Problem matching method and device, equipment and medium

A matching method and problem technology, applied in the field of problem matching methods, equipment and media, devices, and intelligent search technology, can solve the problems of small negative sample space, ignoring similar information, and unsatisfactory sorting effects, so as to reduce bias performance, improve robustness, and increase the effect of negative sample space

Active Publication Date: 2019-12-06
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The classification model trained by the classification task ignores the similarity information, so the effect of using the classification model to sort is not ideal
[0005] uses the sorting model trained by the sorting task. Although the difference in similarity is taken into account, the random sampling method is often used in the process of constructing the data set. The negative The sample space is small (especially when the data is large and the negative sample space is large), so that the robustness of the trained ranking model is not enough, or there is a certain bias

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
  • Problem matching method and device, equipment and medium
  • Problem matching method and device, equipment and medium
  • Problem matching method and device, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0044] figure 1 It is a flow chart of a question matching method provided in the first embodiment of the present application. This embodiment is applicable to the situation of determining the similarity between two questions. Typically, this embodiment is applicable to the situation of determining the similarity between the retrieval question and the existing question in the existing question-answer pair in the retrieval question answering system. The method can be implemented by means of software and / or hardware. see figure 1 , the problem matching method provided in this embodiment includes:

[0045] S110. Using the question classification samples, train the basic network layer reused by the question classification model and the question ranking model, and the classification output network layer in the question classification model.

[0046] Wherein, the problem classification sample refers to a sample for training the model on the problem classification task.

[0047] ...

no. 2 example

[0074] This embodiment is an optional solution proposed on the basis of the foregoing embodiments.

[0075] figure 2 It is a schematic diagram of the structure of the basic network layer.

[0076] Such as figure 2 As shown, given two input questions, determine the word vector of each word in the question, and project the input question into a sentence vector;

[0077] The combination vector is determined according to the sentence vectors of the two questions, and the combination vector is input into the full link layer, processed by the full link layer, and input into the classification output network layer or the sorting output network layer.

[0078] In order to improve the accuracy of similarity determination, more similarity description elements are incorporated into the combination vector.

[0079] Typically, the combination vector is determined according to the sentence vectors of the two questions, including:

[0080] Splicing the sentence vector of the two questi...

no. 3 example

[0106] Figure 5 is a schematic structural diagram of a question matching device provided in the third embodiment of the present application. see Figure 5 , the question matching apparatus 500 provided in this embodiment includes: a classification training module 501 and a sorting training module 502 .

[0107] Wherein, the classification training module 501 is used to use the question classification samples to train the basic network layer reused by the question classification model and the question ranking model, and the classification output network layer in the question classification model;

[0108] The sorting training module 502 is configured to use the question sorting samples to train the basic network layer and the sorting output network layer in the question ranking model, so as to obtain a trained question ranking model for question matching.

[0109]In the technical solution of the embodiment of the present application, on the basis of using the problem sorting...

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 discloses a problem matching method and device, equipment and a medium, and relates to the field of cloud computing and data processing. According to the specific implementation scheme, the method comprises: using a problem classification sample to train a basic network layer multiplexed by a problem classification model and a problem sorting model and a classification output network layer in the problem classification model; and training the basic network layer and a sorting output network layer in a question sorting model by utilizing a question sorting sampleto obtain a trained question sorting model for question matching. According to the problem matching method and device, the equipment and the medium provided by the embodiment of the invention, the robustness of the problem sorting model is improved, and then the accuracy of problem matching is improved.

Description

technical field [0001] The embodiments of the present application relate to the field of data processing, and in particular to intelligent search technology. Specifically, this embodiment relates to a question matching method, device, device and medium. Background technique [0002] Existing models applied to question matching are often trained based on classification tasks or ranking tasks. In the classification task, given two questions, it is necessary to train the model to judge whether the two questions are similar; in the sorting task, given a central question, a positive sample and a negative sample, the model needs to give the positive sample a high score on the score of negative samples. [0003] In the ranking task, existing models applied to question matching suffer from the following shortcomings: [0004] The classification model trained by the classification task ignores the information of the degree of similarity, so the effect of using the classification m...

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): G06F16/332G06F16/33G06F16/35G06N3/04
CPCG06F16/3329G06F16/3344G06F16/35G06N3/045
Inventor 胡哲谢子哲彭程罗雪峰
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