can not only bring happiness to people, but also improve social skills and work efficiency. At present, chatbots, the representatives of "interactive" applications, mostly collect various network resources and then integrate information to interact with service objects, but there are very few chatbots with humorous functions. Such chatbots have no " temperature", the cha...

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): G06F16/35G06F40/58G06F40/268G06N3/04G06N3/08
CPCG06F16/353G06F40/58G06F40/268G06N3/08G06N3/044G06N3/045
Inventor 孙世昶孟佳娜刘玉宁朱彦霖
Owner DALIAN NATIONALITIES UNIVERSITY
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap