Text similarity matching model compression method and system for knowledge distillation
A text similarity and matching model technology, applied in the field of text matching, can solve the problems of small calculation, calculation speed bottleneck, complex model, etc., to achieve the effect of improving accuracy and avoiding the decrease of calculation speed
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0046] The preferred embodiments of the present invention will be described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described here are only used to illustrate and explain the present invention, and are not intended to limit the present invention.
[0047] The embodiment of the present invention provides a text similarity matching model compression method of knowledge distillation, such as figure 1 As shown, the method performs the following steps:
[0048] Step 1: Obtain training data;
[0049] Step 2: According to the training data, using the first deep text matching algorithm to determine the first training model;
[0050] Step 3: Distill the prior knowledge of the first training model into the training data of the second training model, and use the second deep text matching algorithm to determine the second training model, wherein the first deep text matching algorithm The calculation amount is greater th...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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