Mongolian named entity recognition method based on neural network and recognition system thereof

A technology of named entity recognition and neural network, applied in the field of Mongolian named entity recognition method and its recognition system, can solve problems such as poor performance, and achieve the effect of optimizing the splicing method and strong applicability

Active Publication Date: 2019-02-19
INNER MONGOLIA UNIVERSITY
View PDF4 Cites 32 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The information source of the neural network method based on BLSTM and CRF for named entity recognition is mainly annotated corpus, which makes the performance of the technique poor when it is only transplanted to traditional Mongolian.

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
  • Mongolian named entity recognition method based on neural network and recognition system thereof
  • Mongolian named entity recognition method based on neural network and recognition system thereof
  • Mongolian named entity recognition method based on neural network and recognition system thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the embodiments of the present invention. Apparently, the described embodiments are only some of the embodiments of the present invention, not all of them. 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.

[0046] The external source of information currently introduced for BLSTM- and CRF-based neural network methods is word embeddings obtained using large unlabeled corpora. Considering that in the text, to judge whether a word belongs to a named entity, its context information is also valuable. From the perspective of data source used, the present invention is divided into unlabeled text corpus and labeled text corpus, adopts forward and backward two stacked LSTM neural language...

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 Mongolian named entity recognition method based on neural network and a recognition system thereof, and belongs to the technical field of natural language processing. The recognition system comprises a Glove tool, a bi-directional language model component obtaining module, a language model vector obtaining module, a BLSTM vector obtaining module, an attention mechanism layer, a CRF layer and a final model obtaining module. The invention adopts forward and backward cascade neural language model BLSTM to learn context information from a large amount of unlabeled corpus,and introduces the learned context information into a neural network based on BLSTM and CRF by attention mechanism, thereby improving Mongolian named entity recognition efficiency and solving the problems existing in the prior art.

Description

technical field [0001] The invention belongs to the technical field of natural language processing, and relates to a neural network-based Mongolian named entity recognition method and a recognition system thereof. Background technique [0002] Traditional Mongolian is the main language of the Inner Mongolia Autonomous Region of my country. However, its research on natural language processing has just started, and its development is relatively lagging behind compared with major languages ​​such as Chinese and English. [0003] Named entity recognition is the basic information unit in the text, mainly including person names, place names, organization names, etc. Named entity recognition is an important basic work for natural language processing tasks such as machine translation, question answering system, syntax analysis, information extraction, and knowledge graph. [0004] In the field of traditional Mongolian named entity recognition, the existing methods can be divided i...

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): G06F17/27G06N3/04G06N3/08
CPCG06N3/084G06F40/295G06N3/045
Inventor 苏向东高光来熊玉竹飞龙
Owner INNER MONGOLIA UNIVERSITY
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