schliessen

Filtern

 

Bibliotheken

Rethinking Skip-thought: A Neighborhood based Approach

We study the skip-thought model with neighborhood information as weak supervision. More specifically, we propose a skip-thought neighbor model to consider the adjacent sentences as a neighborhood. We train our skip-thought neighbor model on a large corpus with continuous sentences, and then evaluate... Full description

Journal Title: arXiv.org Jun 9, 2017
Main Author: Tang, Shuai
Other Authors: Jin, Hailin , Chen, Fang , Wang, Zhaowen , de Sa, Virginia
Format: Electronic Article Electronic Article
Language: English
Subjects:
Quelle: © ProQuest LLC All rights reserved
Zum Text:
SendSend as email Add to Book BagAdd to Book Bag
Staff View
recordid: proquest2075664124
title: Rethinking Skip-thought: A Neighborhood based Approach
format: Article
creator:
  • Tang, Shuai
  • Jin, Hailin
  • Chen, Fang
  • Wang, Zhaowen
  • de Sa, Virginia
subjects:
  • Neighborhoods
  • Sentences
  • Computation and Language
  • Artificial Intelligence
  • Neural and Evolutionary Computation
ispartof: arXiv.org, Jun 9, 2017
description: We study the skip-thought model with neighborhood information as weak supervision. More specifically, we propose a skip-thought neighbor model to consider the adjacent sentences as a neighborhood. We train our skip-thought neighbor model on a large corpus with continuous sentences, and then evaluate the trained model on 7 tasks, which include semantic relatedness, paraphrase detection, and classification benchmarks. Both quantitative comparison and qualitative investigation are conducted. We empirically show that, our skip-thought neighbor model performs as well as the skip-thought model on evaluation tasks. In addition, we found that, incorporating an autoencoder path in our model didn't aid our model to perform better, while it hurts the performance of the skip-thought model.
language: eng
source: © ProQuest LLC All rights reserved
identifier:
fulltext: fulltext_linktorsrc
url: Link


@attributes
ID1396637702
RANK0.07
NO1
SEARCH_ENGINEprimo_central_multiple_fe
SEARCH_ENGINE_TYPEPrimo Central Search Engine
LOCALfalse
PrimoNMBib
record
control
sourcerecordid2075664124
sourceidproquest
recordidTN_proquest2075664124
sourcesystemPC
pqid2075664124
display
typearticle
titleRethinking Skip-thought: A Neighborhood based Approach
creatorTang, Shuai ; Jin, Hailin ; Chen, Fang ; Wang, Zhaowen ; de Sa, Virginia
contributorde Sa, Virginia (pacrepositoryorg)
ispartofarXiv.org, Jun 9, 2017
subjectNeighborhoods ; Sentences ; Computation and Language ; Artificial Intelligence ; Neural and Evolutionary Computation
descriptionWe study the skip-thought model with neighborhood information as weak supervision. More specifically, we propose a skip-thought neighbor model to consider the adjacent sentences as a neighborhood. We train our skip-thought neighbor model on a large corpus with continuous sentences, and then evaluate the trained model on 7 tasks, which include semantic relatedness, paraphrase detection, and classification benchmarks. Both quantitative comparison and qualitative investigation are conducted. We empirically show that, our skip-thought neighbor model performs as well as the skip-thought model on evaluation tasks. In addition, we found that, incorporating an autoencoder path in our model didn't aid our model to perform better, while it hurts the performance of the skip-thought model.
languageeng
source
0© ProQuest LLC All rights reserved
1Engineering Database
2Publicly Available Content Database
3ProQuest Engineering Collection
4ProQuest Technology Collection
5ProQuest SciTech Collection
6Materials Science & Engineering Database
7ProQuest Central (new)
8ProQuest Central Korea
9SciTech Premium Collection
10Technology Collection
11ProQuest Central Essentials
12ProQuest One Academic
13Engineering Collection (ProQuest)
oafree_for_read
links
openurl$$Topenurl_article
openurlfulltext$$Topenurlfull_article
linktorsrc$$Uhttp://search.proquest.com/docview/2075664124/?pq-origsite=primo$$EView_record_in_ProQuest_(subscribers_only)
search
creatorcontrib
0Tang, Shuai
1Jin, Hailin
2Chen, Fang
3Wang, Zhaowen
4de Sa, Virginia
titleRethinking Skip-thought: A Neighborhood based Approach
descriptionWe study the skip-thought model with neighborhood information as weak supervision. More specifically, we propose a skip-thought neighbor model to consider the adjacent sentences as a neighborhood. We train our skip-thought neighbor model on a large corpus with continuous sentences, and then evaluate the trained model on 7 tasks, which include semantic relatedness, paraphrase detection, and classification benchmarks. Both quantitative comparison and qualitative investigation are conducted. We empirically show that, our skip-thought neighbor model performs as well as the skip-thought model on evaluation tasks. In addition, we found that, incorporating an autoencoder path in our model didn't aid our model to perform better, while it hurts the performance of the skip-thought model.
subject
0Neighborhoods
1Sentences
2Computation and Language
3Artificial Intelligence
4Neural and Evolutionary Computation
general
0English
1Cornell University Library, arXiv.org
2Engineering Database
3Publicly Available Content Database
4ProQuest Engineering Collection
5ProQuest Technology Collection
6ProQuest SciTech Collection
7Materials Science & Engineering Database
8ProQuest Central (new)
9ProQuest Central Korea
10SciTech Premium Collection
11Technology Collection
12ProQuest Central Essentials
13ProQuest One Academic
14Engineering Collection (ProQuest)
sourceidproquest
recordidproquest2075664124
rsrctypearticle
creationdate2017
addtitlearXiv.org
searchscope
01007853
11008875
21008886
31009127
41009240
510000041
610000053
710000120
810000250
910000255
1010000256
1110000258
1210000260
1310000265
1410000268
1510000281
1610000348
1710000356
1810000360
19proquest
scope
01007853
11008875
21008886
31009127
41009240
510000041
610000053
710000120
810000250
910000255
1010000256
1110000258
1210000260
1310000265
1410000268
1510000281
1610000348
1710000356
1810000360
19proquest
lsr43
01007853true
11008875true
21008886true
31009127true
41009240true
510000041true
610000053true
710000120true
810000250true
910000255true
1010000256true
1110000258true
1210000260true
1310000265true
1410000268true
1510000281true
1610000348true
1710000356true
1810000360true
startdate20170609
enddate20170609
sort
titleRethinking Skip-thought: A Neighborhood based Approach
authorTang, Shuai ; Jin, Hailin ; Chen, Fang ; Wang, Zhaowen ; de Sa, Virginia
creationdate20170609
lso0120170609
facets
frbrgroupid7124523259034343920
frbrtype6
newrecords20180917
languageeng
creationdate2017
topic
0Neighborhoods
1Sentences
2Computation and Language
3Artificial Intelligence
4Neural and Evolutionary Computation
collection
0Engineering Database
1Publicly Available Content Database
2ProQuest Engineering Collection
3ProQuest Technology Collection
4ProQuest SciTech Collection
5Materials Science & Engineering Database
6ProQuest Central (new)
7ProQuest Central Korea
8SciTech Premium Collection
9Technology Collection
10ProQuest Central Essentials
11ProQuest One Academic
12Engineering Collection (ProQuest)
prefilterarticles
rsrctypearticles
creatorcontrib
0Tang, Shuai
1Jin, Hailin
2Chen, Fang
3Wang, Zhaowen
4de Sa, Virginia
jtitlearXiv.org
delivery
delcategoryRemote Search Resource
fulltextfulltext_linktorsrc
addata
aulast
0Tang
1Jin
2Chen
3Wang
4de Sa
aufirst
0Shuai
1Hailin
2Fang
3Zhaowen
4Virginia
au
0Tang, Shuai
1Jin, Hailin
2Chen, Fang
3Wang, Zhaowen
4de Sa, Virginia
atitleRethinking Skip-thought: A Neighborhood based Approach
jtitlearXiv.org
risdate20170609
formatjournal
genrearticle
ristypeJOUR
abstractWe study the skip-thought model with neighborhood information as weak supervision. More specifically, we propose a skip-thought neighbor model to consider the adjacent sentences as a neighborhood. We train our skip-thought neighbor model on a large corpus with continuous sentences, and then evaluate the trained model on 7 tasks, which include semantic relatedness, paraphrase detection, and classification benchmarks. Both quantitative comparison and qualitative investigation are conducted. We empirically show that, our skip-thought neighbor model performs as well as the skip-thought model on evaluation tasks. In addition, we found that, incorporating an autoencoder path in our model didn't aid our model to perform better, while it hurts the performance of the skip-thought model.
copIthaca
pubCornell University Library, arXiv.org
urlhttp://search.proquest.com/docview/2075664124/
oafree_for_read
date2017-06-09