Named entity identification method based on time convolution network

A named entity recognition and convolutional network technology, applied in neural learning methods, biological neural network models, special data processing applications, etc., can solve problems such as slow running speed, achieve increased size, improved flexibility, training and verification The effect of shortening time

Pending Publication Date: 2019-11-12
DALIAN UNIV
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

This patented technology allows for better extraction of timings during sequences through an algorithm called Time Convolution (TC). By doing this with just one dimensionally inherited convolution, it overcomes issues such as slow convergence or lack of memory when dealing with real world data. Additionally, its Backpropagated Pathway differs from regular convolution processing due to differences between times at both ends. It also simplifies the process of learning networks quickly without losing their ability to recall past experiences. Overall, these technical improvements improve performance and efficiency across various types of neural systems used today.

Problems solved by technology

The technical problem addressed by this patented technology is that current networks have limited ability for recognizing new or changed things quickly due to their limitations such as being too short memory capacity or requiring large amounts of storage space.

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
  • Named entity identification method based on time convolution network
  • Named entity identification method based on time convolution network
  • Named entity identification method based on time convolution network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0033] Example: see figure 1 , Is the overall architecture of the model proposed by the present invention, which is mainly composed of three parts: the feature presentation layer, the TCN and the CRF layer. Among them, the feature representation layer is mainly composed of word vectors and character feature layers. The word vector layer and the character vector layer accept words and characters as input respectively, and map the discrete One-hot representations to their respective continuous dense low-dimensional feature spaces; then, the word vectors and character-level vectors are spliced ​​to represent words Features in a specific semantic space; then the spliced ​​features are used as the input of TCN, and different features extracted by TCNs with different convolution kernel sizes are merged to obtain the final feature h 1 h 2 ...h n , And use this as the input of the CRF layer. After CRF further restricts the context labeling, the output sequence labeling result y 1 y 2 ....

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 named entity identification method based on a time convolution network. The method comprises the following steps of: firstly, constructing a feature representation layer which mainly consists of a word vector and a character feature layer, wherein the word vector layer and the character vector layer respectively accept words and characters as input, and respectively mapdiscrete One-hot representations to respective continuous dense low-dimensional feature spaces; splicing the word vectors and the character-level vectors to represent features of the words in a particular semantic space; secondly, taking the spliced features as input of a time convolution network, extracting different features through the time convolution network with different fusion convolutionkernel sizes, and obtaining final features h1h2... hn; finally, taking the obtained features as input of a CRF layer; and after the CRF further restrains context annotation, outputting sequence annotation results y1y2... yn. Compared with an existing LSTM network, the TCN network has the advantages that the recognition precision is slightly improved, and the training time is only about 1/3 of thatof the LSTM network.

Description

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

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
Owner DALIAN UNIV
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