Biomedicine English word sense disambiguation method based on graph attention neural network

A biomedical and word sense disambiguation technology, applied in the field of biomedical English word sense disambiguation, can solve problems such as polysemy of a word, and achieve the effect of improving the accuracy of disambiguation

Pending Publication Date: 2022-03-15
HARBIN UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, in order to solve the polysemy phenomenon in biomedical English in the field of natural language processing, the present invention discloses a biomedical English word sense disambiguation method based on graph attention neural network

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
  • Biomedicine English word sense disambiguation method based on graph attention neural network
  • Biomedicine English word sense disambiguation method based on graph attention neural network
  • Biomedicine English word sense disambiguation method based on graph attention neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] In order to clearly and completely describe the technical solutions in the embodiments of the present invention, the present invention will be further described in detail below in conjunction with the drawings in the embodiments.

[0060] Take the disambiguation processing of the ambiguous word "ADA" in the biomedical English sentence "Big budget surplus for ADA reported" as an example.

[0061] The embodiment of the present invention is based on the flow chart of the biomedical English word sense disambiguation method based on graph attention neural network, as figure 1 shown, including the following steps.

[0062] Step 1 The extraction process of disambiguation features is as follows:

[0063] English sentence "Big budget surplus for ADA reported"

[0064] Step 1-1 Use the English word segmentation tool to segment the sentence into vocabulary, and the word segmentation result is: Big budgetsurplus for ADA reported

[0065] Step 1-2 Use the English part-of-speech t...

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 a biomedicine English word sense disambiguation method based on a graph attention network (GAT), and relates to a biomedicine English word sense disambiguation method based on the GAT. The method comprises the following steps: firstly, preprocessing a biomedical English corpus; and in the step, part-of-speech tagging and semantic tagging processing is carried out on statements, containing ambiguous vocabularies, of the training corpus and the test corpus. A sentence where ambiguous vocabularies are located and word forms, part-of-speech and semantics contained in the sentence serve as disambiguation features, the disambiguation features serve as nodes to construct a word sense disambiguation feature graph, a training corpus is used for training a GAT model, and the model is optimized. And word sense disambiguation is performed on the test corpus by using the optimized GAT model, so that probability distribution of ambiguous vocabularies under each semantic category can be obtained. And judging the semantic class corresponding to the maximum probability value as the semantic class of the ambiguous vocabulary. The method has a good word sense disambiguation effect, and the real meaning of the ambiguous vocabulary is more accurately judged.

Description

Technical field: [0001] The invention relates to a biomedical English word sense disambiguation method based on a graph attention neural network, which can be well applied in the field of natural language processing. Background technique: [0002] Word sense disambiguation is an "intermediate problem" that affects many other application problems in the field of natural language processing, and is an important and indispensable key link in the process of natural language processing. Word sense disambiguation is widely used in natural language processing. Natural language processing with text understanding ability can be used in machine translation, automatic summarization, question answering system, public opinion analysis, machine writing, information retrieval and text classification, etc., and has broad application fields and encouraging application prospects. [0003] Artificial neural network has been a research hotspot in the field of artificial intelligence since the ...

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): G06F40/268G06F40/30G06F16/33G06K9/62G06N3/04G06N3/08
CPCG06F40/268G06F40/30G06F16/3346G06N3/084G06N3/047G06N3/045G06F18/241G06F18/2415
Inventor 王明磊刘睿苑庆贤
Owner HARBIN UNIV OF SCI & TECH
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