• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

Shi, Yong (Shi, Yong.) | Xiao, Yang (Xiao, Yang.) | Quan, Pei (Quan, Pei.) | Lei, MingLong (Lei, MingLong.) | Niu, Lingfeng (Niu, Lingfeng.)

Indexed by:

EI Scopus SCIE PubMed

Abstract:

Relation Extraction systems train an extractor by aligning relation instances in Knowledge Base with a large amount of labeled corpora. Since the labeled datasets are very expensive, Distant Supervision Relation Extraction (DSRE) utilizes rough corpus annotated with Knowledge Graph to reduce the cost of acquisition. Nevertheless, the data noise problem limits the performance of the DSRE. Dependency trees can be used to filter the wrong-labeled instances in the distant supervision bag. However, existing dependency tree relation extraction strategies are all based on manually-set paths between the subject and object entities, and suffer from the problem of pruning the trees too aggressively or too insufficiently. To circumvent the shortcomings, in this paper, we propose a novel DSRE framework A2DSRE, based on the Adaptive dependency-path and Additional KG supervision. To obtain the dependency paths related to entity relations adaptively, we introduce an advanced graph neural network-GeniePath into DSRE, which assigns higher weights to those direct neighbor words that contribute more to relation prediction through breadth exploration, and conducts depth exploration to determine the correlation between relations and high-order neighbors. In this way, the irrelevant nodes are pruned while the relevant nodes are kept, our method can obtain more appropriate paths associated with relations. At the same time, to further reduce the noises in the data, we incorporate additional supervision information from the knowledge graph by retracting the margin between the representation of the bag and the pre-training knowledge graph embedding. Extensive numerical experiments validate the effectiveness of our new method. (C) 2020 Elsevier Ltd. All rights reserved.

Keyword:

Additional knowledge graph supervision Dependency-path Adaptive method Distant Supervision Relation Extraction

Author Community:

  • [ 1 ] [Xiao, Yang]Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 101408, Peoples R China
  • [ 2 ] [Quan, Pei]Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 101408, Peoples R China
  • [ 3 ] [Shi, Yong]Univ Chinese Acad Sci, Sch Econ & Management, Beijing 100190, Peoples R China
  • [ 4 ] [Niu, Lingfeng]Univ Chinese Acad Sci, Sch Econ & Management, Beijing 100190, Peoples R China
  • [ 5 ] [Shi, Yong]Chinese Acad Sci, Key Lab Big Data Min & Knowledge Management, Beijing 100190, Peoples R China
  • [ 6 ] [Xiao, Yang]Chinese Acad Sci, Key Lab Big Data Min & Knowledge Management, Beijing 100190, Peoples R China
  • [ 7 ] [Quan, Pei]Chinese Acad Sci, Key Lab Big Data Min & Knowledge Management, Beijing 100190, Peoples R China
  • [ 8 ] [Niu, Lingfeng]Chinese Acad Sci, Key Lab Big Data Min & Knowledge Management, Beijing 100190, Peoples R China
  • [ 9 ] [Shi, Yong]Chinese Acad Sci, Res Ctr Fictitious Econ & Data Sci, Beijing 100190, Peoples R China
  • [ 10 ] [Xiao, Yang]Chinese Acad Sci, Res Ctr Fictitious Econ & Data Sci, Beijing 100190, Peoples R China
  • [ 11 ] [Quan, Pei]Chinese Acad Sci, Res Ctr Fictitious Econ & Data Sci, Beijing 100190, Peoples R China
  • [ 12 ] [Niu, Lingfeng]Chinese Acad Sci, Res Ctr Fictitious Econ & Data Sci, Beijing 100190, Peoples R China
  • [ 13 ] [Shi, Yong]Univ Nebraska, Coll Informat Sci & Technol, Omaha, NE 68182 USA
  • [ 14 ] [Lei, MingLong]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China

Reprint Author's Address:

  • [Niu, Lingfeng]Chinese Acad Sci, Key Lab Big Data Min & Knowledge Management, Beijing 100190, Peoples R China

Show more details

Related Keywords:

Source :

NEURAL NETWORKS

ISSN: 0893-6080

Year: 2021

Volume: 134

Page: 42-53

7 . 8 0 0

JCR@2022

ESI Discipline: COMPUTER SCIENCE;

ESI HC Threshold:87

JCR Journal Grade:1

Cited Count:

WoS CC Cited Count: 29

SCOPUS Cited Count: 37

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 1

Affiliated Colleges:

Online/Total:677/5428524
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.