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

Relation extraction method based on explicit and implicit entity constraints

An implicit entity and relationship extraction technology, applied in character and pattern recognition, instrument, semantic tool creation, etc., can solve the problem of insufficient training and sparse data, alleviate the problem of gradient disappearance, improve the expansion ability, and improve the generalization ability. Effect

Active Publication Date: 2021-03-09
EAST CHINA NORMAL UNIV +1
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The method is simple, effectively solves the class imbalance problem of noise, insufficient training and data sparseness, and has certain practical value in alleviating the impact of noise and NA on classification

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
  • Relation extraction method based on explicit and implicit entity constraints
  • Relation extraction method based on explicit and implicit entity constraints
  • Relation extraction method based on explicit and implicit entity constraints

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] See attached figure 1 , the present invention is based on the framework of the relationship extraction method of explicit and implicit entity constraints, and adopts the method of entity type attention mechanism to extract explicit entity constraint information. For each sentence in a package, entity constraint information that integrates sentence semantics can be extracted, and finally Through the sentence-level attention mechanism, the entity constraint information at the package level is obtained. The specific steps of relationship extraction are as follows:

[0035] Step 1: Data Preprocessing

[0036] Select a large-scale dataset marked by the heuristic of remote supervision, and combine the sentences aligned according to the same entity into a package, then segment each sentence in the package, and use the GloVe model to pre-train the word vector, each sentence will correspond to a matrix composed of word vectors, the specific operation is as follows:

[0037] 1-...

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 relation extraction method based on explicit and implicit entity constraints, which is characterized in that a method for extracting explicit entity constraint information byadopting an entity type attention mechanism is adopted, entity constraint information fused with sentence semantics can be extracted from each sentence in a packet, and finally, through a sentence-level attention mechanism, entity constraint information of a packet level is obtained. The method specifically comprises the steps of data preprocessing, packet representation learning, explicit and implicit entity constraint representation, model iterative training and the like. Compared with the prior art, the method has the advantages that the method is simple and convenient, the problem of class imbalance of noise, insufficient training and sparse data is effectively solved, the influence of noise and NA on classification is relieved, the effect of relationship extraction is improved, and certain practical value is achieved.

Description

technical field [0001] The invention relates to the technical field of natural language processing and information extraction of knowledge graphs, in particular to a relation extraction method based on explicit and implicit entity constraints. Background technique [0002] Information extraction, as a natural language processing technology under artificial intelligence, has become a necessary process for knowledge graph construction due to its advantages of efficiently extracting structured knowledge from unstructured data. At the same time, based on the results of information extraction, it can be applied to upstream tasks including text summarization and machine translation to realize the driving force of knowledge. With the rapid development and popularization of the Internet, the mass data on the Web side is increasing rapidly, and a large amount of knowledge is stored in the cloud, such as major encyclopedia websites, blogs, and news networks, etc. Most of these informa...

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
IPC IPC(8): G06F16/36G06F16/35G06F40/295G06K9/62G06N3/04
CPCG06F16/367G06F16/35G06F40/295G06N3/045G06F18/214
Inventor 高明王嘉宁蔡文渊徐林昊周傲英
Owner EAST CHINA NORMAL UNIV