St. Clair College - Windsor/South Campus

Deep Learning for Matching in Search and Recommendation

Jun, Xu, author.

Boston [Massachusetts] : Now Publishing Inc., 2020.

1 PDF (106 pages) : color illustrations.

Matching, which is to measure the relevance of a document to a query or interest of a user to an item, is a key problem in both search and recommendation. Machine learning has been exploited to address the problem and efforts have been made to develop deep learning techniques for matching tasks in search and recommendation. With the availability of a large amount of data, powerful computational resources, and advanced deep learning techniques, deep learning for matching now becomes the state-of-the-art technology for search and recommendation. The key to the success of the deep learning approach is its strong ability in learning of representations and generalization of matching patterns from data. This survey gives a systematic and comprehensive introduction to the deep matching models for search and recommendation. First, it gives a unified view of matching in search and recommendation and the solutions from the two fields can be compared in one framework. Then, the survey categorizes the current deep learning solutions into two types: methods of representation learning and methods of matching function learning. The fundamental problems as well as the state-of-the-art solutions of query-document matching in search and user-item matching in recommendation are described. Deep Learning for Matching in Search and Recommendation aims to help researchers from both search and recommendation communities to get an in-depth understanding and insight into the spaces, stimulate more ideas and discussions, and promote developments of new technologies. As matching is not limited to search and recommendation, the technologies introduced here can be generalized into a more general task of matching between objects from two spaces. Provided by publisher.

Available

Electronic EbookElectronic Ebook

1 copy available at St. Clair College - Windsor/South Campus

LC Call No:

TJ211.49 .R63 2020eb

Dewey Class No:

629.8/924019 23

Author:

Jun, Xu, author.

Title:

Deep Learning for Matching in Search and Recommendation / Jun, Xu ; Xiangnan, He;Hang, Li.

Physical:

1 PDF (106 pages) : color illustrations.

ContentType:

text rdacontent

MediaType:

electronic isbdmedia

CarrierType:

online resource rdacarrier

Series:

Foundations and trends in information systems, 2331-124X ; 4:2

BibliogrphyNote:

Includes bibliographical references (pages 88-106).

Summary:

Matching, which is to measure the relevance of a document to a query or interest of a user to an item, is a key problem in both search and recommendation. Machine learning has been exploited to address the problem and efforts have been made to develop deep learning techniques for matching tasks in search and recommendation. With the availability of a large amount of data, powerful computational resources, and advanced deep learning techniques, deep learning for matching now becomes the state-of-the-art technology for search and recommendation. The key to the success of the deep learning approach is its strong ability in learning of representations and generalization of matching patterns from data. This survey gives a systematic and comprehensive introduction to the deep matching models for search and recommendation. First, it gives a unified view of matching in search and recommendation and the solutions from the two fields can be compared in one framework. Then, the survey categorizes the current deep learning solutions into two types: methods of representation learning and methods of matching function learning. The fundamental problems as well as the state-of-the-art solutions of query-document matching in search and user-item matching in recommendation are described. Deep Learning for Matching in Search and Recommendation aims to help researchers from both search and recommendation communities to get an in-depth understanding and insight into the spaces, stimulate more ideas and discussions, and promote developments of new technologies. As matching is not limited to search and recommendation, the technologies introduced here can be generalized into a more general task of matching between objects from two spaces. Provided by publisher.

AE:PersName:

Zhang, Qiaoning, author.

AE:PersName:

You, Sangseok, author.

AE:PersName:

Kim, Sangmi, author.

AE:PersName:

Esterwood, Connor, author.

AE:PersName:

Alahmad, Rasha, author.

AE:CorpName:

Now Publications, publisher.

AE:CorpName:

IEEE Xplore (Online Service), distributor.

Field Ind Subfield Data
001 001     3860123
005 005     20201005135231.0
006 006     m eo d
007 007     cr bn||||m|||a
008 008     200520s2020 maua ob 000 0 eng d
020 ISBN   $a ISBN  978-1-68083-707-0
    $q   online
020 ISBN   $q   electronic
035 System Ctrl No   $a System control number  (CaBNVSL)mat09062468
035 System Ctrl No   $a System control number  (IEEE)9062468
035 System Ctrl No   $a System control number  3860105
035 System Ctrl No   $a System control number  3860122
040 Cataloging Src   $a Original cataloging agency  CaBNVSL
    $b Language of cataloging  eng
    $e Description conventions  rda
    $c Transcribing agency  CaBNVSL
    $d Modifying agency  CaBNVSL
050 LC Call No $a Classification number  TJ211.49
    $b Item number  .R63 2020eb
082 Dewey Class No 04  $a Classification number  629.8/924019
    $2 Edition number  23
100 ME:PersonalName 1   $a Personal name  Jun, Xu,
    $e Relator term  author.
245 Title 10  $a Title  Deep Learning for Matching in Search and Recommendation /
    $c Statement of responsibility  Jun, Xu ; Xiangnan, He;Hang, Li.
264 ProductnNotice $a Place of prod/dist/manuf.  Boston [Massachusetts] :
    $b Name of prod./pub./dist./man.  Now Publishing Inc.,
    $c Date of prod/dist/manuf/copyrt  2020.
264 ProductnNotice $a Place of prod/dist/manuf.  [Piscataqay, New Jersey] :
    $b Name of prod./pub./dist./man.  IEEE Xplore,
    $c Date of prod/dist/manuf/copyrt  2020
300 Physical Desc   $a Extent  1 PDF (106 pages) :
    $b Other physical details  color illustrations.
336 ContentType   $a Content type term  text
    $2 Source  rdacontent
337 MediaType   $a Media type term  electronic
    $2 Source  isbdmedia
338 CarrierType   $a Carrier type term  online resource
    $2 Source  rdacarrier
490 SeriesStatement 1   $a Series statement  Foundations and trends in information systems,
    $x ISSN  2331-124X ;
    $v Vol. no./sequential designatn  4:2
504 BibliogrphyNote   $a Bibliography, etc. note  Includes bibliographical references (pages 88-106).
505 505 0   $a 505  1. Introduction -- 2. Literature review -- 3. Thrust area. 1. Human personality and human€€“robot interaction -- 4. Thrust area 2. Robot personality and human€€“robot interaction -- 5. Thrust area 3. Robot and human personality similarities and differences -- 6. Thrust area 4. Factors impacting robot personality -- 7. Major findings and a way forward -- References.
506 506   $a 506  Restricted to subscribers or individual electronic text purchasers.
520 Summary   $a Summary, etc. note  Matching, which is to measure the relevance of a document to a query or interest of a user to an item, is a key problem in both search and recommendation. Machine learning has been exploited to address the problem and efforts have been made to develop deep learning techniques for matching tasks in search and recommendation. With the availability of a large amount of data, powerful computational resources, and advanced deep learning techniques, deep learning for matching now becomes the state-of-the-art technology for search and recommendation. The key to the success of the deep learning approach is its strong ability in learning of representations and generalization of matching patterns from data. This survey gives a systematic and comprehensive introduction to the deep matching models for search and recommendation. First, it gives a unified view of matching in search and recommendation and the solutions from the two fields can be compared in one framework. Then, the survey categorizes the current deep learning solutions into two types: methods of representation learning and methods of matching function learning. The fundamental problems as well as the state-of-the-art solutions of query-document matching in search and user-item matching in recommendation are described. Deep Learning for Matching in Search and Recommendation aims to help researchers from both search and recommendation communities to get an in-depth understanding and insight into the spaces, stimulate more ideas and discussions, and promote developments of new technologies. As matching is not limited to search and recommendation, the technologies introduced here can be generalized into a more general task of matching between objects from two spaces.
    $c   Provided by publisher.
538 538   $a 538  Mode of access: World Wide Web.
588 588   $a 588  Description based on PDF viewed May 20, 2020.
650 Subj. $a Topical heading  Human-robot interactions.
650 Subj. $a Topical heading  Robotics.
655 655 $a 655  Electronic books.
700 AE:PersName 1   $a Personal name  Zhang, Qiaoning,
    $e Relator  author.
700 AE:PersName 1   $a Personal name  You, Sangseok,
    $e Relator  author.
700 AE:PersName 1   $a Personal name  Kim, Sangmi,
    $e Relator  author.
700 AE:PersName 1   $a Personal name  Esterwood, Connor,
    $e Relator  author.
700 AE:PersName 1   $a Personal name  Alahmad, Rasha,
    $e Relator  author.
710 AE:CorpName 2   $a Corporate name  Now Publications,
    $e Relator term  publisher.
710 AE:CorpName 2   $a Corporate name  IEEE Xplore (Online Service),
    $e Relator term  distributor.
830 830 $a 830  Foundations and trends in information systems ;
    $v   4:2.
    $x   2331-124X.
852 Holdings   $a Location  221
    $h Classification part  ebook
    $p Barcode  904
    $9 Cost  $0.00
856 ElectronicLocat 40  $3 Materials specified  Abstract with links to resource
    $u Uniform Resource Identifier  https://ra.ocls.ca/ra/login.aspx?inst=stclair&url=https://ieeexplore-ieee-org.eztest.ocls.ca/document/9141194

Google Books Preview

preview