A neural generative autoencoder for bilingual word embeddings

Bilingual word embeddings (BWEs) have been shown to be useful in various cross-lingual natural language processing tasks. To accurately learn BWEs, previous studies often resort to discriminative approaches which explore semantic proximities between translation equivalents of different languages. In...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Information sciences Ročník 424; s. 287 - 300
Hlavní autoři: Su, Jinsong, Wu, Shan, Zhang, Biao, Wu, Changxing, Qin, Yue, Xiong, Deyi
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Inc 01.01.2018
Témata:
ISSN:0020-0255, 1872-6291
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Bilingual word embeddings (BWEs) have been shown to be useful in various cross-lingual natural language processing tasks. To accurately learn BWEs, previous studies often resort to discriminative approaches which explore semantic proximities between translation equivalents of different languages. Instead, in this paper, we propose a neural generative bilingual autoencoder (NGBAE) which introduces a latent variable to explicitly induce the underlying semantics of bilingual text. In this way, NGBAE is able to obtain better BWEs from more robust bilingual semantics by modeling the semantic distributions of bilingual text. In order to facilitate scalable inference and learning, we utilize deep neural networks to perform the recognition and generation procedures, and then employ stochastic gradient variational Bayes algorithm to optimize them jointly. We validate the proposed model via both extrinsic (cross-lingual document classification and translation probability modeling) and intrinsic (word embedding analysis) evaluations. Experimental results demonstrate the effectiveness of NGBAE on learning BWEs.
AbstractList Bilingual word embeddings (BWEs) have been shown to be useful in various cross-lingual natural language processing tasks. To accurately learn BWEs, previous studies often resort to discriminative approaches which explore semantic proximities between translation equivalents of different languages. Instead, in this paper, we propose a neural generative bilingual autoencoder (NGBAE) which introduces a latent variable to explicitly induce the underlying semantics of bilingual text. In this way, NGBAE is able to obtain better BWEs from more robust bilingual semantics by modeling the semantic distributions of bilingual text. In order to facilitate scalable inference and learning, we utilize deep neural networks to perform the recognition and generation procedures, and then employ stochastic gradient variational Bayes algorithm to optimize them jointly. We validate the proposed model via both extrinsic (cross-lingual document classification and translation probability modeling) and intrinsic (word embedding analysis) evaluations. Experimental results demonstrate the effectiveness of NGBAE on learning BWEs.
Author Zhang, Biao
Wu, Changxing
Xiong, Deyi
Qin, Yue
Wu, Shan
Su, Jinsong
Author_xml – sequence: 1
  givenname: Jinsong
  surname: Su
  fullname: Su, Jinsong
  email: jssu@xmu.edu.cn
  organization: Xiamen University, Xiamen 361005, China
– sequence: 2
  givenname: Shan
  surname: Wu
  fullname: Wu, Shan
  email: wushan@stu.xmu.edu.cn
  organization: Xiamen University, Xiamen 361005, China
– sequence: 3
  givenname: Biao
  surname: Zhang
  fullname: Zhang, Biao
  email: zb@stu.xmu.edu.cn
  organization: Xiamen University, Xiamen 361005, China
– sequence: 4
  givenname: Changxing
  surname: Wu
  fullname: Wu, Changxing
  email: wuchangxing@ecjtu.edu.cn
  organization: Virtual Reality and Interactive Techniques Institute, East China Jiaotong University, Nanchang 330013, China
– sequence: 5
  givenname: Yue
  orcidid: 0000-0002-7857-2936
  surname: Qin
  fullname: Qin, Yue
  email: qinyue@stu.xmu.edu.cn
  organization: Xiamen University, Xiamen 361005, China
– sequence: 6
  givenname: Deyi
  orcidid: 0000-0002-2353-5038
  surname: Xiong
  fullname: Xiong, Deyi
  email: dyxiong@suda.edu.cn
  organization: Soochow University, Suzhou 215006, China
BookMark eNp9kE1LAzEQhoNUsFZ_gLf9A7tO0t1Ng3goxS8oeNFzmE1mS8o2kWRb8d-bUk8eenphmOdl5rlmEx88MXbHoeLA2_tt5XyqBHBZgapAwgWb8oUUZSsUn7ApgIASRNNcseuUtgBQy7adssdl4WkfcSg25Cni6A5U4H4M5E2wFIs-xKJzg_ObfV76DtEWtOvI2jxJN-yyxyHR7V_O2Ofz08fqtVy_v7ytluvSCCXHsoeGOokdItoWpVI1kFRiTl2jSHT1Ag2SzZ2ql6K1OS1QXq5JNTU2aj5j8tRrYkgpUq-NG_OtwY8R3aA56KMFvdXZgj5a0KB0tpBJ_o_8im6H8ecs83BiKL90cBR1Mi77IOsimVHb4M7Qvx-webU
CitedBy_id crossref_primary_10_1016_j_ins_2021_03_064
crossref_primary_10_1016_j_patrec_2019_11_033
crossref_primary_10_1016_j_ins_2020_01_035
crossref_primary_10_1016_j_ipm_2018_04_007
crossref_primary_10_1016_j_jocn_2020_01_050
crossref_primary_10_1016_j_knosys_2018_10_025
crossref_primary_10_1016_j_ins_2018_09_057
crossref_primary_10_1007_s10489_023_05157_4
crossref_primary_10_1145_3610289
crossref_primary_10_1016_j_ins_2022_06_081
crossref_primary_10_1016_j_eswa_2020_114020
crossref_primary_10_1016_j_eswa_2020_114070
crossref_primary_10_1080_08839514_2021_2019885
crossref_primary_10_1145_3464427
crossref_primary_10_1007_s11227_019_03024_z
crossref_primary_10_1007_s40998_023_00626_5
crossref_primary_10_1007_s10489_022_03563_8
crossref_primary_10_1109_TASLP_2021_3097935
Cites_doi 10.1016/j.ins.2017.04.024
10.1162/089120103321337421
10.7551/mitpress/7503.003.0024
10.1109/TIP.2015.2487860
10.1007/s11063-017-9605-7
10.1016/j.ins.2017.06.026
ContentType Journal Article
Copyright 2017 Elsevier Inc.
Copyright_xml – notice: 2017 Elsevier Inc.
DBID AAYXX
CITATION
DOI 10.1016/j.ins.2017.09.070
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Library & Information Science
EISSN 1872-6291
EndPage 300
ExternalDocumentID 10_1016_j_ins_2017_09_070
S0020025517309891
GroupedDBID --K
--M
--Z
-~X
.DC
.~1
0R~
1B1
1OL
1RT
1~.
1~5
29I
4.4
457
4G.
5GY
5VS
7-5
71M
8P~
9JN
9JO
AAAKF
AAAKG
AABNK
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AARIN
AAXUO
AAYFN
ABAOU
ABBOA
ABEFU
ABFNM
ABJNI
ABMAC
ABTAH
ABUCO
ABXDB
ABYKQ
ACAZW
ACDAQ
ACGFS
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADGUI
ADJOM
ADMUD
ADTZH
AEBSH
AECPX
AEKER
AENEX
AFFNX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIGVJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
APLSM
ARUGR
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
HAMUX
HLZ
HVGLF
HZ~
H~9
IHE
J1W
JJJVA
KOM
LG9
LY1
M41
MHUIS
MO0
MS~
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
ROL
RPZ
SBC
SDF
SDG
SDP
SDS
SES
SEW
SPC
SPCBC
SSB
SSD
SST
SSV
SSW
SSZ
T5K
TN5
TWZ
UHS
WH7
WUQ
XPP
YYP
ZMT
ZY4
~02
~G-
77I
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
ADVLN
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
ID FETCH-LOGICAL-c297t-f05eb7abaaad6a79940e7923eb59e2b48acaededd9f726ddd9d0eaaa4e954a593
ISICitedReferencesCount 23
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000414889900017&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0020-0255
IngestDate Sat Nov 29 06:59:46 EST 2025
Tue Nov 18 22:30:15 EST 2025
Fri Feb 23 02:45:38 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Translation probability modeling
Bilingual word embeddings
Cross-lingual document classification
Neural generative autoencoder
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c297t-f05eb7abaaad6a79940e7923eb59e2b48acaededd9f726ddd9d0eaaa4e954a593
ORCID 0000-0002-2353-5038
0000-0002-7857-2936
PageCount 14
ParticipantIDs crossref_citationtrail_10_1016_j_ins_2017_09_070
crossref_primary_10_1016_j_ins_2017_09_070
elsevier_sciencedirect_doi_10_1016_j_ins_2017_09_070
PublicationCentury 2000
PublicationDate January 2018
2018-01-00
PublicationDateYYYYMMDD 2018-01-01
PublicationDate_xml – month: 01
  year: 2018
  text: January 2018
PublicationDecade 2010
PublicationTitle Information sciences
PublicationYear 2018
Publisher Elsevier Inc
Publisher_xml – name: Elsevier Inc
References Bengio, Ducharme, Vincent, Janvin (bib0001) 2003; 3
Klementiev, Titov, Bhattarai (bib0025) 2012
Liu, Liu, Chua, Sun (bib0030) 2015
Och, Ney (bib0037) 2003
Kim, Park, Oh, Yu (bib0022) 2017; 417
Liu, Qiu, Huang (bib0029) 2015
Vulić, Moens (bib0048) 2015
Garcia, Rodriguez, Rifon (bib0011) 2017; 406
Bhatia, Guthrie, Eisenstein (bib0003) 2016
Zou, Rocher, Cer, Manning (bib0054) 2013
Theano Development Team, Theano: a Python framework for fast computation of mathematical expressions, arXiv e-prints abs/1605.02688 (2016).
Hong, Yu, Tao, Wang (bib0018) 2015; 62
Shi, Liu, Liu, Sun (bib0041) 2015
Tian, Wong, Chao, Quaresma, Oliveira, Yi (bib0046) 2014
Guo, Che, Yarowsky, Wang, Liu (bib0015) 2016
Upadhyay, Faruqui, Dyer, Roth (bib0047) 2016
Chung, Kastner, Dinh, Goel, Courville, Bengio (bib0005) 2015
Ling, Dyer, Black, Trancoso, Fermandez, Amir, Marujo, Luis (bib0028) 2015
Zhou, Chen, Shi, Huang (bib0053) 2015
Rezende, Mohamed, Wierstra (bib0040) 2014
Yu, Yang, Gao, Tao (bib0051) 2016
Duong, Kanayama, Ma, Bird, Cohn (bib0010) 2016
Hermann, Blunsom (bib0017) 2014
Coulmance, Marty, Wenzek, Benhalloum (bib0008) 2015
Hong, Yu, Wan, Tao, Wang (bib0019) 2015; 24
Yu, Zhang, Kuang, Lin, Fan (bib0052) 2016
Qian, Qiu, Huang (bib0039) 2016
Stratos, Collins, Hsu (bib0044) 2015
Collins (bib0006) 2002
Gouws, Bengio, Corrado (bib0012) 2015
Yin, Schütze (bib0050) 2016
Gregor, Danihelka, Graves, Wierstra (bib0013) 2015; abs/1502.04623
Luong, Pham, Manning (bib0032) 2015
Kočiský, Hermann, Blunsom (bib0027) 2014
Duchi, Hazan, Singer (bib0009) 2010
Cotterell, Schütze, Eisner (bib0007) 2016
Ji, Yun, Yanardag, Matsushima, Vishwanathan (bib0021) 2016
Kingma, Mohamed, Rezende, Welling (bib0023) 2014
Chandar, Lauly, Larochelle, Khapra, Ravindran, Raykar, Saha (bib0004) 2014
Gu, Gu, Wu (bib0014) 2017
Y. Bengio, P. Lamblin, D. Popovici, H. Larochelle, U. Montreal, Greedy layer-wise training of deep networks, Proc. of NIPS2007, 2007.
Huang, Socher, Manning, Ng (bib0020) 2012
Lu, Wang, Bansal, Gimpel, Livescu (bib0031) 2015
T. Mikolov, Q.V. Le, I. Sutskever, Exploiting similarities among languages for machine translation, Arxiv preprint. abs/1309.4168 (2013).
Kingma, Welling (bib0024) 2014
Maaten, Hinton (bib0033) 2008; 9
Soyer, Stenetorp, Aizawa (bib0043) 2015
Hermann, Blunsom (bib0016) 2014
T. Mikolov, K. Chen, G. Corrado, J. Dean, Efficient estimation of word representations in vector space, Arxiv preprint. abs/1301.3781 (2013).
Y. Miao, L. Yu, P. Blunsom, Neural variational inference for text processing, Arxiv preprint. abs/1511.06038 (2015).
Oshikiri, Fukui, Shimodaira (bib0038) 2016
Koehn, Och, Marcu (bib0026) 2003
Socher, Pennington, Huang, Ng, Manning (bib0042) 2011
Vulić, Moens (bib0049) 2015
Zhou (10.1016/j.ins.2017.09.070_bib0053) 2015
Bengio (10.1016/j.ins.2017.09.070_bib0001) 2003; 3
Lu (10.1016/j.ins.2017.09.070_bib0031) 2015
Luong (10.1016/j.ins.2017.09.070_bib0032) 2015
10.1016/j.ins.2017.09.070_bib0002
Coulmance (10.1016/j.ins.2017.09.070_bib0008) 2015
Chandar (10.1016/j.ins.2017.09.070_bib0004) 2014
Chung (10.1016/j.ins.2017.09.070_bib0005) 2015
Cotterell (10.1016/j.ins.2017.09.070_bib0007) 2016
Koehn (10.1016/j.ins.2017.09.070_bib0026) 2003
10.1016/j.ins.2017.09.070_bib0045
Rezende (10.1016/j.ins.2017.09.070_bib0040) 2014
Garcia (10.1016/j.ins.2017.09.070_bib0011) 2017; 406
Upadhyay (10.1016/j.ins.2017.09.070_bib0047) 2016
Kingma (10.1016/j.ins.2017.09.070_bib0023) 2014
Socher (10.1016/j.ins.2017.09.070_bib0042) 2011
Kingma (10.1016/j.ins.2017.09.070_bib0024) 2014
Maaten (10.1016/j.ins.2017.09.070_bib0033) 2008; 9
Och (10.1016/j.ins.2017.09.070_bib0037) 2003
Liu (10.1016/j.ins.2017.09.070_bib0030) 2015
Huang (10.1016/j.ins.2017.09.070_bib0020) 2012
Hong (10.1016/j.ins.2017.09.070_bib0018) 2015; 62
Hermann (10.1016/j.ins.2017.09.070_bib0017) 2014
Oshikiri (10.1016/j.ins.2017.09.070_bib0038) 2016
Duong (10.1016/j.ins.2017.09.070_bib0010) 2016
Yu (10.1016/j.ins.2017.09.070_bib0051) 2016
Duchi (10.1016/j.ins.2017.09.070_bib0009) 2010
Tian (10.1016/j.ins.2017.09.070_bib0046) 2014
Gregor (10.1016/j.ins.2017.09.070_bib0013) 2015; abs/1502.04623
Zou (10.1016/j.ins.2017.09.070_bib0054) 2013
Hermann (10.1016/j.ins.2017.09.070_bib0016) 2014
Guo (10.1016/j.ins.2017.09.070_bib0015) 2016
Ji (10.1016/j.ins.2017.09.070_bib0021) 2016
Liu (10.1016/j.ins.2017.09.070_bib0029) 2015
Yu (10.1016/j.ins.2017.09.070_bib0052) 2016
Yin (10.1016/j.ins.2017.09.070_bib0050) 2016
Klementiev (10.1016/j.ins.2017.09.070_bib0025) 2012
Kočiský (10.1016/j.ins.2017.09.070_bib0027) 2014
Hong (10.1016/j.ins.2017.09.070_bib0019) 2015; 24
Vulić (10.1016/j.ins.2017.09.070_bib0049) 2015
Shi (10.1016/j.ins.2017.09.070_bib0041) 2015
Gouws (10.1016/j.ins.2017.09.070_bib0012) 2015
10.1016/j.ins.2017.09.070_bib0035
10.1016/j.ins.2017.09.070_bib0036
Qian (10.1016/j.ins.2017.09.070_bib0039) 2016
Collins (10.1016/j.ins.2017.09.070_bib0006) 2002
Gu (10.1016/j.ins.2017.09.070_bib0014) 2017
10.1016/j.ins.2017.09.070_bib0034
Vulić (10.1016/j.ins.2017.09.070_bib0048) 2015
Ling (10.1016/j.ins.2017.09.070_bib0028) 2015
Bhatia (10.1016/j.ins.2017.09.070_bib0003) 2016
Stratos (10.1016/j.ins.2017.09.070_bib0044) 2015
Kim (10.1016/j.ins.2017.09.070_bib0022) 2017; 417
Soyer (10.1016/j.ins.2017.09.070_bib0043) 2015
References_xml – start-page: 151
  year: 2011
  end-page: 161
  ident: bib0042
  article-title: Semi-supervised recursive autoencoders for predicting sentiment distributions
  publication-title: Proc. of EMNLP2011
– start-page: 363
  year: 2015
  end-page: 372
  ident: bib0049
  article-title: Monolingual and cross-lingual information retrieval models based on (bilingual) word embeddings
  publication-title: Proc. of SIGIR2015
– start-page: 1
  year: 2016
  end-page: 11
  ident: bib0051
  article-title: Deep multimodal distance metric learning using click constraints for image ranking
  publication-title: IEEE Trans. Cybern.
– start-page: 490
  year: 2016
  end-page: 500
  ident: bib0003
  article-title: Morphological priors for probabilistic neural word embeddings
  publication-title: Proc. of EMNLP2016
– start-page: 1109
  year: 2015
  end-page: 1113
  ident: bib0008
  article-title: Trans-gram, fast cross-lingual word-embeddings
  publication-title: Proc. of EMNLP2015
– reference: Theano Development Team, Theano: a Python framework for fast computation of mathematical expressions, arXiv e-prints abs/1605.02688 (2016).
– start-page: 1005
  year: 2016
  end-page: 1016
  ident: bib0052
  article-title: Iprivacy: image privacy protection by identifying sensitive objects via deep multi-task learning
  publication-title: IEEE Trans. Inf. Forensics Secur.
– start-page: 1661
  year: 2016
  end-page: 1670
  ident: bib0047
  article-title: Cross-lingual models of word embeddings: an empirical comparison
  publication-title: Proc. of ACL2016
– start-page: 719
  year: 2015
  end-page: 725
  ident: bib0048
  article-title: Bilingual word embeddings from non-parallel document-aligned data applied to bilingual lexicon induction
  publication-title: Proc. of ACL2015
– reference: T. Mikolov, K. Chen, G. Corrado, J. Dean, Efficient estimation of word representations in vector space, Arxiv preprint. abs/1301.3781 (2013).
– start-page: 250
  year: 2015
  end-page: 256
  ident: bib0031
  article-title: Deep multilingual correlation for improved word embeddings
  publication-title: Proc. of NAACL2015
– start-page: 2734
  year: 2016
  end-page: 2740
  ident: bib0015
  article-title: A representation learning framework for multi-source transfer parsing
  publication-title: Proc. of AAAI2016
– year: 2014
  ident: bib0016
  article-title: Multilingual distributed representations without word alignment
  publication-title: Proc. of ICLR2014
– start-page: 48
  year: 2003
  end-page: 54
  ident: bib0026
  article-title: Statistical phrase-based translation
  publication-title: Proceedings of NAACL 2003
– year: 2014
  ident: bib0040
  article-title: Stochastic backpropagation and approximate inference in deep generative models
  publication-title: Proc. of ICML2014
– start-page: 1459
  year: 2012
  end-page: 1474
  ident: bib0025
  article-title: Inducing crosslingual distributed representations of words
  publication-title: Proc. of COLING2012
– start-page: 224
  year: 2014
  end-page: 229
  ident: bib0027
  article-title: Learning bilingual word representations by marginalizing alignments
  publication-title: Proc. of ACL2014
– start-page: 1284
  year: 2015
  end-page: 1290
  ident: bib0029
  article-title: Learning context-sensitive word embeddings with neural tensor skip-gram mode
  publication-title: Proc. of IJCAI2015
– start-page: 493
  year: 2016
  end-page: 498
  ident: bib0038
  article-title: Cross-lingual word representations via spectral graph embeddings
  publication-title: Proc. of ACL2016
– reference: T. Mikolov, Q.V. Le, I. Sutskever, Exploiting similarities among languages for machine translation, Arxiv preprint. abs/1309.4168 (2013).
– reference: Y. Bengio, P. Lamblin, D. Popovici, H. Larochelle, U. Montreal, Greedy layer-wise training of deep networks, Proc. of NIPS2007, 2007.
– year: 2014
  ident: bib0024
  article-title: Auto-encoding variational bayes
  publication-title: Proc. of ICLR2014
– start-page: 1351
  year: 2016
  end-page: 1360
  ident: bib0050
  article-title: Learning word meta-embeddings
  publication-title: Proc. of ACL2016
– start-page: 2980
  year: 2015
  end-page: 2988
  ident: bib0005
  article-title: A recurrent latent variable model for sequential data
  publication-title: Proc. of NIPS2015
– volume: 417
  start-page: 72
  year: 2017
  end-page: 87
  ident: bib0022
  article-title: Deep hybrid recommender systems via exploiting document context and statistics of items
  publication-title: Inf. Sci.
– start-page: 873
  year: 2012
  end-page: 882
  ident: bib0020
  article-title: Improving word representations via global context and multiple word prototypes
  publication-title: Proc. of ACL2012
– start-page: 1
  year: 2002
  end-page: 8
  ident: bib0006
  article-title: Discriminative training methods for hidden markov models: theory and experiments with perceptron algorithms
  publication-title: Proceedings of EMNLP 2002
– start-page: 658
  year: 2016
  end-page: 668
  ident: bib0021
  article-title: Wordrank: learning word embeddings via robust ranking
  publication-title: Proc. of EMNLP2016
– start-page: 430
  year: 2015
  end-page: 440
  ident: bib0053
  article-title: Learning bilingual sentiment word embeddings for cross-language sentiment classification
  publication-title: Proc. of ACL2015
– start-page: 748
  year: 2015
  end-page: 756
  ident: bib0012
  article-title: Bilbowa: fast bilingual distributed representations without word alignments
  publication-title: Proc. of ICML2015
– start-page: 1285
  year: 2016
  end-page: 1295
  ident: bib0010
  article-title: Learning crosslingual word embeddings without bilingual corpora
  publication-title: Proc. of EMNLP2016
– start-page: 567
  year: 2015
  end-page: 572
  ident: bib0041
  article-title: Learning cross-lingual word embeddings via matrix co-factorization
  publication-title: Proc. of ACL2015
– start-page: 3581
  year: 2014
  end-page: 3589
  ident: bib0023
  article-title: Semi-supervised learning with deep generative models
  publication-title: Proc. of NIPS2014
– volume: 9
  start-page: 2579
  year: 2008
  end-page: 2605
  ident: bib0033
  article-title: Visualizing data using t-sne
  publication-title: J. Mach. Learn. Res.
– volume: 406
  start-page: 12
  year: 2017
  end-page: 28
  ident: bib0011
  article-title: Wikipedia-based cross-language text classification
  publication-title: Inf. Sci
– volume: 24
  start-page: 5659
  year: 2015
  end-page: 5670
  ident: bib0019
  article-title: Multimodal deep autoencoder for human pose recovery
  publication-title: IEEE Trans. Image Process.
– start-page: 1478
  year: 2016
  end-page: 1488
  ident: bib0039
  article-title: Investigating language universal and specific properties in word embeddings
  publication-title: Proc. of ACL2016
– start-page: 2418
  year: 2015
  end-page: 2424
  ident: bib0030
  article-title: Topical word embeddings
  publication-title: Proc. of AAAI2015
– volume: abs/1502.04623
  year: 2015
  ident: bib0013
  article-title: DRAW: a recurrent neural network for image generation
  publication-title: CoRR
– start-page: 151
  year: 2015
  end-page: 159
  ident: bib0032
  article-title: Bilingual word representations with monolingual quality in mind
  publication-title: Proc. of NAACL2015
– year: 2015
  ident: bib0043
  article-title: Leveraging monolingual data for crosslingual compositional word representations
  publication-title: Proc. of ICLR2015
– start-page: 1282
  year: 2015
  end-page: 1291
  ident: bib0044
  article-title: Model-based word embeddings from decompositions of count matrices
  publication-title: Proc. of ACL2015
– reference: Y. Miao, L. Yu, P. Blunsom, Neural variational inference for text processing, Arxiv preprint. abs/1511.06038 (2015).
– start-page: 1853
  year: 2014
  end-page: 1861
  ident: bib0004
  article-title: An autoencoder approach to learning bilingual word representations
  publication-title: Proc. of NIPS2014
– year: 2017
  ident: bib0014
  article-title: Cascaded convolutional neural networks for aspect-based opinion summary
  publication-title: Neural Process. Lett.
– start-page: 1837
  year: 2014
  end-page: 1842
  ident: bib0046
  article-title: Um-corpus: a large english-chinese parallel corpus for statistical machine translation
  publication-title: Proc. of LREC
– start-page: 58
  year: 2014
  end-page: 68
  ident: bib0017
  article-title: Multilingual models for compositional distributed semantics
  publication-title: Proc. of ACL2014
– start-page: 1651
  year: 2016
  end-page: 1660
  ident: bib0007
  article-title: Morphological smoothing and extrapolation of word embeddings
  publication-title: Proc. of ACL2016
– start-page: 1520
  year: 2015
  end-page: 1530
  ident: bib0028
  article-title: Finding function in form: compositional character models for open vocabulary word representation
  publication-title: Proc. of EMNLP2015
– volume: 3
  start-page: 1137
  year: 2003
  end-page: 1155
  ident: bib0001
  article-title: A neural probabilistic language model
  publication-title: J. Mach. Learn. Res.
– year: 2010
  ident: bib0009
  article-title: Adaptive subgradient methods for online learning and stochastic optimization
  publication-title: Technical report
– start-page: 1393
  year: 2013
  end-page: 1398
  ident: bib0054
  article-title: Bilingual word embeddings for phrase-based machine translation
  publication-title: Proc. of EMNLP2013
– start-page: 19
  year: 2003
  end-page: 51
  ident: bib0037
  article-title: A systematic comparison of various statistical alignment models
  publication-title: Comput. Ling.
– volume: 62
  start-page: 3742
  year: 2015
  end-page: 3751
  ident: bib0018
  article-title: Image-based three-dimensional human pose recovery by multiview locality-sensitive sparse retrieval
  publication-title: IEEE Trans. Ind. Electron.
– start-page: 430
  year: 2015
  ident: 10.1016/j.ins.2017.09.070_bib0053
  article-title: Learning bilingual sentiment word embeddings for cross-language sentiment classification
– start-page: 1478
  year: 2016
  ident: 10.1016/j.ins.2017.09.070_bib0039
  article-title: Investigating language universal and specific properties in word embeddings
– volume: 406
  start-page: 12
  year: 2017
  ident: 10.1016/j.ins.2017.09.070_bib0011
  article-title: Wikipedia-based cross-language text classification
  publication-title: Inf. Sci
  doi: 10.1016/j.ins.2017.04.024
– start-page: 1109
  year: 2015
  ident: 10.1016/j.ins.2017.09.070_bib0008
  article-title: Trans-gram, fast cross-lingual word-embeddings
– start-page: 1282
  year: 2015
  ident: 10.1016/j.ins.2017.09.070_bib0044
  article-title: Model-based word embeddings from decompositions of count matrices
– start-page: 224
  year: 2014
  ident: 10.1016/j.ins.2017.09.070_bib0027
  article-title: Learning bilingual word representations by marginalizing alignments
– volume: 9
  start-page: 2579
  year: 2008
  ident: 10.1016/j.ins.2017.09.070_bib0033
  article-title: Visualizing data using t-sne
  publication-title: J. Mach. Learn. Res.
– start-page: 658
  year: 2016
  ident: 10.1016/j.ins.2017.09.070_bib0021
  article-title: Wordrank: learning word embeddings via robust ranking
– start-page: 2418
  year: 2015
  ident: 10.1016/j.ins.2017.09.070_bib0030
  article-title: Topical word embeddings
– start-page: 1853
  year: 2014
  ident: 10.1016/j.ins.2017.09.070_bib0004
  article-title: An autoencoder approach to learning bilingual word representations
– year: 2010
  ident: 10.1016/j.ins.2017.09.070_bib0009
  article-title: Adaptive subgradient methods for online learning and stochastic optimization
– year: 2014
  ident: 10.1016/j.ins.2017.09.070_bib0040
  article-title: Stochastic backpropagation and approximate inference in deep generative models
– year: 2015
  ident: 10.1016/j.ins.2017.09.070_bib0043
  article-title: Leveraging monolingual data for crosslingual compositional word representations
– year: 2014
  ident: 10.1016/j.ins.2017.09.070_bib0024
  article-title: Auto-encoding variational bayes
– start-page: 493
  year: 2016
  ident: 10.1016/j.ins.2017.09.070_bib0038
  article-title: Cross-lingual word representations via spectral graph embeddings
– start-page: 3581
  year: 2014
  ident: 10.1016/j.ins.2017.09.070_bib0023
  article-title: Semi-supervised learning with deep generative models
– start-page: 1520
  year: 2015
  ident: 10.1016/j.ins.2017.09.070_bib0028
  article-title: Finding function in form: compositional character models for open vocabulary word representation
– start-page: 363
  year: 2015
  ident: 10.1016/j.ins.2017.09.070_bib0049
  article-title: Monolingual and cross-lingual information retrieval models based on (bilingual) word embeddings
– start-page: 151
  year: 2015
  ident: 10.1016/j.ins.2017.09.070_bib0032
  article-title: Bilingual word representations with monolingual quality in mind
– volume: 62
  start-page: 3742
  year: 2015
  ident: 10.1016/j.ins.2017.09.070_bib0018
  article-title: Image-based three-dimensional human pose recovery by multiview locality-sensitive sparse retrieval
  publication-title: IEEE Trans. Ind. Electron.
– start-page: 151
  year: 2011
  ident: 10.1016/j.ins.2017.09.070_bib0042
  article-title: Semi-supervised recursive autoencoders for predicting sentiment distributions
– start-page: 58
  year: 2014
  ident: 10.1016/j.ins.2017.09.070_bib0017
  article-title: Multilingual models for compositional distributed semantics
– ident: 10.1016/j.ins.2017.09.070_bib0036
– year: 2014
  ident: 10.1016/j.ins.2017.09.070_bib0016
  article-title: Multilingual distributed representations without word alignment
– start-page: 1661
  year: 2016
  ident: 10.1016/j.ins.2017.09.070_bib0047
  article-title: Cross-lingual models of word embeddings: an empirical comparison
– volume: 3
  start-page: 1137
  year: 2003
  ident: 10.1016/j.ins.2017.09.070_bib0001
  article-title: A neural probabilistic language model
  publication-title: J. Mach. Learn. Res.
– start-page: 19
  year: 2003
  ident: 10.1016/j.ins.2017.09.070_bib0037
  article-title: A systematic comparison of various statistical alignment models
  publication-title: Comput. Ling.
  doi: 10.1162/089120103321337421
– start-page: 1393
  year: 2013
  ident: 10.1016/j.ins.2017.09.070_bib0054
  article-title: Bilingual word embeddings for phrase-based machine translation
– start-page: 48
  year: 2003
  ident: 10.1016/j.ins.2017.09.070_bib0026
  article-title: Statistical phrase-based translation
– volume: abs/1502.04623
  year: 2015
  ident: 10.1016/j.ins.2017.09.070_bib0013
  article-title: DRAW: a recurrent neural network for image generation
  publication-title: CoRR
– start-page: 1285
  year: 2016
  ident: 10.1016/j.ins.2017.09.070_bib0010
  article-title: Learning crosslingual word embeddings without bilingual corpora
– start-page: 2734
  year: 2016
  ident: 10.1016/j.ins.2017.09.070_bib0015
  article-title: A representation learning framework for multi-source transfer parsing
– start-page: 2980
  year: 2015
  ident: 10.1016/j.ins.2017.09.070_bib0005
  article-title: A recurrent latent variable model for sequential data
– ident: 10.1016/j.ins.2017.09.070_bib0002
  doi: 10.7551/mitpress/7503.003.0024
– volume: 24
  start-page: 5659
  year: 2015
  ident: 10.1016/j.ins.2017.09.070_bib0019
  article-title: Multimodal deep autoencoder for human pose recovery
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2015.2487860
– start-page: 1
  year: 2002
  ident: 10.1016/j.ins.2017.09.070_bib0006
  article-title: Discriminative training methods for hidden markov models: theory and experiments with perceptron algorithms
– year: 2017
  ident: 10.1016/j.ins.2017.09.070_bib0014
  article-title: Cascaded convolutional neural networks for aspect-based opinion summary
  publication-title: Neural Process. Lett.
  doi: 10.1007/s11063-017-9605-7
– start-page: 1284
  year: 2015
  ident: 10.1016/j.ins.2017.09.070_bib0029
  article-title: Learning context-sensitive word embeddings with neural tensor skip-gram mode
– ident: 10.1016/j.ins.2017.09.070_bib0035
– start-page: 1837
  year: 2014
  ident: 10.1016/j.ins.2017.09.070_bib0046
  article-title: Um-corpus: a large english-chinese parallel corpus for statistical machine translation
– start-page: 1
  year: 2016
  ident: 10.1016/j.ins.2017.09.070_bib0051
  article-title: Deep multimodal distance metric learning using click constraints for image ranking
  publication-title: IEEE Trans. Cybern.
– start-page: 873
  year: 2012
  ident: 10.1016/j.ins.2017.09.070_bib0020
  article-title: Improving word representations via global context and multiple word prototypes
– start-page: 748
  year: 2015
  ident: 10.1016/j.ins.2017.09.070_bib0012
  article-title: Bilbowa: fast bilingual distributed representations without word alignments
– ident: 10.1016/j.ins.2017.09.070_bib0045
– start-page: 1351
  year: 2016
  ident: 10.1016/j.ins.2017.09.070_bib0050
  article-title: Learning word meta-embeddings
– start-page: 567
  year: 2015
  ident: 10.1016/j.ins.2017.09.070_bib0041
  article-title: Learning cross-lingual word embeddings via matrix co-factorization
– start-page: 719
  year: 2015
  ident: 10.1016/j.ins.2017.09.070_bib0048
  article-title: Bilingual word embeddings from non-parallel document-aligned data applied to bilingual lexicon induction
– start-page: 250
  year: 2015
  ident: 10.1016/j.ins.2017.09.070_bib0031
  article-title: Deep multilingual correlation for improved word embeddings
– start-page: 1651
  year: 2016
  ident: 10.1016/j.ins.2017.09.070_bib0007
  article-title: Morphological smoothing and extrapolation of word embeddings
– start-page: 1005
  year: 2016
  ident: 10.1016/j.ins.2017.09.070_bib0052
  article-title: Iprivacy: image privacy protection by identifying sensitive objects via deep multi-task learning
  publication-title: IEEE Trans. Inf. Forensics Secur.
– start-page: 490
  year: 2016
  ident: 10.1016/j.ins.2017.09.070_bib0003
  article-title: Morphological priors for probabilistic neural word embeddings
– volume: 417
  start-page: 72
  year: 2017
  ident: 10.1016/j.ins.2017.09.070_bib0022
  article-title: Deep hybrid recommender systems via exploiting document context and statistics of items
  publication-title: Inf. Sci.
  doi: 10.1016/j.ins.2017.06.026
– start-page: 1459
  year: 2012
  ident: 10.1016/j.ins.2017.09.070_bib0025
  article-title: Inducing crosslingual distributed representations of words
– ident: 10.1016/j.ins.2017.09.070_bib0034
SSID ssj0004766
Score 2.3510153
Snippet Bilingual word embeddings (BWEs) have been shown to be useful in various cross-lingual natural language processing tasks. To accurately learn BWEs, previous...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 287
SubjectTerms Bilingual word embeddings
Cross-lingual document classification
Neural generative autoencoder
Translation probability modeling
Title A neural generative autoencoder for bilingual word embeddings
URI https://dx.doi.org/10.1016/j.ins.2017.09.070
Volume 424
WOSCitedRecordID wos000414889900017&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1872-6291
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0004766
  issn: 0020-0255
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1RT9swELamsgf2MG2MaYwx-QHtYShS4rpx_MBDQUxjD2gSTOpb5Ngua8VSBO3oz-fOdpzQbQgm8ZJWlp1Wd5_Od_bdd4TsCgNuhGY2UUyzhOsx2EHBIXBV4L5mWmII4ZpNiJOTYjSS30N1ybVrJyDqulgu5eWTqhrGQNlYOvsIdceXwgB8B6XDE9QOzwcpfriHHJUg-XPHKO1Sg9RiPkPGSiSOcPmZE6xCx8qRGywXtL8qa0w8M5822e2xsnEvbJTRAT9dOPW70rHzaNjd4OnPFnDxOPpgomZ3p7myhmWzcYZzh6xYOXeIBTF38jXR-0wwTPHbi7ephWBJznxTrsbocsa7ZjNsun4H7jvu0j-Nuz9nmEJEgjzrmXAEtb7tyApnNl5Bu2gpAwMmC2Q3WGMCwNcja8Pjo9G3tnRW-Ovs5n83F98uBXDlh_7uunTckbNX5GWII-jQ6_81eWbrDfKiwy65QXZCTQr9RDuqpMGavyH7Q-qRQluk0A5SKKyhESkUkUJbpGySH1-Ozg6_JqGbRqKZFPNknA5sJVSllDK5ElLy1CJ5pK0G0rKKF0ora-AdcixYbuDTpBYmcysHXA1k_y3p1bPaviNUZNymzGibmpznppAgaGYqjM616vfNFkkbQZU6UM1jx5OLsskpnJYg2xJlW6ayBNlukc9xyaXnWblvMm-kXwb8ewewBKj8e9n7_1u2TdZb_H8gvfnVwu6Q5_r3fHJ99TEA6hbrpow9
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+neural+generative+autoencoder+for+bilingual+word+embeddings&rft.jtitle=Information+sciences&rft.au=Su%2C+Jinsong&rft.au=Wu%2C+Shan&rft.au=Zhang%2C+Biao&rft.au=Wu%2C+Changxing&rft.date=2018-01-01&rft.pub=Elsevier+Inc&rft.issn=0020-0255&rft.eissn=1872-6291&rft.volume=424&rft.spage=287&rft.epage=300&rft_id=info:doi/10.1016%2Fj.ins.2017.09.070&rft.externalDocID=S0020025517309891
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0020-0255&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0020-0255&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0020-0255&client=summon