Method and device for judging continuity of conversion contents and equipment

A coherent, content technology, applied in the computer field, that can solve problems such as incoherent responses

Active Publication Date: 2018-11-27
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF6 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the traditional method only compares the similarity between two sentences

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
  • Method and device for judging continuity of conversion contents and equipment
  • Method and device for judging continuity of conversion contents and equipment
  • Method and device for judging continuity of conversion contents and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] In a specific implementation, the dialog content includes the above and the current sentence. In order to determine whether the current sentence q is semantically coherent with the above c, a method for judging the coherence of the dialog content is provided, such as figure 1 shown, including:

[0050] Step S100: Input the above sentence into the sentence generation model to generate the following sentence.

[0051] In order to better express the sentence generation model, first define some variables, see figure 2 and image 3 , the above sentence is represented by s, the current sentence is represented by q, the above is represented by c, the above c includes multiple above sentences s, and is represented by a set, c={s 1 ,s 2 ,...,s n}. see figure 2 , the sentence generation model can adopt models in the field of dialogue systems and machine translation. One implementation of the sentence generation model can be: given the above sentence s, generate the follo...

Embodiment 2

[0081] In another specific embodiment, such as Figure 4 As shown, a device for judging the coherence of dialogue content is provided, including:

[0082] The following sentence generation module 10 is used to input the above sentence into the sentence generation model to generate the following sentence;

[0083] The first similarity matrix construction module 20 is used to calculate the similarity between each of the above sentences and the current sentence to construct the first similarity matrix;

[0084] The second similarity matrix construction module 30 is used to calculate the similarity between each of the following sentences and the current sentence to construct a second similarity matrix;

[0085] The coherence feature parameter calculation module 40 is used to input the first similarity matrix and the second similarity matrix into the coherence discrimination model respectively to generate the coherence feature parameter of the current sentence, and the coherence ...

Embodiment 3

[0094] An embodiment of the present invention provides a device for judging the continuity of dialogue content, such as Image 6 shown, including:

[0095] A memory 400 and a processor 500 , the memory 400 stores computer programs that can run on the processor 500 . When the processor 500 executes the computer program, the method for judging the continuity of the dialogue content in the foregoing embodiments is implemented. The number of memory 400 and processor 500 may be one or more.

[0096] The communication interface 600 is used for the memory 400 and the processor 500 to communicate with the outside.

[0097] The memory 400 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one magnetic disk memory.

[0098] If the memory 400, the processor 500, and the communication interface 600 are implemented independently, the memory 400, the processor 500, and the communication interface 600 may be connected to...

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 provides a method for judging continuity of conversion contents. The method includes the steps that previous text sentences are input into a sentence generation model, so that next textsentences are generated; the similarity of each previous text sentence and a current sentence is calculated to construct a first similarity matrix; the similarity of each next text sentence and the current sentence is calculated to construct a second similarity matrix; the first similarity matrix and the second similarity matrix are separately input into a continuity judgment model to generate continuity feature parameters of the current sentence, and the continuity judgment model is constructed based on a convolutional neural network. The continuity judgment model and the sentence generationmodel are combined to realize the continuity of the conversion contents; the continuity of two sentences can be compared based on dimensions of semantics, and replies which are continuous and excellent in quality are pushed to users. The invention further provides a device for judging the continuity of the conversion contents and equipment.

Description

technical field [0001] The invention relates to the field of computers, in particular to a method for judging the coherence of dialogue content, and also relates to a judging device for the coherence of dialogue content, a device for judging the coherence of dialogue content, and a computer-readable storage medium. Background technique [0002] In a general dialog system, how to make the context content in the dialog process coherent is an urgent problem to be solved. Content coherence refers to the contextual relevance of the dialogue, that is, the coherence between the current sentence and the previous sentence, or the current sentence and the next sentence in terms of semantic theme logic. For example, the content mentioned above is "The World Cup is really exciting", and its content is related to the theme of football. If the feedback below is "Ball and Ball Battle is really fun", its content is related to the theme of the game, indicating that the above is lack of seman...

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
IPC IPC(8): G06F17/30G06F17/27
CPCG06F40/30
Inventor 彭金华马宗阳连荣忠姜迪何径舟
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