暂无图片
暂无图片
暂无图片
暂无图片
暂无图片
基于张量分解的知识超图链接预测模型 - 王培妍, 段磊, 郭正山, 蒋为鹏, 张译丹.pdf
363
13页
0次
2021-11-10
免费下载
DOI
:
issn
JournalofCom
p
uterResearchandDevelo
p
ment
(
):
,
 
稿
:
;
:
 
:
(
);
(
YFB
);
(
YFG
)
Thisworkwassu
pp
ortedb
y
the NationalNaturalScienceFoundationofChina
(
),
the NationalKe
y
Researchand
Develo
p
mentPro
g
ramofChina
(
YFB
),
andtheSichuanScienceandTechnolo
gy
Pro
g
ram
(
YFG
)
 
:
(
leiduanscueducn
)
 
 
 
 
 
(
 
 
)
(
won
gpy
stuscueducn
)
Knowled
g
eH
yp
er
g
ra
p
hLinkPrediction ModelBasedonTensorDecom
p
osition
Wan
g
Pei
y
an
,
DuanLei
,
GuoZhen
g
shan
,
Jian
g
Wei
p
en
g
,
andZhan
g
Yidan
(
Schoolo
f
Com
p
uterScience
,
SichuanUniversit
y
,
Chen
g
du
)
Abstract  Knowled
g
e h
yp
er
g
ra
p
hs contain facts in the real world and
p
rovide a structured
re
p
resentationofthesefacts
,
butthe
y
cannotincludeallfactsThe
y
arehi
g
hl
y
incom
p
leteLink
p
redictiona
pp
roachesaimatinferrin
g
missin
g
linksbasedonexistin
g
linksbetweenentities
,
sothe
y
arewidel
y
usedinknowled
g
ebasecom
p
letionAt
p
resent
,
mostresearchesfocusonthecom
p
letionof
thebinar
y
relationalknowled
g
e
g
ra
p
hsHowever
,
therelationsbetweenentitiesintherealworld
usuall
yg
obe
y
ond
p
airwiseassociations
,
thatis
,
thereare morethantwoentitiesinvolvedina
relationCom
p
aredwithknowled
g
e
g
ra
p
hs
,
knowled
g
eh
yp
er
g
ra
p
hscanre
p
resentthesecom
p
lex
n
ar
y
relationsinaflexibleand naturalwa
y
Therefore
,
we
p
ro
p
oseaknowled
g
eh
yp
er
g
ra
p
hlink
p
redictionmodelbasedontensordecom
p
osition
,
calledT
yp
erItex
p
licitl
y
modelstherolesofentities
indifferentrelationsand
p
ositions
,
and decom
p
osestherelationstoim
p
rovethe
p
erformance
Meanwhile
,
considerin
g
that
p
romotin
g
theinformationflowbetweenentitiesandrelationsishel
p
ful
forlearnin
g
embeddin
g
sofentitiesandrelations
,
we
p
ro
p
osetheconce
p
tofwindowstoincreasethe
interactionbetweenentitiesandrelationsInaddition
,
we
p
roveT
yp
erisfull
y
ex
p
ressiveandderivea
boundonthedimensionalit
y
ofitsembeddin
g
sforfullex
p
ressivit
y
Weconductextensiveex
p
eriments
on multi
p
le
p
ublicrealworld knowled
g
e h
yp
er
g
ra
p
h datasetsEx
p
erimentsshow that T
yp
eris
effectiveforlink
p
redictioninknowled
g
eh
yp
er
g
ra
p
hsandachievesbetterresultsonallbenchmark
datasetsthanothera
pp
roaches
Ke
y
words knowled
g
eh
yp
er
g
ra
p
h
;
link
p
rediction
;
knowled
g
ebasecom
p
letion
;
n
ar
y
relation
;
tensordecom
p
osition
;
embeddin
g
learnin
g
 
 
,
,
,
广
,
,
,
,
T
yp
er
,
,
,
,
,
,
T
yp
er
,
使
,
T
yp
er
,
 
;
;
;
;
;
 TP
  
,
,
广
,
,
Freebase
[
]
,
,
,
,
[
]
,
,
,
,
,
[
]
[
]
[
]
[
]
(
),
,
[
]
[
]
,
,
,
,
,
Freebase
,
[
]
,
[
]
,
,
Wen
[
]
,
SC
(
startocli
q
ue
)
,
,
广
,
mTransH
[
]
TransH
[
]
广
,
mCP
[
]
CP
[
]
广
,
mDistMult
[
]
DistMult
[
]
广
,
mDistMult
,
DistMult
,
,
mDistMult
使
,
,
mDistMult
,
,
(
trans
lation
)
(
tensordecom
p
osition
)
(
g
ra
p
hneuralnetwork
,
GNN
)
(
ke
y
value
p
air
)
,
,
(
:
)
(
:
)
[
]
,
,
,
[
]
,
,
Fi
g
 Ato
y
exam
p
leofknowled
g
eh
yp
er
g
ra
p
h
 
,
,
:
)
:
,
;
,
 
,
(
)
of 13
免费下载
【版权声明】本文为墨天轮用户原创内容,转载时必须标注文档的来源(墨天轮),文档链接,文档作者等基本信息,否则作者和墨天轮有权追究责任。如果您发现墨天轮中有涉嫌抄袭或者侵权的内容,欢迎发送邮件至:contact@modb.pro进行举报,并提供相关证据,一经查实,墨天轮将立刻删除相关内容。

评论

关注
最新上传
暂无内容,敬请期待...
下载排行榜
Top250 周榜 月榜