Unlock instant, AI-driven research and patent intelligence for your innovation.

New word recognition method and device based on BERT pre-training model

A new word recognition and pre-training technology, applied in character and pattern recognition, biological neural network models, instruments, etc., can solve problems such as the inability to correctly identify the meaning of sentences and the inability to accurately identify new words.

Pending Publication Date: 2021-06-01
科技日报社
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the current semantic recognition scenario, it is often impossible to correctly identify the meaning of the sentence due to the inability to accurately recognize the new words in the sentence

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
  • New word recognition method and device based on BERT pre-training model
  • New word recognition method and device based on BERT pre-training model
  • New word recognition method and device based on BERT pre-training model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of them. the embodiment. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0036] In the current process of semantic recognition, due to the inability to accurately recognize new words, the exact meaning of sentences containing new words cannot be recognized. For example, Xiao Li aspires to become a slash youth. The word combinations after word segmentation using the old word algorithm include: Xiaoli, Lizhi, Become, Yiming, Slash, and Youth. Based on the 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 provides a new word recognition method and device based on a BERT pre-training model, and relates to the technical field of new word mining, and the method comprises the steps of: obtaining corpus information, and carrying out word segmentation processing on the corpus information through an N-Gram word segmentation algorithm to obtain a plurality of new words; inputting the new words into a shallow network of a BERT pre-training model, and outputting shallow dense vectors, wherein a bidirectional self-attention network is introduced into the BERT pre-training model, the shallow dense vectors comprise syntactic feature vectors and lexical feature vectors of the new words, and the shallow dense vectors are used for recognizing boundary information of the new words; extracting discrete features of the new words; and inputting the shallow dense vectors and the discrete features into a DNN dichotomy model, identifying correct new words, determining boundaries of the words through a shallow network of the BERT pre-training model, and further accurately identifying correct new words.

Description

technical field [0001] The invention relates to the technical field of new word mining, in particular to a new word recognition method and device based on a BERT pre-training model. Background technique [0002] With the rapid development of Internet technology, some emerging vocabulary, that is, "new words" are often coined. In the current semantic recognition scenario, it is often impossible to correctly identify the meaning of a sentence due to the inability to accurately recognize the new words in the sentence. Contents of the invention [0003] The object of the present invention is to provide a new word recognition method and device based on the BERT pre-training model. The shallow network of the BERT pre-training model determines the boundaries of words, and then accurately recognizes the correct new words. [0004] In the first aspect, the embodiment of the present invention provides a new word recognition method based on the BERT pre-training model, including: ...

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): G06F40/279G06F40/289G06K9/62G06N3/04
CPCG06F40/279G06F40/289G06N3/045G06F18/2414
Inventor 邵德奇石聪关培培朱经南赵诗阳冯超李腾飞段治平
Owner 科技日报社