Providing Definitive Learning Direction for Relation Classification System

Deep neural network has adequately revealed its superiority of solving various tasks in Natural Language Processing, especially for relation classification. However, unlike traditional feature-engineering methods that targetedly extract well-designed features for specific task, the diversity of inpu...

Full description

Saved in:
Bibliographic Details
Main Authors: Pengda Qin, Weiran Xu, Jun Guo
Format: Article
Language:English
Published: Wiley 2017-01-01
Series:Journal of Control Science and Engineering
Online Access:http://dx.doi.org/10.1155/2017/3924641
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849414088128462848
author Pengda Qin
Weiran Xu
Jun Guo
author_facet Pengda Qin
Weiran Xu
Jun Guo
author_sort Pengda Qin
collection DOAJ
description Deep neural network has adequately revealed its superiority of solving various tasks in Natural Language Processing, especially for relation classification. However, unlike traditional feature-engineering methods that targetedly extract well-designed features for specific task, the diversity of input format for deep learning is limited; word sequence as input is the frequently used setting. Therefore, the input of neural network, to some extent, lacks pertinence. For relation classification task, it is not uncommon that, without specific entity pair, a sentence contains various relation types; therefore, entity pair indicates the distribution of the crucial information in input sentence for recognizing specific relation. Aiming at this characteristic, in this paper, several strategies are proposed to integrate entity pair information into the application of deep learning in relation classification task, in a way to provide definitive learning direction for neural network. Experimental results on the SemEval-2010 Task 8 dataset show that our method outperforms most of the state-of-the-art models, without external linguistic features.
format Article
id doaj-art-70e93bfb1033484c8d1b46e527325f50
institution Kabale University
issn 1687-5249
1687-5257
language English
publishDate 2017-01-01
publisher Wiley
record_format Article
series Journal of Control Science and Engineering
spelling doaj-art-70e93bfb1033484c8d1b46e527325f502025-08-20T03:33:57ZengWileyJournal of Control Science and Engineering1687-52491687-52572017-01-01201710.1155/2017/39246413924641Providing Definitive Learning Direction for Relation Classification SystemPengda Qin0Weiran Xu1Jun Guo2School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaDeep neural network has adequately revealed its superiority of solving various tasks in Natural Language Processing, especially for relation classification. However, unlike traditional feature-engineering methods that targetedly extract well-designed features for specific task, the diversity of input format for deep learning is limited; word sequence as input is the frequently used setting. Therefore, the input of neural network, to some extent, lacks pertinence. For relation classification task, it is not uncommon that, without specific entity pair, a sentence contains various relation types; therefore, entity pair indicates the distribution of the crucial information in input sentence for recognizing specific relation. Aiming at this characteristic, in this paper, several strategies are proposed to integrate entity pair information into the application of deep learning in relation classification task, in a way to provide definitive learning direction for neural network. Experimental results on the SemEval-2010 Task 8 dataset show that our method outperforms most of the state-of-the-art models, without external linguistic features.http://dx.doi.org/10.1155/2017/3924641
spellingShingle Pengda Qin
Weiran Xu
Jun Guo
Providing Definitive Learning Direction for Relation Classification System
Journal of Control Science and Engineering
title Providing Definitive Learning Direction for Relation Classification System
title_full Providing Definitive Learning Direction for Relation Classification System
title_fullStr Providing Definitive Learning Direction for Relation Classification System
title_full_unstemmed Providing Definitive Learning Direction for Relation Classification System
title_short Providing Definitive Learning Direction for Relation Classification System
title_sort providing definitive learning direction for relation classification system
url http://dx.doi.org/10.1155/2017/3924641
work_keys_str_mv AT pengdaqin providingdefinitivelearningdirectionforrelationclassificationsystem
AT weiranxu providingdefinitivelearningdirectionforrelationclassificationsystem
AT junguo providingdefinitivelearningdirectionforrelationclassificationsystem