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

Chinese named entity recognition model and method based on double neural network fusion

A named entity recognition, dual neural network technology, applied in biological neural network model, neural architecture, text database clustering/classification, etc., can solve problems such as difficult to learn

Active Publication Date: 2020-10-16
DALIAN NATIONALITIES UNIVERSITY
View PDF1 Cites 39 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the word "article" in most Chinese sentences represents a non-named entity, and it is difficult for the model to learn the representation of this different context

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
  • Chinese named entity recognition model and method based on double neural network fusion
  • Chinese named entity recognition model and method based on double neural network fusion
  • Chinese named entity recognition model and method based on double neural network fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] Chinese Named Entity Recognition: Various previous works try to solve the problem by treating Chinese sentences as a string because there are no separators such as spaces between Chinese words. Traditional models rely on rules or hand-extracted features (such as case, word form, part-of-speech tag, etc.). Based on these features, many machine learning algorithms have been applied to supervised NER, including HMMs, SVM, and CRF. In recent years, neural network methods have been applied to English NER. This shows that neural networks that are good at automatically mining hidden features can outperform traditional machine learning methods without handcrafted features. Deep learning-based models treat the NER task as a sequence labeling task, including the input of distributed word representations, contextual encoding, and token decoding.

[0064] Distributed representation of input: Depending on the granularity, most models can be divided into two categories: word-based ...

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 Chinese named entity recognition model and method based on double neural network fusion, which belong to the field of named entity recognition. The problem that an existing single model often has insufficient feature representation is solved. The model comprises a Bert embedding layer used for converting a sentence from a character sequence to a dense vector sequence, anda Bi _ LSTM layer with a self-attention mechanism, wherein the Bi _ LSTM layer learns the implicit representation of the words from the context in the whole process, processes sentence layer information, and obtains the preceding and following text information with long-distance dependence characteristics; the model further comprises a stacking a DCNN layer which combines wider context informationinto a mark for representation, extracts local information of characters, and obtains preceding and following text information with wide local features, and a CRF decoding layer which is used for decoding dual-model output into sequence marks and explicitly outputting named entities through labels marked by the sequence marks. The model has the effect of enhancing the capability of implicitly acquiring context representation among character sequences of the model.

Description

technical field [0001] The invention belongs to the field of named entity recognition, and relates to a Chinese named entity recognition model and method based on double neural network fusion. Background technique [0002] Named Entity Recognition (NER), as a basic work of information extraction, has been attracting people's attention in recent years. The task of NER is to identify entity names from text and classify their types into different categories, such as person names, place names, organization names, etc. For example, given the sentence "Steve Jobs is the founder of Apple", the task of NER is to recognize that "Steve Jobs" is a person name entity and "Apple" is a company name entity. NER is a fundamental and important task in the field of natural language processing (NLP), which can be used for many downstream NLP tasks, such as entity linking, relation extraction, and question answering. [0003] Research on named entity recognition has been carried out for a lon...

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): G06F40/295G06F40/126G06F16/35G06N3/04
CPCG06F40/295G06F40/126G06F16/35G06N3/049G06N3/045Y02D10/00
Inventor 赵丹丹孟佳娜刘爽张志浩
Owner DALIAN NATIONALITIES UNIVERSITY
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