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

Model adversarial training method and device and named entity recognition method and device

A technology of named entities and models, applied in neural learning methods, biological neural network models, instruments, etc.

Active Publication Date: 2020-08-11
ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
View PDF7 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This sparsity of training data brings great challenges to model training

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
  • Model adversarial training method and device and named entity recognition method and device
  • Model adversarial training method and device and named entity recognition method and device
  • Model adversarial training method and device and named entity recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0076] The solutions provided in this specification will be described below in conjunction with the accompanying drawings.

[0077] figure 1 A schematic diagram of an implementation scenario of an embodiment disclosed in this specification. Among them, the sequence of word segmentation that will contain multiple word segmentation Input the feature extraction network, and the feature extraction network can output the feature hidden vector of each word segment , based on each feature latent vector, the distribution probability of each participle in each category can be determined, and based on these distribution probabilities, the classification result of each participle is obtained, that is, the label of which category each participle corresponds to. Categories can be represented by labels. SOS is the start symbol of the word segmentation sequence, and EOS is the end symbol of the word segmentation sequence.

[0078] Named entities (Entity), also known as entity words, ha...

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 provides a model adversarial training method and device and a named entity recognition method and device. The adversarial training method comprises steps of during training, replacing a first named entity in the first sample sequence with a corresponding original label character to obtain a second sample sequence, determining a first text fragment containing the replaced original label character from the second sample sequence, and determining a classification label value of the first text fragment as a first value for representing a replaced named entity; determining feature implicit vectors of a plurality of segmented words in the second sample sequence by adopting a feature extraction network; determining a first segment vector of the first text segment based on the feature implicit vectors of the plurality of segmented words in the second sample sequence, and inputting the first segment vector into a first discriminator to obtain a first prediction value; determining a first loss value based on a difference between the first prediction value and the first value; updating the first discriminator by taking minimization of the first loss value as atarget; and updating the feature extraction network by taking maximization of the first loss value as a target.

Description

technical field [0001] One or more embodiments of this specification relate to the technical field of natural language processing, and in particular, relate to model confrontation training and named entity recognition methods and devices. Background technique [0002] In the field of natural language processing technology, the classification of named entities (Entity) in text sequences is an important direction of research. Named entities have the nature of nouns in the part of speech, including person names, organization names, place names, and all other entity categories identified by names. Broader named entities also include categories such as numbers, dates, currencies, addresses, and more. Accurate recognition of the categories of named entities can improve the accuracy and effectiveness of natural language processing. [0003] Usually, a training set is used to train a model for recognizing named entities, and after the model is trained, a test set is used to test t...

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): G06F40/284G06F40/295G06N3/04G06N3/08
CPCG06F40/284G06F40/295G06N3/049G06N3/084G06N3/044G06N3/045
Inventor 李扬名李小龙姚开盛
Owner ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
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