Keyword extraction method based on deep learning language model fused with semantic features

A language model and deep learning technology, applied in the research field of keyword extraction in natural language processing, can solve unrealistic problems and achieve a good domain-independent effect

Pending Publication Date: 2021-02-12
CHONGQING UNIV OF POSTS & TELECOMM
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Manually labeling such a massive amoun

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
  • Keyword extraction method based on deep learning language model fused with semantic features
  • Keyword extraction method based on deep learning language model fused with semantic features
  • Keyword extraction method based on deep learning language model fused with semantic features

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0029]The technical solutions in the embodiments of the present invention will be described clearly and in detail below in conjunction with the drawings in the embodiments of the present invention. The described embodiments are only a part of the embodiments of the present invention.

[0030]The technical solutions of the present invention to solve the above technical problems are:

[0031]Such asfigure 1As shown, a keyword extraction method based on deep learning language model fusion semantic features, the basic implementation process is as follows:

[0032]Step S1. Given a target document d, first use natural language text processing tools to perform word segmentation and part-of-speech tagging on document d, select nouns or nominal phrases in it as candidate keywords, and obtain a candidate keyword set W={ w1,w2,...,wn}; At the same time, the target document is divided into sentences to obtain a set of sentences D = {s1,s2,...,sn}.

[0033]Step S2: Input the sentence set of the target docum...

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 discloses a keyword extraction method based on deep learning language model fused with semantic features, and belongs to the field of keyword extraction research in text processing. Themethod includes: processing a target text by using a text processing tool and only reserving adjectives and nouns in the target text to serve as candidate keywords of the target text; inputting the candidate keywords into a pre-training language model to obtain vector representation of each candidate keyword, performing sentence segmentation processing on the target document, similarly inputting the target document into the pre-training language model by taking sentences as units to obtain vector representation of each sentence, and for each candidate keyword, and calculating the mean value ofthe similarity sums of the candidate keywords and each sentence in the text, taking the mean value as the final score of the candidate keywords, and finally sorting the candidate keywords according to the scores of the candidate keywords to obtain the keywords of the text.

Description

technical field [0001] The invention belongs to the research field of keyword extraction in natural language processing, in particular to a keyword extraction method based on deep learning language model fusion semantic features. Background technique [0002] Keyword extraction refers to extracting a group of representative words from documents, which is a basic task of text information processing and an important topic in the field of natural language processing. Keywords extracted from documents can be regarded as A concise summary of documents is an important way to quickly obtain the subject content of documents. It can be used for classification, clustering, summary generation, and recommendation of documents. It is crucial for many fields of natural language processing. In the current era of information explosion, keyword extraction can help people quickly find key points from massive amounts of information. [0003] The keywords of a document are usually several word...

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): G06F40/211G06F40/289G06F40/30G06N20/00
CPCG06F40/211G06F40/289G06F40/30G06N20/00
Inventor 刘洪涛苏宁
Owner CHONGQING UNIV OF POSTS & TELECOMM
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