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

Method and device for relation extraction based on semantic level

A technology of relation extraction and semantics, applied in semantic analysis, natural language data processing, instruments, etc., can solve problems such as obtaining effective information, relation extraction errors, and poor results

Active Publication Date: 2022-03-04
THE 28TH RES INST OF CHINA ELECTRONICS TECH GROUP CORP
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Most of the technical solutions in the prior art are carried out based on English corpus, but Chinese and English have great differences in linguistics, Chinese expressions are more diverse, and there are a large number of different words expressing the same meaning, so Traditional relational extraction schemes do not work well in Chinese. They cannot accurately identify entity words from the text, and cannot classify entity words into correct named entities. Therefore, it is difficult to obtain effective information from the text, and there are problems in relation extraction. error problem, while relational triples are far from being able to fully express the overall meaning of the Chinese text

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
  • Method and device for relation extraction based on semantic level
  • Method and device for relation extraction based on semantic level

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The technical solutions of the present invention will be further described below with reference to the accompanying drawings.

[0022] See figure 1 It is a flowchart showing a flow of a semantic level based on a semantic level provided by the present invention.

[0023] Step 1, establish a named entity dictionary associated with the data set field.

[0024] In the embodiment of the present invention, the named entity dictionary includes a nomenclature and a corresponding entity vocabulary, a semantic level of nomenchat entity, and a naming entity matching relationship in a semantic level; the data set includes a training set.

[0025] In the specific implementation, due to the different vocabulary of the same meaning in Chinese, the field of nomenchatgical dictionary is established, the field of the nomenclature is required to be associated with the fields to be identified, and all the words will be covered in this field as much as possible. In the case of using a variety o...

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 semantic level-based relation extraction method and device. The method includes: establishing a named entity dictionary associated with the field of data sets; using the trained relation extraction model to extract the entity vocabulary relation from the text to be recognized to obtain the entity The relation sentence of vocabulary; The training process of described relation extraction model comprises: the relation between training relation extraction model identification training set text entity vocabulary and named entity; Based on semantic level, use training set to carry out entity vocabulary relation training to relation extraction model . With the above technical solution, for the effective identification of entity words in the text data, the extraction result can completely and accurately express the overall meaning of the Chinese text.

Description

Technical field [0001] The present invention relates to the field of natural language processing, and more particularly to a relationship extraction method based on a semantic level. Background technique [0002] Today, the amount of data on the Internet is explosive, but most of them are unstructured data, and they are difficult to quickly obtain effective information from them for users. Therefore, the unstructured data is converted into structured data, and the rapid extraction of effective information is one of the important research topics now. [0003] The technical solution commonly used in the prior art relates to naming entity identification and relationship extraction, where named entity recognition, NER is the key technique in the knowledge map construction process, mainly completing the identification of entity from unstructured data. And classified by the predetermined naming entity type, the purpose of the relational extraction is to determine the potential semantic...

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): G06F40/30G06F40/295G06F40/242G06F16/33G06K9/62G06N3/04
CPCG06F40/30G06F40/242G06F40/295G06F16/334G06N3/044G06F18/214
Inventor 方酉后弘毅郭嘉欣
Owner THE 28TH RES INST OF CHINA ELECTRONICS TECH GROUP CORP