A Distant Supervised Relation Extraction Method with Entity Awareness Based on PCNN Model

A technology of relationship extraction and remote supervision, applied in neural learning methods, biological neural network models, instruments, etc., can solve the problems of ignoring semantic information and not further exploring the different contributions of the three segments in PCNN, so as to improve the ability of prediction Effect

Active Publication Date: 2021-10-01
海乂知信息科技(南京)有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are still some deficiencies in the above methods that need to be improved
For example, existing methods do not consider the impact of entity pairs and sentence context on word encoding, which may ignore some important semantic information; moreover, the different contributions of the three segments in PCNN to relation classification are not further explored

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 Distant Supervised Relation Extraction Method with Entity Awareness Based on PCNN Model
  • A Distant Supervised Relation Extraction Method with Entity Awareness Based on PCNN Model
  • A Distant Supervised Relation Extraction Method with Entity Awareness Based on PCNN Model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0073] The remote supervised relation extraction task can be briefly described as: given a bag B={s 1 ,s 2 ,...,s m}, each sentence in the bag contains the same entity pair (head entity e f and tail entity e t ), the purpose of relation extraction is to predict the relation y between two entities. According to this definition, the extraction of remote supervision relations in the present invention adopts a novel gated segmental convolutional neural network EA-GPCNN with entity-aware enhancement function, such as figure 1 shown.

[0074] Specifically, it can be summarized as follows:

[0075] S1. For a sentence in a given sentence bag, the input layer uses Google's pre-trained word2vec word vector to map each word in the sentence to a low-dimensional word embedding vector to obtain an input sequence;

[0076] S2. The entity-aware enhanced word representation layer uses a multi-head self-attention mechanism to fuse word embeddings with head and tail entity embeddings and r...

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 present invention provides a PCNN model-based remote supervision relationship extraction method with entity perception, specifically comprising: first, the present invention uses a multi-head self-attention mechanism to combine word embedding with head entity and tail entity embedding and relative position embedding, In order to generate an enhanced word semantic representation of perceptible entities, it is able to capture the semantic dependencies between each word and entity pair; then, the present invention introduces a global gate to combine the enhanced word representation perceived by each entity in the input sentence with Their average values ​​are combined to form the final word representation for the PCNN input; moreover, to determine the key sentence segments where the most important relationship classification information appears. The method of the present invention introduces another gate mechanism to assign different weights to each sentence segment to highlight the effect of key sentence segments in PCNN. Experiments show that the remote supervision relationship extraction method of the present invention can improve the prediction ability of the remote supervision relationship in sentences.

Description

technical field [0001] The invention relates to relation extraction in natural language processing and information processing, in particular to a PCNN model-based remote supervision relation extraction method with entity perception, which can be widely used in the automatic generation of knowledge graphs in various fields. Background technique [0002] Relation extraction is one of the key technologies of information extraction. It aims to identify the semantic relationship between entity pairs in a given sentence. The extracted semantic relationship can be applied to downstream tasks such as knowledge base automatic completion and question answering system. [0003] Traditional supervised relation extraction methods require a large amount of precisely labeled training data, however, it takes a lot of time and effort to obtain these data. In order to overcome the above problems, Mintz et al. proposed a remote supervision method, which aligned the large-scale knowledge graph ...

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): G06F40/211G06F40/295G06F40/30G06N3/04G06N3/08
CPCG06F40/211G06F40/295G06F40/30G06N3/08G06N3/048G06N3/045
Inventor 朱新华温海旭张兰芳
Owner 海乂知信息科技(南京)有限公司
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