Large-Scale Text Classification with Deep Neural Networks

The classification problem in the field of Natural Language Processing has been studied for a long time. Continuing forward with our previous research, which classifies large-scale text using Convolutional Neural Networks (CNN), we implemented Recurrent Neural Networks (RNN), Long- Short Term Memory...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:KIISE Transactions on Computing Practices Ročník 23; číslo 5; s. 322 - 327
Hlavní autoři: Jo, Hwiyeol, Kim, Jin-Hwa, Kim, Kyung-Min, Chang, Jeong-Ho, Eom, Jae-Hong, Zhang, Byoung-Tak
Médium: Journal Article
Jazyk:angličtina
Vydáno: Korean Institute of Information Scientists and Engineers 15.05.2017
한국정보과학회
Témata:
ISSN:2383-6318, 2383-6326
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract The classification problem in the field of Natural Language Processing has been studied for a long time. Continuing forward with our previous research, which classifies large-scale text using Convolutional Neural Networks (CNN), we implemented Recurrent Neural Networks (RNN), Long- Short Term Memory (LSTM) and Gated Recurrent Units (GRU). The experiment’s result revealed that the performance of classification algorithms was Multinomial Naïve Bayesian Classifier < Support Vector Machine (SVM) < LSTM < CNN < GRU, in order. The result can be interpreted as follows: First, the result of CNN was better than LSTM. Therefore, the text classification problem might be related more to feature extraction problem than to natural language understanding problems. Second, judging from the results the GRU showed better performance in feature extraction than LSTM. Finally, the result that the GRU was better than CNN implies that text classification algorithms should consider feature extraction and sequential information. We presented the results of fine-tuning in deep neural networks to provide some intuition regard natural language processing to future researchers. KCI Citation Count: 4
AbstractList The classification problem in the field of Natural Language Processing has been studied for a long time. Continuing forward with our previous research, which classifies large-scale text using Convolutional Neural Networks (CNN), we implemented Recurrent Neural Networks (RNN), Long- Short Term Memory (LSTM) and Gated Recurrent Units (GRU). The experiment’s result revealed that the performance of classification algorithms was Multinomial Naïve Bayesian Classifier < Support Vector Machine (SVM) < LSTM < CNN < GRU, in order. The result can be interpreted as follows: First, the result of CNN was better than LSTM. Therefore, the text classification problem might be related more to feature extraction problem than to natural language understanding problems. Second, judging from the results the GRU showed better performance in feature extraction than LSTM. Finally, the result that the GRU was better than CNN implies that text classification algorithms should consider feature extraction and sequential information. We presented the results of fine-tuning in deep neural networks to provide some intuition regard natural language processing to future researchers. KCI Citation Count: 4
Author Jae-Hong Eom(엄재홍)
Jeong-Ho Chang(장정호)
Hwiyeol Jo(조휘열)
Jin-Hwa Kim(김진화)
Kyung-Min Kim(김경민)
Byoung-Tak Zhang(장병탁)
Author_xml – sequence: 1
  givenname: Hwiyeol
  surname: Jo
  fullname: Jo, Hwiyeol
– sequence: 2
  givenname: Jin-Hwa
  surname: Kim
  fullname: Kim, Jin-Hwa
– sequence: 3
  givenname: Kyung-Min
  surname: Kim
  fullname: Kim, Kyung-Min
– sequence: 4
  givenname: Jeong-Ho
  surname: Chang
  fullname: Chang, Jeong-Ho
– sequence: 5
  givenname: Jae-Hong
  surname: Eom
  fullname: Eom, Jae-Hong
– sequence: 6
  givenname: Byoung-Tak
  surname: Zhang
  fullname: Zhang, Byoung-Tak
BackLink https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART002223970$$DAccess content in National Research Foundation of Korea (NRF)
BookMark eNo9kLFOwzAQhi1UJErpCzBlYWBI8NlJ7IxVWqAiahFkt2zHLlZDUjmpCm9PSqtO_w3ff6f7btGoaRuD0D3gKElJ-vRW5u8RwcAiQqMkooRcoTGhnIYpJenoMgO_QdOucwoT4CTmGYxRVki_MeGnlrUJSvPTB3ktB8Y6LXvXNsHB9V_B3JhdsDJ7L-sh-kPrt90duray7sz0nBNUPi_K_DUs1i_LfFaEGjCDkDJqQUPFE6OASZzgmCnKU1slDLCiVsUq44niacY0aKwYt8xWDHOulFR0gh5PaxtvxVY70Ur3n5tWbL2YfZRLAZQBy_DAkhOrfdt13lix8-5b-l8BWBxViaMqcVQlCBWJGFQNpYfzgf0Am8rJS2u1ni-GH9I4w0D_AArwaQQ
ContentType Journal Article
DBID DBRKI
TDB
AAYXX
CITATION
ACYCR
DOI 10.5626/KTCP.2017.23.5.322
DatabaseName DBPIA - 디비피아
Nurimedia DBPIA Journals
CrossRef
Korean Citation Index
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
DocumentTitle_FL 깊은 신경망 기반 대용량 텍스트 데이터 분류 기술
EISSN 2383-6326
EndPage 327
ExternalDocumentID oai_kci_go_kr_ARTI_1371790
10_5626_KTCP_2017_23_5_322
NODE07164901
GroupedDBID .UV
ALMA_UNASSIGNED_HOLDINGS
DBRKI
TDB
AAYXX
CITATION
ACYCR
M~E
ID FETCH-LOGICAL-c1071-373f1c1d85eb17a05047b386fd5710b3fb4b985b8697c1c0b78f7fd7088bbab3
ISSN 2383-6318
IngestDate Tue Nov 21 21:17:23 EST 2023
Sat Nov 29 02:07:29 EST 2025
Thu Feb 06 14:03:58 EST 2025
IsPeerReviewed false
IsScholarly false
Issue 5
Keywords deep learning
artificial neural networks
자연어 처리
인공신경망
대용량 문서 분류
natural language processing
large-scale text classification
딥러닝
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c1071-373f1c1d85eb17a05047b386fd5710b3fb4b985b8697c1c0b78f7fd7088bbab3
PageCount 6
ParticipantIDs nrf_kci_oai_kci_go_kr_ARTI_1371790
crossref_primary_10_5626_KTCP_2017_23_5_322
nurimedia_primary_NODE07164901
PublicationCentury 2000
PublicationDate 2017-05-15
PublicationDateYYYYMMDD 2017-05-15
PublicationDate_xml – month: 05
  year: 2017
  text: 2017-05-15
  day: 15
PublicationDecade 2010
PublicationTitle KIISE Transactions on Computing Practices
PublicationYear 2017
Publisher Korean Institute of Information Scientists and Engineers
한국정보과학회
Publisher_xml – name: Korean Institute of Information Scientists and Engineers
– name: 한국정보과학회
SSID ssib021824891
ssib044742771
ssib053377435
ssib019653237
Score 1.6230513
Snippet The classification problem in the field of Natural Language Processing has been studied for a long time. Continuing forward with our previous research, which...
SourceID nrf
crossref
nurimedia
SourceType Open Website
Index Database
Publisher
StartPage 322
SubjectTerms 컴퓨터학
Title Large-Scale Text Classification with Deep Neural Networks
URI https://www.dbpia.co.kr/journal/articleDetail?nodeId=NODE07164901
https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART002223970
Volume 23
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
ispartofPNX 정보과학회 컴퓨팅의 실제 논문지, 2017, 23(5), , pp.322-327
journalDatabaseRights – providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2383-6326
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssib044742771
  issn: 2383-6318
  databaseCode: M~E
  dateStart: 20140101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3da9swEBdpN9hexsY2ln0UM_YWlMWWbNmPJc1ImjYL1Iy-iciWiumwQ_oNZX_77ix_NWOwPuxFCQqREt2Pu9P57neEfIEbFzeAHKoSDy8oSUCVUS51PUSUHqW6zKr8cSQWi_D0NFr2evd1Lcz1T5Hn4e1ttP6vooY5EDaWzj5C3M2iMAHvQegwgthh_CfBH2FuNz2Bs9eDGFSv7XuJGUFW1mXk9UDr9QCJOUBCC5sJftH1U-ez2cnEMp_byofyqYJtAYHBhWVVXNUmIJYh1-lNdqeLJmmjatV8mOV0erPamp3fgZ6hx1mDznEduz7UBXwyLboRCbBySGbqt4oLvABGA1bp1UrL2qriCk1-R2UyW5dcWV9mmQK2FTt4aRhjmMfjJabjiaHHhv6w-WqXRXvLujU5h3DbwVUkriFxDekx6UtYY4c88YQfoVo__jWptRFSLbIOkw9S3fOwZRbiXHBPtM40-M3gSpcdXZsDsFVauO3XP3_6A09oJ9_A-Cy_wqYOoBk6Tk78kryobifOvkXVK9LT-WsSdRDlIKKch4hyEFEOIsqxiHJqRL0h8bdJPJ7SquMGTVzwNcHaMOMmbhr6YMLFauSPuFAsDEzqgyeqmFFcRaGvwiASiZuMlAiNMKkAU6XUSrG3ZDcvcv2OOFECpsQIzYzRnAdaeSxdpbgJKIcojfpkUP95uba8KvLvEuqTz3A-8jzJJNKh4-tZIc83Ei59M-kygTxzfbLXHF-z5uL7wQQ35eD3vn_Unh_I8xbcH8nu5eZKfyJPk-vL7GKzV0LlNz7XfTU
linkProvider ISSN International Centre
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=Large-Scale+Text+Classification+with+Deep+Neural+Networks&rft.jtitle=KIISE+Transactions+on+Computing+Practices&rft.au=Jo%2C+Hwiyeol&rft.au=Kim%2C+Jin-Hwa&rft.au=Kim%2C+Kyung-Min&rft.au=Chang%2C+Jeong-Ho&rft.date=2017-05-15&rft.issn=2383-6318&rft.volume=23&rft.issue=5&rft.spage=322&rft.epage=327&rft_id=info:doi/10.5626%2FKTCP.2017.23.5.322&rft.externalDBID=n%2Fa&rft.externalDocID=10_5626_KTCP_2017_23_5_322
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2383-6318&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2383-6318&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2383-6318&client=summon