An Infinite Replicated Softmax Model for Topic Modeling
In this paper, we describe the infinite replicated Softmax model (iRSM) as an adaptive topic model, utilizing the combination of the infinite restricted Boltzmann machine (iRBM) and the replicated Softmax model (RSM). In our approach, the iRBM extends the RBM by enabling its hidden layer to adapt to...
Saved in:
Published in | Modeling Decisions for Artificial Intelligence pp. 307 - 318 |
---|---|
Main Authors | , , , |
Format | Book Chapter Conference Proceeding |
Language | English |
Published |
Cham
Springer International Publishing
2019
|
Series | Lecture Notes in Computer Science |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | In this paper, we describe the infinite replicated Softmax model (iRSM) as an adaptive topic model, utilizing the combination of the infinite restricted Boltzmann machine (iRBM) and the replicated Softmax model (RSM). In our approach, the iRBM extends the RBM by enabling its hidden layer to adapt to the data at hand, while the RSM allows for modeling low-dimensional latent semantic representation from a corpus. The combination of the two results is a method that is able to self-adapt to the number of topics within the document corpus and hence, renders manual identification of the correct number of topics superfluous. We propose a hybrid training approach to effectively improve the performance of the iRSM. An empirical evaluation is performed on a standard data set and the results are compared to the results of a baseline topic model. The results show that the iRSM adapts its hidden layer size to the data and when trained in the proposed hybrid manner outperforms the base RSM model. |
---|---|
AbstractList | In this paper, we describe the infinite replicated Softmax model (iRSM) as an adaptive topic model, utilizing the combination of the infinite restricted Boltzmann machine (iRBM) and the replicated Softmax model (RSM). In our approach, the iRBM extends the RBM by enabling its hidden layer to adapt to the data at hand, while the RSM allows for modeling low-dimensional latent semantic representation from a corpus. The combination of the two results is a method that is able to self-adapt to the number of topics within the document corpus and hence, renders manual identification of the correct number of topics superfluous. We propose a hybrid training approach to effectively improve the performance of the iRSM. An empirical evaluation is performed on a standard data set and the results are compared to the results of a baseline topic model. The results show that the iRSM adapts its hidden layer size to the data and when trained in the proposed hybrid manner outperforms the base RSM model. |
Author | Riveiro, Maria Huhnstock, Nikolas Alexander Karlsson, Alexander Steinhauer, H. Joe |
Author_xml | – sequence: 1 givenname: Nikolas Alexander surname: Huhnstock fullname: Huhnstock, Nikolas Alexander email: nikolas.huhnstock@his.se – sequence: 2 givenname: Alexander surname: Karlsson fullname: Karlsson, Alexander – sequence: 3 givenname: Maria surname: Riveiro fullname: Riveiro, Maria – sequence: 4 givenname: H. Joe surname: Steinhauer fullname: Steinhauer, H. Joe |
BackLink | https://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-17664$$DView record from Swedish Publication Index https://urn.kb.se/resolve?urn=urn:nbn:se:hj:diva-45795$$DView record from Swedish Publication Index |
BookMark | eNqNkE1PAjEQhqtiIiD_wMPetdpOu-32SPCLBGOi6LUp3RaLsN3srlH_vQXx7mlm3vfJHJ4B6lWxcgidUXJJCZFXShaYYcIIBiElw7kGeYAGLCW7gB2iPhWUYsa4OkKjxP91UPRQf7tjJTk7QYO2XRFCQCroIzmusmnlQxU6lz25eh2s6VyZPUffbcxX9hBLt858bLJ5rIP9vUO1PEXH3qxbN9rPIXq5vZlP7vHs8W46Gc9wy6jscK44UOtIQWBRgGDS2hSAzb1Qoiih4FYJaYAb7xgFILykxhLwueG-ZCUbovPfv-2nqz8Wum7CxjTfOpqgr8PrWMdmqd9WmudS5Ym--AcdWk2lEDzhsMcTWC1doxcxvqeW6K10nSRqppM6vXOst9LZDzbGcK4 |
ContentType | Book Chapter Conference Proceeding |
Copyright | Springer Nature Switzerland AG 2019 |
Copyright_xml | – notice: Springer Nature Switzerland AG 2019 |
DBID | ABSHZ ADTPV BNKNJ BVBDO D8T DF6 AABRY D8X |
DOI | 10.1007/978-3-030-26773-5_27 |
DatabaseName | SWEPUB Högskolan i Skövde full text SwePub SwePub Conference SwePub Conference full text SWEPUB Freely available online SWEPUB Högskolan i Skövde SWEPUB Högskolan i Jönköping full text SWEPUB Högskolan i Jönköping |
DatabaseTitleList | |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Computer Science |
EISBN | 3030267733 9783030267735 |
EISSN | 1611-3349 |
Editor | Torra, Vicenç Narukawa, Yasuo Viviani, Marco Pasi, Gabriella |
Editor_xml | – sequence: 1 givenname: Vicenç orcidid: 0000-0002-0368-8037 surname: Torra fullname: Torra, Vicenç email: vtorra@ieee.org – sequence: 2 givenname: Yasuo surname: Narukawa fullname: Narukawa, Yasuo email: nrkwy@eng.tamagawa.ac.jp – sequence: 3 givenname: Gabriella orcidid: 0000-0002-6080-8170 surname: Pasi fullname: Pasi, Gabriella email: gabriella.pasi@unimib.it – sequence: 4 givenname: Marco orcidid: 0000-0002-2274-9050 surname: Viviani fullname: Viviani, Marco email: marco.viviani@unimib.it |
EndPage | 318 |
ExternalDocumentID | oai_DiVA_org_hj_45795 oai_DiVA_org_his_17664 |
GroupedDBID | -DT -GH -~X 1SB 29L 2HA 2HV 5QI 875 AASHB ABMNI ACGFS ADCXD AEFIE ALMA_UNASSIGNED_HOLDINGS EJD F5P FEDTE HVGLF LAS LDH P2P RIG RNI RSU SVGTG VI1 ~02 38. AABBV ABSHZ ADTPV AEDXK AEJLV AEKFX AIFIR AYMPB BBABE BNKNJ BVBDO CXBFT CZZ D8T DF6 EXGDT FCSXQ I4C IEZ MGZZY NSQWD OORQV SBO TPJZQ TSXQS Z5O Z7R Z7S Z7U Z7V Z7W Z7X Z7Y Z7Z Z81 Z82 Z83 Z84 Z85 Z87 Z88 AABRY D8X |
ID | FETCH-LOGICAL-s317t-59421ce0802b82637cc4212c5f6968d284c967a24afe312204d1ac02f5a4fd3d3 |
ISBN | 9783030267728 3030267725 9783030267735 3030267733 |
ISSN | 0302-9743 |
IngestDate | Tue Oct 01 22:06:04 EDT 2024 Tue Oct 01 22:10:27 EDT 2024 Tue Oct 01 19:40:22 EDT 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Language | English |
LinkModel | OpenURL |
MergedId | FETCHMERGED-LOGICAL-s317t-59421ce0802b82637cc4212c5f6968d284c967a24afe312204d1ac02f5a4fd3d3 |
OpenAccessLink | https://urn.kb.se/resolve?urn=urn:nbn:se:hj:diva-45795 |
PageCount | 12 |
ParticipantIDs | swepub_primary_oai_DiVA_org_hj_45795 swepub_primary_oai_DiVA_org_his_17664 springer_books_10_1007_978_3_030_26773_5_27 |
PublicationCentury | 2000 |
PublicationDate | 2019 |
PublicationDateYYYYMMDD | 2019-01-01 |
PublicationDate_xml | – year: 2019 text: 2019 |
PublicationDecade | 2010 |
PublicationPlace | Cham |
PublicationPlace_xml | – name: Cham |
PublicationSeriesSubtitle | Lecture Notes in Artificial Intelligence |
PublicationSeriesTitle | Lecture Notes in Computer Science |
PublicationSeriesTitleAlternate | Lect.Notes Computer |
PublicationSubtitle | 16th International Conference, MDAI 2019, Milan, Italy, September 4–6, 2019, Proceedings |
PublicationTitle | Modeling Decisions for Artificial Intelligence |
PublicationYear | 2019 |
Publisher | Springer International Publishing |
Publisher_xml | – name: Springer International Publishing |
RelatedPersons | Hartmanis, Juris Gao, Wen Bertino, Elisa Woeginger, Gerhard Goos, Gerhard Steffen, Bernhard Yung, Moti |
RelatedPersons_xml | – sequence: 1 givenname: Gerhard surname: Goos fullname: Goos, Gerhard – sequence: 2 givenname: Juris surname: Hartmanis fullname: Hartmanis, Juris – sequence: 3 givenname: Elisa orcidid: 0000-0002-4029-7051 surname: Bertino fullname: Bertino, Elisa – sequence: 4 givenname: Wen surname: Gao fullname: Gao, Wen – sequence: 5 givenname: Bernhard surname: Steffen fullname: Steffen, Bernhard – sequence: 6 givenname: Gerhard surname: Woeginger fullname: Woeginger, Gerhard – sequence: 7 givenname: Moti surname: Yung fullname: Yung, Moti |
SSID | ssj0002792 ssj0002209125 |
Score | 2.122898 |
Snippet | In this paper, we describe the infinite replicated Softmax model (iRSM) as an adaptive topic model, utilizing the combination of the infinite restricted... |
SourceID | swepub springer |
SourceType | Open Access Repository Publisher |
StartPage | 307 |
SubjectTerms | Adaptive Neural Network Restricted Boltzmann machine Skövde Artificial Intelligence Lab (SAIL) Topic modeling Unsupervised learning |
Title | An Infinite Replicated Softmax Model for Topic Modeling |
URI | http://link.springer.com/10.1007/978-3-030-26773-5_27 https://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-17664 https://urn.kb.se/resolve?urn=urn:nbn:se:hj:diva-45795 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Bb9MwFLa6ceMADBCd2OTDOEWZWttxlAOHig111dZTN-1mOYlDAyKZ2lRC_A5-MO_FdpN2E9K4RFXUJs770ufn5_d9j5AzrgvcnzEhhAKjUMjUhIkssN5B5DxlETMaCc43czm9FbP76H4w-NOrWto06Xn2-0leyf-gCucAV2TJPgPZ7UXhBHwGfOEICMNxL_jdTbPaDkPYwwYX-heuTU6rrIDZ9tKpQlz15DY7-JYQEDonOC9_wMp23bFctu5Xr3Ds1Q4FZrs3Aw6ytPSYG22rlH1pcFkt9ca-BNPzYFbvvJFt_rEoMcjFuN-y77ButGh-6l9tV7aWTBks6ocyC_zzWb-Heszrz9dux2NeN20hWeCbUngf9ShhuZfy7LJuOytcmGGxR1bMek4aT4WwDrKO0VjHLVGOkVv5U-eMue2n6-Z1bv38oymjXyUCVw7xbjyMFIsPyEGcgKd8MbmcXd9tM3eMQYzVKTqOUILR7lXZUSGDyI86shpP3VP02JtP3bK3H7-nXdvGO4vX5CVyYCiSU8B6b8jAVEfklTc2dcZ-S-JJRT2mtMOUOkxpiyEFTGmLKfWYviO3Xy8XX6aha8URriHAbMIoEWycGSRmp7Ag5XGWYSlBFhUorpRDjJMlMtZM6MLwMVhI5GOdjVgRaVHkPOfvyWFVV-YDoTE3gmuYZwWXQmswnpGpLFB6jTM95kMSeBMo_HOtlVfWBoMprsBgqjWYQoMNySdrJfVg1VkU6qVflHcTVa--qWUJP4-lFENy9s_vfVciipPo-Fk3_0gOm9XGnEBY2qSn7j35C0c7iBg |
link.rule.ids | 230,310,311,785,786,790,795,796,799,891,4069,4070,27956 |
linkProvider | Library Specific Holdings |
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%3Abook&rft.genre=bookitem&rft.title=Modeling+Decisions+for+Artificial+Intelligence&rft.au=Huhnstock%2C+Nikolas+Alexander&rft.au=Karlsson%2C+Alexander&rft.au=Riveiro%2C+Maria&rft.au=Steinhauer%2C+H.+Joe&rft.atitle=An+Infinite+Replicated+Softmax+Model+for+Topic+Modeling&rft.series=Lecture+Notes+in+Computer+Science&rft.pub=Springer+International+Publishing&rft.isbn=9783030267728&rft.issn=0302-9743&rft.eissn=1611-3349&rft.spage=307&rft.epage=318&rft_id=info:doi/10.1007%2F978-3-030-26773-5_27 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0302-9743&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0302-9743&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0302-9743&client=summon |