Semantic similarity task model training method and device, electronic equipment and storage medium

A technology of semantic similarity and task model, which is applied in the fields of devices, electronic equipment and storage media, and the training method of semantic similarity task model, which can solve the difficulty of directly fitting the margin of the teacher model, the difficulty of signal migration of the teacher model, and the inability of the student model Effectively learn the teacher model and other issues to achieve a good knowledge transfer effect

Active Publication Date: 2020-08-14
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

This patented technique allows students who are learning about different things (like teachers) with similar goals or concepts more easily than they would otherwise have done without it. It improves how data scientists work on understanding complex systems by providing an improved way of comparing two models based upon their content.

Problems solved by technology

This patents discusses how deep neural networks have been developed over time due to their ability to accurately recognize patterns within documents or speech signals without being explicitly stated about them. These techniques require significant amounts of annotating data from both known sources and unknown ones during training process. Current methods involve performing regression analysis after each iteration until an acceptable level of accuracy has been achieved through trial-and-error procedures. Additionally, these previous approaches were limited when applied to new datasets containing irrelevant details such as annotations.

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
  • Semantic similarity task model training method and device, electronic equipment and storage medium
  • Semantic similarity task model training method and device, electronic equipment and storage medium
  • Semantic similarity task model training method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] Exemplary embodiments of the present application are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

[0028] figure 1 is a schematic diagram according to the first embodiment of the present application; as figure 1 As shown, this embodiment provides a training method for a semantic similarity task model, which may specifically include the following steps:

[0029] S101. When each piece of training data is used to train the semantic similarity task model, obtain the sc

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 similarity task model training method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence. Accordingto the specific implementation scheme, the method includes: when each piece of training data is adopted to train a semantic similarity task model, obtaining the score difference of positive and negative examples in the training data predicted by the semantic similarity task model; constructing an adaptive difference loss function of the semantic similarity task model based on the score differenceof the positive and negative examples in the training data obtained by a pre-trained semantic similarity scoring model and the score difference of the positive and negative examples in the training data predicted by the semantic similarity task model; and training the semantic similarity task model based on the adaptive difference loss function. According to the training method, the semantic similarity task model can learn signals of the semantic similarity scoring model more easily, and then the semantic similarity task model can effectively learn information of the semantic similarity scoring model.

Description

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

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
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD
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