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

A Method of Named Entity Recognition Based on Hybrid Cascade Model

A named entity recognition and model technology, which is applied in the direction of specific mathematical models, calculation models, instruments, etc., can solve problems such as improving the difficulty of identifying complex named entities, and achieve the effect of improving recognition accuracy and recognition recall rate

Active Publication Date: 2019-02-05
NORTHEASTERN UNIV LIAONING
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This phenomenon of nesting among named entities greatly increases the difficulty of identifying complex named entities

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
  • A Method of Named Entity Recognition Based on Hybrid Cascade Model
  • A Method of Named Entity Recognition Based on Hybrid Cascade Model
  • A Method of Named Entity Recognition Based on Hybrid Cascade Model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0031] The named entity recognition method based on the hybrid cascading model proposed by the present invention significantly improves the recognition accuracy and recall rate of person-name entity, place-name entity and institution-name entity.

[0032] The recognition accuracy rate and the recognition recall rate are used to evaluate the quality of the named entity recognition results. The recognition accuracy rate refers to the ratio of the number of relevant documents retrieved to the total number of retrieved documents, and measures the precision rate of the retrieval system; The rate refers to the ratio of the number of retrieved related documents to the number of all related documents in the document library, which measures the recall rate of the retrieval system; the F value is the weighted harmonic average of the recognition accurac...

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

A named entity recognition method based on a hybrid cascade model, including: preprocessing; using an adaptive selection method, in a hidden Markov model and a conditional random field model, select a higher F value as an adaptive statistical recognition model, conduct preliminary named entity recognition on the preprocessed recognized corpus, and obtain preliminary named entity recognition results; construct a basic dictionary composed of a knowledge base and a recognition rule base; use the basic dictionary, and use an adaptive statistical recognition model to Perform secondary recognition on the preliminary named entity recognition results, analyze the F value of the secondary recognition results, and update the basic dictionary; build a hybrid cascading model, recognize the preprocessed corpus to be recognized layer by layer, and use the recognition results recognized by the current layer Add it to the basic dictionary for the next layer of recognition, and finally get the person name entity, place name entity and organization name entity in the corpus to be recognized. The recognition accuracy rate and recognition recall rate of the invention are significantly improved.

Description

technical field [0001] The invention belongs to the technical field of natural language processing, and in particular relates to a named entity recognition method based on a hybrid cascading model. Background technique [0002] With the application of emerging networks such as the Internet, cloud computing, mobile media, and the Internet of Things, a large number of user-created content Web 2.0 technologies have emerged, making Web applications enter the era of big data, and a series of Internet search engines, e-commerce, and social networking sites. Derivative business developed rapidly. Big data in the modern era has four characteristics: large amount of data, diverse data structures, fast data generation, and high commercial value. With large amounts of data, not all information is useful data. This leads to the coexistence of a large amount of invalid data and valuable data. Therefore, in the era of big data, how to find valuable data from huge data sets has become 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
Patent Type & Authority Patents(China)
IPC IPC(8): G06F17/27G06N7/00
CPCG06F40/295G06N7/01
Inventor 贾大宇王国仁信俊昌聂铁铮
Owner NORTHEASTERN UNIV LIAONING