Iterated dilated convolutional neural networks for word segmentation

The latest development of neural word segmentation is governed by bi-directional Long Short-Term Memory Networks (Bi-LSTMs) that utilize Recurrent Neural Networks (RNNs) as standard sequence tagging models, resulting in expressive and accurate performance on large-scale dataset. However, RNNs are no...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Neural network world Ročník 30; číslo 5; s. 333
Hlavní autori: He. H., Yang, X, Wu L., Wang, G
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Prague Czech Technical University in Prague, Faculty of Transportation Sciences 01.01.2020
Predmet:
ISSN:1210-0552, 2336-4335
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract The latest development of neural word segmentation is governed by bi-directional Long Short-Term Memory Networks (Bi-LSTMs) that utilize Recurrent Neural Networks (RNNs) as standard sequence tagging models, resulting in expressive and accurate performance on large-scale dataset. However, RNNs are not adapted to fully exploit the parallelism capability of Graphics Processing Unit (GPU), limiting their computational efficiency in both learning and inferring phases. This paper proposes a novel approach adopting Iterated Dilated Convolutional Neural Networks (ID-CNNs) to supersede Bi-LSTMs for faster computation while retaining accuracy. Our implementation has achieved state-of-the-art result on SIGHAN Bakeoff 2005 datasets. Extensive experiments showed that our approach with ID-CNNs enables 3x training time speedups with no accuracy loss, achieving better accuracy compared to the prevailing Bi-LSTMs. Source code and corpora of this paper have been made publicly available on GitHub.
AbstractList The latest development of neural word segmentation is governed by bi-directional Long Short-Term Memory Networks (Bi-LSTMs) that utilize Recurrent Neural Networks (RNNs) as standard sequence tagging models, resulting in expressive and accurate performance on large-scale dataset. However, RNNs are not adapted to fully exploit the parallelism capability of Graphics Processing Unit (GPU), limiting their computational efficiency in both learning and inferring phases. This paper proposes a novel approach adopting Iterated Dilated Convolutional Neural Networks (ID-CNNs) to supersede Bi-LSTMs for faster computation while retaining accuracy. Our implementation has achieved state-of-the-art result on SIGHAN Bakeoff 2005 datasets. Extensive experiments showed that our approach with ID-CNNs enables 3x training time speedups with no accuracy loss, achieving better accuracy compared to the prevailing Bi-LSTMs. Source code and corpora of this paper have been made publicly available on GitHub.
Author Wang, G
Wu L.
He. H.
Yang, X
Author_xml – sequence: 1
  fullname: He. H.
– sequence: 2
  givenname: X
  surname: Yang
  fullname: Yang, X
– sequence: 3
  fullname: Wu L.
– sequence: 4
  givenname: G
  surname: Wang
  fullname: Wang, G
BookMark eNotzjFPwzAQBWALFYm0sDNGYk7w-ewkHlGBUqkSC8zVxbmglmBD7NC_TylM3xuent5czHzwLMQ1yBI0Atx6fyiVVLJEWUqlzkSmEKtCI5qZyECBLKQx6kLMY9xLqY1tdCbu14lHStzl3W446YL_DsOUdsHTkHuexhPpEMb3mPdhzI-pyyO_fbBP9Nu7FOc9DZGv_l2I18eHl-VTsXlerZd3m8KpGlLhOrZEqJoauGIAamtoGmKwfaWIrNaulY4sAxnbIlLX9eD6tqqcddZYXIibv93PMXxNHNN2H6bxeDNula4tYl01Bn8ApaFQ-g
CitedBy_id crossref_primary_10_3390_app13053245
crossref_primary_10_3390_mi14030531
ContentType Journal Article
Copyright Copyright Czech Technical University in Prague, Faculty of Transportation Sciences 2020
Copyright_xml – notice: Copyright Czech Technical University in Prague, Faculty of Transportation Sciences 2020
DBID 3V.
4T-
4U-
7SC
7XB
88I
8AL
8FD
8FE
8FG
8FK
ABUWG
AFKRA
ARAPS
AZQEC
BENPR
BGLVJ
BYOGL
CCPQU
DWQXO
GNUQQ
HCIFZ
JQ2
K7-
L7M
L~C
L~D
M0N
M2P
P5Z
P62
PHGZM
PHGZT
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
PSYQQ
Q9U
DOI 10.14311/nnw.2020.30.022
DatabaseName ProQuest Central (Corporate)
Docstoc
University Readers
Computer and Information Systems Abstracts
ProQuest Central (purchase pre-March 2016)
Science Database (Alumni Edition)
Computing Database (Alumni Edition)
Technology Research Database
ProQuest SciTech Collection
ProQuest Technology Collection
ProQuest Central (Alumni) (purchase pre-March 2016)
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
Advanced Technologies & Computer Science Collection
ProQuest Central Essentials
ProQuest Central
Technology Collection
East Europe, Central Europe Database (ProQuest)
ProQuest One
ProQuest Central Korea
ProQuest Central Student
SciTech Premium Collection
ProQuest Computer Science Collection
Computer Science Database (ProQuest)
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
Computing Database
Science Database
Advanced Technologies & Aerospace Database
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Premium
ProQuest One Academic (New)
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
ProQuest One Psychology
ProQuest Central Basic
DatabaseTitle ProQuest One Psychology
University Readers
Computer Science Database
ProQuest Central Student
Technology Collection
Technology Research Database
Computer and Information Systems Abstracts – Academic
ProQuest One Academic Middle East (New)
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest Central China
ProQuest Central
ProQuest One Applied & Life Sciences
ProQuest Central Korea
ProQuest Central (New)
Advanced Technologies Database with Aerospace
Advanced Technologies & Aerospace Collection
ProQuest Computing
ProQuest Science Journals (Alumni Edition)
ProQuest Central Basic
ProQuest Science Journals
ProQuest Computing (Alumni Edition)
ProQuest One Academic Eastern Edition
East Europe, Central Europe Database
ProQuest Technology Collection
ProQuest SciTech Collection
Computer and Information Systems Abstracts Professional
Advanced Technologies & Aerospace Database
ProQuest One Academic UKI Edition
Docstoc
ProQuest One Academic
ProQuest Central (Alumni)
ProQuest One Academic (New)
DatabaseTitleList ProQuest One Psychology
Database_xml – sequence: 1
  dbid: BYOGL
  name: East Europe, Central Europe Database
  url: https://search.proquest.com/eastcentraleurope
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 2336-4335
GroupedDBID 123
188
29N
3V.
4T-
4U-
53G
7SC
7XB
88I
8AL
8FD
8FE
8FG
8FK
8R4
8R5
ABUWG
ACGOD
ADMLS
AENEX
AFKRA
ALMA_UNASSIGNED_HOLDINGS
ARAPS
AZQEC
BENPR
BGLVJ
BPHCQ
BYOGL
CCPQU
DWQXO
EOJEC
GNUQQ
HCIFZ
JQ2
K6V
K7-
L7M
L~C
L~D
M0N
M2P
OBODZ
P2P
P62
PHGZM
PHGZT
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
PROAC
PSYQQ
PUEGO
Q2X
Q9U
TUS
UZ4
ID FETCH-LOGICAL-c271t-cde9aa32871e6e11ab7188ae19f62aa944cb0ca9e1a59b33addf1cfb66c9c9593
IEDL.DBID K7-
ISICitedReferencesCount 3
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000606815700004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1210-0552
IngestDate Sun Sep 07 03:28:17 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 5
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c271t-cde9aa32871e6e11ab7188ae19f62aa944cb0ca9e1a59b33addf1cfb66c9c9593
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
PQID 2479337685
PQPubID 2036027
ParticipantIDs proquest_journals_2479337685
PublicationCentury 2000
PublicationDate 2020-01-01
PublicationDateYYYYMMDD 2020-01-01
PublicationDate_xml – month: 01
  year: 2020
  text: 2020-01-01
  day: 01
PublicationDecade 2020
PublicationPlace Prague
PublicationPlace_xml – name: Prague
PublicationSubtitle International Journal on Neural and Mass - Parallel Computing and Information Systems
PublicationTitle Neural network world
PublicationYear 2020
Publisher Czech Technical University in Prague, Faculty of Transportation Sciences
Publisher_xml – name: Czech Technical University in Prague, Faculty of Transportation Sciences
SSID ssj0045984
Score 2.1685014
Snippet The latest development of neural word segmentation is governed by bi-directional Long Short-Term Memory Networks (Bi-LSTMs) that utilize Recurrent Neural...
SourceID proquest
SourceType Aggregation Database
StartPage 333
SubjectTerms Accuracy
Artificial neural networks
Datasets
Graphics processing units
Neural networks
Recurrent neural networks
Segmentation
Source code
Title Iterated dilated convolutional neural networks for word segmentation
URI https://www.proquest.com/docview/2479337685
Volume 30
WOSCitedRecordID wos000606815700004&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: PRVPQU
  databaseName: Advanced Technologies & Aerospace Database
  customDbUrl:
  eissn: 2336-4335
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0045984
  issn: 1210-0552
  databaseCode: P5Z
  dateStart: 20130701
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Computer Science Database
  customDbUrl:
  eissn: 2336-4335
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0045984
  issn: 1210-0552
  databaseCode: K7-
  dateStart: 20130701
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/compscijour
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: East Europe, Central Europe Database
  customDbUrl:
  eissn: 2336-4335
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0045984
  issn: 1210-0552
  databaseCode: BYOGL
  dateStart: 20130701
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/eastcentraleurope
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 2336-4335
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0045984
  issn: 1210-0552
  databaseCode: BENPR
  dateStart: 20130701
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Science Database
  customDbUrl:
  eissn: 2336-4335
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0045984
  issn: 1210-0552
  databaseCode: M2P
  dateStart: 20130701
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/sciencejournals
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LSwMxEA7aevBifeKjlj14jd1ks5vNSXy0KGpZRKV4KXnMSkG32q36903SFMGDFy_JwsKyZGa-yUwm8yF0ZAgwUjKBpXVOmCUSsFSGY51yIDJW2vh8x-MNHwzy4VAUIeFWh7LKBSZ6oDYT7XLkXepSQNYa8vTk7R071ih3uhooNJZRk1BKnJ5fc7xAYpYKzzjsemThOE1pOKa0PpN0q-rLRofUBq3xceyoc39Bsfcv_dZ__2wdrYWdZXQ6V4UNtATVJmotWBuiYMRb6OLKN1IGE5nxi59d5XnQQPsB1-HST74-vI7srjayTyaq4fk13FSqttFDv3d_fokDlwLWlJMZ1gaElImLjyADQqSyTimXQESZUSkFY1rFWgoroFSoJLGwVxJdqizTQrvmxTuoUU0q2EURV2UWG6Op0gnjXEueEckAhEWHWOewh9qLdRoFg6hHP4u0__frA7TqxDLPcrRRYzb9gEO0oj9n43raQc2z3qC463g52_GWFnYs0qdvNuG07w
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V07T8MwED6VggQL5SkeBTLAaBo7zsMDQohStWqpOhRUsRTHdlAlSKEpVPwpfiO2mwiJga0Dk4dIlp27-853Pt8HcCqxojihDHHtnBD1uEI8liESfqgwd2Mhbb7jvhN2u9FgwHol-CrewpiyygITLVDLsTA58hoxKSBtDZF_-fqGDGuUuV0tKDTmatFWnzMdsmUXrbqW7xkhjZv-dRPlrAJIkBBPkZCKce6ZSEEFCmMea3iOuMIsCQjnjFIRu4IzvVSfxZ6nASDBIomDQDBh2vjqeZdgmVIdLGn76fkPBfJTn1mGY9OTC7m-T_JrUe2jcS1NZzoaJTpIds9dQ9X7C_qtP2tU_tuf2ID1_OTsXM1VfRNKKt2CSsFK4eQgtQ31lm0UraQjR892NJX1uYXpCUwHTzvY-vfM0ad2x-zCydTTS_4SK92Bu4XsZRfK6ThVe-CEcRK4UgoSC4-GoeBhgDlVimn0c0Wk9qFayGWYG3w2_BHKwd-fT2C12b_tDDutbvsQ1oxKzDM6VShPJ-_qCFbEx3SUTY6tbjnwuGgRfgN88xHM
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V07T8MwED6VghAL5SkeBTLAaBonThwPCCFKRdWq6gCoYimO7aBKkEJTqPhr_Dps1xESAxsDk4dIlp27-853Pt8HcCyxIjgjDHHtnBAJuUI8lRSJiCrM_VRIm--469JeLxkMWL8Cn-VbGFNWWWKiBWo5FiZH3ghMCkhbQxI1MlcW0W-2zl9ekWGQMjetJZ3GXEU66mOmw7firN3Usj4JgtbVzeU1cgwDSAQUT5GQinEemqhBxQpjnmqoTrjCLIsDzhkhIvUFZ3rZEUvDUINBhkWWxrFgwrT01fMuwCLVMaYJ_PrRfekFSMQs27Hpz4X8KArcFan217iR5zMdmQY6YPZPfUPb-8MNWN_Wqv3nv7IGq-5E7V3MTWAdKirfgFrJVuE58NqEZts2kFbSk6MnO5qKe2d5egLT2dMOti6-8PRp3jO78Ar1-OxeaOVbcPsne9mGaj7O1Q54NM1iX0oRpCIklApOY8yJUkyjoi8StQv1UkZDBwTF8FtAe79_PoJlLblht93r7MOK0Y55oqcO1enkTR3AknifjorJoVUzDx7-WoJfgPAaoA
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=Iterated+dilated+convolutional+neural+networks+for+word+segmentation&rft.jtitle=Neural+network+world&rft.au=He.+H.&rft.au=Yang%2C+X&rft.au=Wu+L.&rft.au=Wang%2C+G&rft.date=2020-01-01&rft.pub=Czech+Technical+University+in+Prague%2C+Faculty+of+Transportation+Sciences&rft.issn=1210-0552&rft.eissn=2336-4335&rft.volume=30&rft.issue=5&rft.spage=333&rft_id=info:doi/10.14311%2Fnnw.2020.30.022&rft.externalDBID=HAS_PDF_LINK
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1210-0552&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1210-0552&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1210-0552&client=summon