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

A method and device for jointly identifying and connecting named entities

A named entity and named entity recognition technology, which is applied in the fields of instruments, computing, and electrical digital data processing, etc., can solve the problems that named entities cannot be connected, error propagation, etc.

Active Publication Date: 2021-07-06
北京如布科技有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, in the method of identifying named entities first and then connecting entities, there is a risk of error propagation, that is, the wrongly identified named entities in the first step or the named entities that have not been identified cannot be correctly connected to entities in the second step library

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 and device for jointly identifying and connecting named entities
  • A method and device for jointly identifying and connecting named entities
  • A method and device for jointly identifying and connecting named entities

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] figure 1 It is a flow chart of a method for jointly identifying and connecting named entities provided by Embodiment 1 of the present invention. This embodiment is applicable to the case of identifying and connecting named entities to input text. The method can be used to jointly identify and connect named entities The device is implemented, the device can be realized by means of software and / or hardware, and the method for jointly identifying and connecting named entities specifically includes the following steps:

[0050] Step 110, mark the part of speech of the word segmentation of the input text, and generate the word segmentation text.

[0051] Wherein, the input text can be the text input by the user or the text converted according to the voice input by the user, and the input text is segmented using a preset text segmentation system. For example, ICTCLAS (Institute of Computing Technology, Chinese Lexical Analysis System) can be used , Chinese lexical analysis s...

Embodiment 2

[0058] figure 2 It is a flowchart of a method for jointly identifying and connecting named entities provided by Embodiment 2 of the present invention. The technical solution of this embodiment is further refined on the basis of the above technical solution. Step 130 includes:

[0059] Step 210, when the word segmentation is the first-level word segmentation, according to the matching result of the first-level word segmentation and the preset named entity in the preset entity library, generate a word-segmentation answer combination of the first-level word segmentation.

[0060] Step 220, when the word segmentation is not the first-level word segmentation, according to the matching results of the current-level word segmentation in the word-segmented text and at least one preset named entity in the preset entity library, and the screening word-segmentation answer combination of the upper-level word segmentation, generate the current-level word segmentation Participle answer combin...

Embodiment 3

[0066] image 3 It is a flowchart of a method for jointly identifying and connecting named entities provided by Embodiment 3 of the present invention. The technical solution of this embodiment is further refined on the basis of the above embodiments, wherein step 230 is based on the word segmentation answer of this level Combined scoring results in named entity recognition and connectivity. Optionally, scoring the combination of word segmentation answers at this level includes:

[0067] Step 310, extract features of word segmentation answer combinations, and generate corresponding answer feature sets.

[0068] Among them, the characteristics of the participle answer combination include: each participle, the previous participle of each participle, the next participle of each participle, the first two participles of each participle, the last two participles of each participle, the part of speech of each participle, the part of speech of each participle The part of speech of th...

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 discloses a method and device for jointly identifying and connecting named entities. A method for joint identification and connection of named entities, comprising: marking part of speech of the word segmentation of the input text to generate a word segmentation text; connecting the word segmentation text and at least one preset entity library; determining the naming according to at least one candidate answer combination generated by the connection result The result of entity recognition and connection. The embodiment of the present invention proposes a method for jointly identifying and connecting named entities. The method takes into account the dependency between named entity recognition and entity connection, alleviates the problem of error propagation, and thus can improve the accuracy of named entity recognition and entity connection.

Description

technical field [0001] Embodiments of the present invention relate to natural language processing technology, and in particular to a method and device for jointly identifying and connecting named entities. Background technique [0002] Human-machine automatic response system based on natural language is an important application of natural language understanding. After the human-machine automatic response system performs special processing on the knowledge base in a certain field, the user asks questions in natural language, and the system can automatically give answers in the form of multimedia. [0003] Named entity recognition and entity linking are an important part of natural language understanding. In practical applications, the existing technology first performs named entity recognition (Named Entity Recognition), and then performs entity linking (EntityLinking). [0004] However, in the method of identifying named entities first and then connecting entities, there is...

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): G06F40/295
CPCG06F40/295
Inventor 郭瑞郭祥雷宇
Owner 北京如布科技有限公司
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com