Unlock instant, AI-driven research and patent intelligence for your innovation.

Comment on training methods and apparatus for evaluation models

A technology for evaluating models and models, applied in the field of text processing, can solve problems such as small number of samples and training models, and achieve the effect of saving labeling costs

Active Publication Date: 2021-09-07
ADVANCED NEW TECH CO LTD
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when training a model for product reviews in a certain field, the number of samples in this field may be small, making it difficult to train a more accurate model

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
  • Comment on training methods and apparatus for evaluation models
  • Comment on training methods and apparatus for evaluation models
  • Comment on training methods and apparatus for evaluation models

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] Embodiments of this specification will be described below with reference to the accompanying drawings.

[0049] figure 1 A schematic diagram of a review evaluation system 100 according to an embodiment of the present specification is shown. Such as figure 1 As shown, the system 100 includes three neural network structures: a source domain neural network 11 , a shared neural network 12 and a target domain neural network 13 . As shown in the figure, X s represents the source domain input, X t Represents the target domain input. Among them, the shared neural network 12 is used to learn the common representations of the source domain and the target domain, and the source domain neural network 11 and the target domain neural network 13 are used to learn the unique representations of the source domain and the target domain respectively, so that through the source domain More data helps to train the shared neural network 12 for more accurately predicting the input of the ...

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 this specification provides a method and device for training a review evaluation model and a method and device for sorting reviews, the review evaluation model includes a neural network, and the neural network includes a source domain neural network, a target domain neural network, and a shared A neural network, the training method comprising: obtaining at least one sample, the at least one sample including at least one source domain sample and / or at least one target domain sample; inputting the comment text and domain label value included in each of the at least one sample The current model to predict at least one usefulness evaluation value respectively corresponding to the at least one sample; and using the at least one sample and the at least one usefulness evaluation value respectively corresponding to the at least one sample The model is trained such that the loss function of the model after training is reduced compared to before training.

Description

technical field [0001] The embodiments of this specification relate to the technical field of text processing, and more specifically, to a method and device for training a review evaluation model, and a method and device for sorting review texts. Background technique [0002] With the rapid development of online e-commerce, existing online consumers have formed the habit of judging the quality of products and services based on product reviews. Online e-commerce is not like traditional shopping, users can see and touch the real thing. Online shopping is nihility, and what users can see are the modified text and pictures of the merchants. Therefore, the user basically decides whether to select a product or a business based on the reviews. As more and more users share product reviews and a large number of merchant trolls get involved, it becomes increasingly difficult to judge the quality of these reviews. Many reviews that are useful (ie, informative) to consumers are burie...

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 Patents(China)
IPC IPC(8): G06F16/35G06N3/04G06N3/08G06F40/289
CPCG06N3/08G06F40/289G06N3/045
Inventor 陈岑周俊李小龙
Owner ADVANCED NEW TECH CO LTD