A Multi-Channel Deep Neural Network for Relation Extraction

The task of relation recognition identifies semantic relationships between two named entities in a sentence. In neural network based models, a convolutional layer is often conducted to extract representative local features of a sentence. The convolution operation is implemented through a whole sente...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2020, Vol.8, p.13195-13203
Main Authors: Chen, Yanping, Wang, Kai, Yang, Weizhe, Qing, Yongbin, Huang, Ruizhang, Chen, Ping
Format: Article
Language:English
Subjects:
Artificial neural networks
Channels
Convolution
Feature extraction
Hidden Markov models
Information extraction
Natural language processing
neural network
Neural networks
relation recognition
Semantics
Task analysis
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The task of relation recognition identifies semantic relationships between two named entities in a sentence. In neural network based models, a convolutional layer is often conducted to extract representative local features of a sentence. The convolution operation is implemented through a whole sentence, without considering the structure of a sentence. Because the task to recognize entity relation is processed in sentence level, many ambiguous phenomena (e.g., polysemy) are influential rather than in a document. Capturing structural information of a sentence is helpful to solve this problem. In this paper, a multi-channel framework is presented, which uses two named entities to divide a sentence into several channels. Each channel is stacked with layered neural networks. These channels do not interact during recurrent propagation, which enables a neural network to learn different representations. In our experiments, it outperforms the widely used position embedding approach. Comparing with the state-of-the-art approaches, its performance shows a meaningful improvement.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2020.2966303