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

Sentence vector generation method and device based on bidirectional representation model and computer equipment

A sentence vector and representation technology, applied in the field of artificial intelligence, can solve problems such as unsatisfactory sentence vectors, affecting the accuracy of sentence vectors, difficulty in obtaining training samples, etc., to improve quality, avoid semantic loss, and reduce semantic loss Effect

Pending Publication Date: 2021-11-30
PING AN TECH (SHENZHEN) CO LTD
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Some of the existing sentence vector generation technologies simply divide the words in the sentence and then generate a sentence vector, but this will lose the semantic information in the sentence and affect the accuracy of the sentence vector; some generate sentence vectors through supervised learning. However, in practical applications, it is difficult to obtain a large number of high-quality, labeled training samples, so the sentence vectors generated by the model are often not satisfactory

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
  • Sentence vector generation method and device based on bidirectional representation model and computer equipment
  • Sentence vector generation method and device based on bidirectional representation model and computer equipment
  • Sentence vector generation method and device based on bidirectional representation model and computer equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field of the application; the terms used herein in the description of the application are only to describe specific embodiments The purpose is not to limit the present application; the terms "comprising" and "having" and any variations thereof in the specification and claims of the present application and the description of the above drawings are intended to cover non-exclusive inclusion. The terms "first", "second" and the like in the description and claims of the present application or the above drawings are used to distinguish different objects, rather than to describe a specific order.

[0044] Reference herein to an "embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The occurrenc...

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 embodiment of the invention belongs to the field of artificial intelligence, and relates to a sentence vector generation method and device based on a bidirectional representation model, computer equipment and a storage medium, and the method comprises the steps of generating a translated text set of each initial text in an initial text set; determining similar texts of the initial text in the translated text set according to the similarity; obtaining an initial sentence vector of the initial text and a similar sentence vector of the similar text through an initial bidirectional representation model; for the initial text, taking the similar sentence vector of the initial text as a positive sample, taking other initial sentence vectors and similar sentence vectors in the initial text set as negative samples, and carrying out comparative learning on the initial bidirectional representation model to obtain a bidirectional representation model; and inputting the to-be-processed text into the bidirectional representation model to obtain a sentence vector of the to-be-processed text. In addition, the invention also relates to a block chain technology, and the initial text set can be stored in a block chain. According to the invention, the accurate and available sentence vectors can be efficiently generated.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, in particular to a method, device, computer equipment and storage medium for generating sentence vectors based on a bidirectional representation model. Background technique [0002] In the field of natural language processing, how to obtain high-quality sentence embeddings has always been one of the research hotspots. The generation of sentence vectors usually maps the words (tokens) in a sentence to a quantifiable space. In specific tasks, the generated sentence vectors are usually provided to downstream tasks for further processing, such as similarity calculation, classification and clustering based on sentence vectors. [0003] Some of the existing sentence vector generation technologies simply divide the words in the sentence and then generate a sentence vector, but this will lose the semantic information in the sentence and affect the accuracy of the sentence vecto...

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): G06F40/211G06F16/33G06F40/289G06F40/30G06K9/62
CPCG06F40/211G06F40/289G06F40/30G06F16/3344G06F18/214Y02D10/00
Inventor 陈浩谯轶轩
Owner PING AN TECH (SHENZHEN) CO LTD
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