A method and device for sentence template recall based on seed sentences

A seed sentence and sentence technology, applied in the field of sentence template recall based on seed sentences, can solve the problems of incorrect sentences and poor diversity of recalled sentences, and achieve the effect of small semantic deviation

Active Publication Date: 2019-08-09
广东惠禾科技发展有限公司
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, according to the similarity calculation of words, since only part of the words are replaced, the newly recalled sentences are often very similar to the seed sentences; in this way, the diversity of the recalled sentences will be poor; Similar replacement, and whether the replaced word is also used in the same sentence, in this case, the recalled sentence is likely to be wrong

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
  • A method and device for sentence template recall based on seed sentences
  • A method and device for sentence template recall based on seed sentences
  • A method and device for sentence template recall based on seed sentences

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] Embodiment 1 of the present invention proposes a method for recalling a sentence template based on a seed sentence, such as figure 1 shown, including the following steps:

[0051] Step 101, acquiring corpus related to the seed sentence whose quantity exceeds a certain value;

[0052] Specifically, the correlation can be domain-related. For example, the seed sentence is "today's Hunan cuisine is delicious" and belongs to the food domain, so that the corpus of the food domain can be obtained if the number exceeds a certain value; of course, the same is true for other domains, for example It can also be a news sentence, that is, it belongs to the news field and so on. In addition, the more specific numbers, the better. There is only a lower limit, but no upper limit. The more the number is obtained, the more sentence templates will be recalled, and the more accurate it will be.

[0053] Step 102, determine the dependency syntax tree of each sentence in the corpus;

[00...

Embodiment 2

[0081] Embodiment 2 of the present invention also proposes a device for recalling a sentence template based on a seed sentence, such as Figure 5 shown, including:

[0082] An acquisition module 201, configured to acquire corpus related to the seed sentence whose quantity exceeds a certain value;

[0083] The first determination module 202 is used to determine the dependency syntax tree of each sentence in the corpus;

[0084] The second determination module 203 is used to recall each sentence in the corpus based on the tree structure of the dependent syntactic tree of the seed sentence according to the structural similarity of the dependent syntactic tree, and set the recalled sentence as the initial sentence template ;

[0085] The third determining module 204 is used to calculate the correlation between each of the initial sentence templates and the seed sentence, and determine the correlation between each of the initial sentence templates and the seed sentence;

[0086]...

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 and equipment for recalling a sentence template based on a seed sentence. The method specifically comprises the following steps of obtaining corpuses, and determining a dependency syntax tree of each sentence of each corpus, wherein the number of corpuses exceeds a certain value, and each corpus relates to the seed sentence; according to the structure similarity of the dependency grammar trees, recalling each sentence in each corpus based on a tree structure of a dependency grammar tree of the seed sentence, and determining recalled sentences; calculating the similarity between the recalled sentences and the seed sentence, and determining the relevancy between each recalled sentence and the seed sentence; according to the relevancy, selecting a recalled sentence as the sentence template. The method at least has one of the following characteristics that the type of the recalled sentences is richer; the recalled sentences basically have no grammar mistake; components of the recalled sentences are richer; the semantics deviation of the recalled sentences is little; the recalled sentences are designed with a template, and an artificial template is not needed.

Description

technical field [0001] The invention relates to the field of information processing, in particular to a method and device for recalling a sentence template based on a seed sentence. Background technique [0002] In the prior art, most of the similarity calculations for sentence templates are based on word similarity. However, according to the similarity calculation of words, since only part of the words are replaced, the newly recalled sentences are often very similar to the seed sentences; in this way, the diversity of the recalled sentences will be poor; Similar replacement, and whether the replaced word is also used in the same sentence, in this case, the recalled sentence is likely to be wrong. Contents of the invention [0003] Aiming at the defects in the prior art, the present invention proposes a method and device for recalling a sentence template based on a seed sentence to overcome the defects in the prior art. [0004] Specifically, the present invention propo...

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): G06F17/27
CPCG06F40/211G06F40/253G06F40/30
Inventor 姚佳
Owner 广东惠禾科技发展有限公司
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