Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Verb phrase component labeling method and device, electronic equipment and storage medium

A technology of verb phrases and target components, applied in the field of artificial intelligence, can solve problems such as complex and difficult to understand Chinese sentences, and achieve high accuracy and high efficiency

Pending Publication Date: 2021-10-08
PINGAN INT SMART CITY TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For the generation of similar phrase corpus, the modular analysis of verb phrases, and the extraction of the core words of verb phrases will not be very suitable, making it difficult to convert sentences from high-dimensional to Chinese sentences when doing specific model training tasks. When language information is reduced to lower-dimensional semantic information, it will be complicated and difficult for machines to understand Chinese 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
  • Verb phrase component labeling method and device, electronic equipment and storage medium
  • Verb phrase component labeling method and device, electronic equipment and storage medium
  • Verb phrase component labeling method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] figure 1 It is a flow chart of the verb phrase component labeling method provided by Embodiment 1 of the present invention. The verb phrase component labeling method specifically includes the following steps. According to different requirements, the order of the steps in the flow chart can be changed, and some of them can be omitted.

[0063] S11. Obtain multiple verb phrases.

[0064] Verb phrases are common phrases in daily life and in the current Chinese scene, and verb phrases are also the basic components of Chinese language components. Verb phrase refers to a phrase composed of a verb and some other words (with the verb as the center), expressing a concept. The verb phrase can be, for example, adverbial word+verb, verb+complementary word, adverbial word+verb+complementary word. After obtaining multiple verb phrases, analyze the components in the verb phrases, so as to identify two or three components such as adverbial words, verbs, and complement words from the...

Embodiment 2

[0141] figure 2 It is a structural diagram of the verb phrase component tagging device provided by Embodiment 2 of the present invention.

[0142] In some embodiments, the verb phrase component tagging device 20 may include a plurality of functional modules composed of computer program segments. The computer program of each program segment in the verb phrase component tagging device 20 can be stored in the memory of the electronic device, and executed by at least one processor to execute (see for details figure 1 Description) The function of marking the components of verb phrases.

[0143] In this embodiment, the verb phrase component tagging device 20 can be divided into multiple functional modules according to the functions it performs. The functional modules may include: an acquisition module 201 , a matching module 202 , a correction module 203 , a segmentation module 204 , a training module 205 and a labeling module 206 . The module referred to in the present inventio...

Embodiment 3

[0222] This embodiment provides a computer-readable storage medium, and a computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, the steps in the above embodiment of the verb phrase component tagging method are implemented, for example figure 1 S11-S16 shown:

[0223] S11, obtaining multiple verb phrases;

[0224] S12, create an adverbial template based on the preset adverbial vocabulary and create a complement template based on the preset complement vocabulary, match the plurality of verb phrases with the adverbial template and the complement template respectively, and obtain the key of each verb phrase elements of a word;

[0225] S13, correcting the composition of the keyword of each verb phrase to obtain the target composition;

[0226] S14. Segmenting the verb phrase in units of characters, and marking the target component corresponding to each character with a target label in a preset format to obtain a...

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 relates to artificial intelligence, and provides a verb phrase component labeling method and device, electronic equipment and a storage medium. An adverbial template is created based on a preset adverbial word list, a complement template is created based on a preset complement word list, and a plurality of obtained verb phrases are respectively matched with the adverbial template and the complement template; as the verb phrases may be matched with the adverbial templates and the complement targets at the same time, the components of the keywords of the matched verb phrases need to be corrected to obtain target components; if the components of the keywords of the matched verb phrases are incomplete, the verb phrases are segmented according to the word units, and target components are labeled with target labels in a preset format to obtain a data set, so that a labeling model is trained based on the data set, the labeling model is purified through a positive feedback test, and the target labeling model with high generalization performance and accuracy is obtained; the components of the verb phrases to be processed are labeled through the target labeling model, and the efficiency and the accuracy are high.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a verb phrase component labeling method, device, electronic equipment and storage medium. Background technique [0002] For machines to understand the Chinese language, verb phrases are very important in the segmentation of sentence modules and phrase modules. Deep understanding on the basis of phrases or abstraction and simplification at the language level will help machines understand humans. Language is very important. [0003] In the process of implementing the present invention, the inventors found that when faced with Chinese sentences, the traditional method usually divides the sentence into words or words, and then adopts the form of model training to obtain the attachment relationship between words. When faced with a Chinese phrase block, it is usually segmented according to the word, and the segmentation is meticulous. It is difficult to judge t...

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): G06F16/903G06F40/117G06F40/186G06F40/279G06N3/08
CPCG06F16/90344G06F40/117G06F40/186G06F40/279G06N3/08Y02D10/00
Inventor 陈凡
Owner PINGAN INT SMART CITY TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products