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

Part-of-speech tagging method, device and equipment and storage medium

A part-of-speech tagging and part-of-speech technology, applied in instruments, digital data processing, computing, etc., can solve problems such as time-consuming and labor-intensive, high professional knowledge requirements, inaccurate part-of-speech tagging results, etc., to enhance performance and improve the accuracy of part-of-speech tagging. degree of effect

Pending Publication Date: 2020-07-24
北京深知无限人工智能研究院有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Obtaining high-quality part-of-speech tagging corpus requires high professional knowledge of the tagger, and is also a time-consuming and labor-intensive project. It is difficult to accumulate a large amount of corpus in a short period of time; and the existing part-of-speech tagging models output The part-of-speech tagging results of the words in the original sentence are inaccurate

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
  • Part-of-speech tagging method, device and equipment and storage medium
  • Part-of-speech tagging method, device and equipment and storage medium
  • Part-of-speech tagging method, device and equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] figure 1 It is a flowchart of a part-of-speech tagging method provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation of how to accurately give the part of speech of each word in the original sentence for a given original sentence. The method can be executed by the part-of-speech tagging device provided by the embodiment of the present invention, the device can be implemented in the form of software and / or hardware, and the device can be integrated on the computing device. see figure 1 , the method specifically includes:

[0026] S110, acquiring the original sentence.

[0027] In this embodiment, the original sentence refers to the sentence to be marked with the part of speech of the word; the original sentence can be obtained directly, and the user enters the sentence in the form of text; it can also be obtained after converting the utterance input by the user in the form of voice into text form statement etc.

[0028] S12...

Embodiment 2

[0043] figure 2 The flow chart of a method for determining the part of speech of a function word provided by Embodiment 2 of the present invention. This embodiment is further optimized on the basis of the above Embodiment 1 to provide a solution for determining the part of speech of a sample function word in the function word part of speech corpus. see figure 2 , the method specifically includes:

[0044] S210. Determine sample function words in the sample sentence.

[0045] Specifically, for a given sample sentence, sample function words can be extracted from the sentence based on the characteristics of Chinese words. For example, the sample sentence is "When I bought strawberry ice cream, Zhang San was playing basketball", wherein the sample function word is "的".

[0046] S220, using the sample function words and the sample sentences as input of the semantic dependency model to obtain candidate words associated with the sample function words.

[0047]In this embodiment...

Embodiment 3

[0067] image 3 It is a flow chart of a part-of-speech tagging method provided by Embodiment 3 of the present invention. This embodiment provides a preferred example by further optimization on the basis of the foregoing embodiments. see image 3 , the method specifically includes:

[0068] S310. Determine sample function words in the sample sentence.

[0069] S320. Using the sample function words and the sample sentences as inputs to the semantic dependency model, to obtain candidate words associated with the sample function words.

[0070] S330. Determine the part of speech of the sample function word according to the semantic information of the candidate word and the sample function word.

[0071] S340, using the general part-of-speech corpus to train the neural network model to obtain a basic part-of-speech tagging model.

[0072] S350. Based on the parameters of the basic part-of-speech tagging model, determine the posterior probability of the part-of-speech of the sam...

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 part-of-speech tagging method, device and equipment and a storage medium. The method comprises the steps of obtaining an original statement; taking the original statement as the input of a part-of-speech tagging model to obtain the part-of-speech of each word in the original statement, wherein the part-of-speech tagging model is obtained by training a neural network model based on a virtual word part-of-speech corpus and a general word part-of-speech corpus. Through the technical scheme provided by the embodiment of the invention, the part-of-speechtagging accuracy of the words in the original statement is improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of artificial intelligence, and in particular to a part-of-speech tagging method, device, equipment and storage medium. Background technique [0002] Part-of-speech tagging in natural language processing is an important analysis method for obtaining syntactic and semantic structure information of sentences. While Chinese is a language that lacks morphological changes, high-quality part-of-speech analysis results can effectively improve the level of syntactic and semantic analysis. However, Chinese words are highly heterogeneous, which brings great challenges to automatic part-of-speech tagging. [0003] At present, Chinese part-of-speech tagging is mainly based on the part-of-speech tagging model, and the construction of the part-of-speech tagging model requires high-quality part-of-speech tagging corpus. Obtaining high-quality part-of-speech tagging corpus requires high professional ...

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): G06F40/117G06F40/284
Inventor 孙薇薇汉斯·乌思克尔特艾人龙
Owner 北京深知无限人工智能研究院有限公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com