An AdaBoost for Efficient Use of Confidences of Weak Hypotheses on Text Categorization View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2014

AUTHORS

Tomoya Iwakura , Takahiro Saitou , Seishi Okamoto

ABSTRACT

We propose a boosting algorithm based on AdaBoost for using real-valued weak hypotheses that return confidences of their classifications as real numbers with an approximated upper bound of the training error. The approximated upper bound is induced with Bernoulli’s inequality and the upper bound enables us to analytically calculate a confidence-value that satisfies a reduction in the original upper bound. The experimental results on the Reuters-21578 data set and an Amazon review data show that our boosting algorithm with the perceptron attains better accuracy than Support Vector Machines, decision stumps-based boosting algorithms and a perceptron. More... »

PAGES

782-794

References to SciGraph publications

  • 2001-03. Soft Margins for AdaBoost in MACHINE LEARNING
  • 1999. Theoretical Views of Boosting and Applications in ALGORITHMIC LEARNING THEORY
  • 2011-03. Pegasos: primal estimated sub-gradient solver for SVM in MATHEMATICAL PROGRAMMING
  • 2000-05. BoosTexter: A Boosting-based System for Text Categorization in MACHINE LEARNING
  • 2002-07. Logistic Regression, AdaBoost and Bregman Distances in MACHINE LEARNING
  • 2001. Optimizing the Induction of Alternating Decision Trees in ADVANCES IN KNOWLEDGE DISCOVERY AND DATA MINING
  • 2002-09-20. Learning and Inference for Clause Identification in MACHINE LEARNING: ECML 2002
  • 1999-12. Improved Boosting Algorithms Using Confidence-rated Predictions in MACHINE LEARNING
  • 2000. Boosting Applied to Word Sense Disambiguation in MACHINE LEARNING: ECML 2000
  • Book

    TITLE

    PRICAI 2014: Trends in Artificial Intelligence

    ISBN

    978-3-319-13559-5
    978-3-319-13560-1

    Author Affiliations

    Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/978-3-319-13560-1_62

    DOI

    http://dx.doi.org/10.1007/978-3-319-13560-1_62

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1013843827


    Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
    Incoming Citations Browse incoming citations for this publication using opencitations.net

    JSON-LD is the canonical representation for SciGraph data.

    TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

    [
      {
        "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
        "about": [
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0806", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Information Systems", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Information and Computing Sciences", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Fujitsu (Japan)", 
              "id": "https://www.grid.ac/institutes/grid.418251.b", 
              "name": [
                "Fujitsu Laboratories Ltd., 1-1, Kamikodanaka 4-chome, Nakahara-ku\u00a0Kawasaki, 211-8588, Japan"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Iwakura", 
            "givenName": "Tomoya", 
            "id": "sg:person.010334324445.74", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010334324445.74"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Fujitsu (Japan)", 
              "id": "https://www.grid.ac/institutes/grid.418251.b", 
              "name": [
                "Fujitsu Laboratories Ltd., 1-1, Kamikodanaka 4-chome, Nakahara-ku\u00a0Kawasaki, 211-8588, Japan"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Saitou", 
            "givenName": "Takahiro", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Fujitsu (Japan)", 
              "id": "https://www.grid.ac/institutes/grid.418251.b", 
              "name": [
                "Fujitsu Laboratories Ltd., 1-1, Kamikodanaka 4-chome, Nakahara-ku\u00a0Kawasaki, 211-8588, Japan"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Okamoto", 
            "givenName": "Seishi", 
            "id": "sg:person.012442023053.51", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012442023053.51"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1023/a:1007649029923", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1001772171", 
              "https://doi.org/10.1023/a:1007649029923"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-45164-1_14", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1002927114", 
              "https://doi.org/10.1007/3-540-45164-1_14"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1023/a:1007618119488", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1003090683", 
              "https://doi.org/10.1023/a:1007618119488"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1006/jcss.1997.1504", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1004338842"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.artint.2006.10.014", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1013181560"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1023/a:1013912006537", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1017358459", 
              "https://doi.org/10.1023/a:1013912006537"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1214/aos/1016218223", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1020629296"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1553374.1553439", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1030162420"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1214/aos/1013203451", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1030645893"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1037/h0042519", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1030890551"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1273496.1273533", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1034579123"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-36755-1_4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1040986348", 
              "https://doi.org/10.1007/3-540-36755-1_4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-36755-1_4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1040986348", 
              "https://doi.org/10.1007/3-540-36755-1_4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-45357-1_50", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1042567650", 
              "https://doi.org/10.1007/3-540-45357-1_50"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-46769-6_2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1045955876", 
              "https://doi.org/10.1007/3-540-46769-6_2"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s10107-010-0420-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1050541291", 
              "https://doi.org/10.1007/s10107-010-0420-4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1023/a:1007614523901", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1050587930", 
              "https://doi.org/10.1023/a:1007614523901"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.3115/1118693.1118694", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099201575"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.3115/1118693.1118694", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099201575"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2014", 
        "datePublishedReg": "2014-01-01", 
        "description": "We propose a boosting algorithm based on AdaBoost for using real-valued weak hypotheses that return confidences of their classifications as real numbers with an approximated upper bound of the training error. The approximated upper bound is induced with Bernoulli\u2019s inequality and the upper bound enables us to analytically calculate a confidence-value that satisfies a reduction in the original upper bound. The experimental results on the Reuters-21578 data set and an Amazon review data show that our boosting algorithm with the perceptron attains better accuracy than Support Vector Machines, decision stumps-based boosting algorithms and a perceptron.", 
        "editor": [
          {
            "familyName": "Pham", 
            "givenName": "Duc-Nghia", 
            "type": "Person"
          }, 
          {
            "familyName": "Park", 
            "givenName": "Seong-Bae", 
            "type": "Person"
          }
        ], 
        "genre": "chapter", 
        "id": "sg:pub.10.1007/978-3-319-13560-1_62", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": {
          "isbn": [
            "978-3-319-13559-5", 
            "978-3-319-13560-1"
          ], 
          "name": "PRICAI 2014: Trends in Artificial Intelligence", 
          "type": "Book"
        }, 
        "name": "An AdaBoost for Efficient Use of Confidences of Weak Hypotheses on Text Categorization", 
        "pagination": "782-794", 
        "productId": [
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/978-3-319-13560-1_62"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "41f304e8b2765c2fbdc580d7ef751413b97190b3bbab7070dedaf961e346c243"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1013843827"
            ]
          }
        ], 
        "publisher": {
          "location": "Cham", 
          "name": "Springer International Publishing", 
          "type": "Organisation"
        }, 
        "sameAs": [
          "https://doi.org/10.1007/978-3-319-13560-1_62", 
          "https://app.dimensions.ai/details/publication/pub.1013843827"
        ], 
        "sdDataset": "chapters", 
        "sdDatePublished": "2019-04-15T11:33", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000001_0000000264/records_8660_00000251.jsonl", 
        "type": "Chapter", 
        "url": "http://link.springer.com/10.1007/978-3-319-13560-1_62"
      }
    ]
     

    Download the RDF metadata as:  json-ld nt turtle xml License info

    HOW TO GET THIS DATA PROGRAMMATICALLY:

    JSON-LD is a popular format for linked data which is fully compatible with JSON.

    curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-13560-1_62'

    N-Triples is a line-based linked data format ideal for batch operations.

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-13560-1_62'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-13560-1_62'

    RDF/XML is a standard XML format for linked data.

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-13560-1_62'


     

    This table displays all metadata directly associated to this object as RDF triples.

    143 TRIPLES      23 PREDICATES      44 URIs      20 LITERALS      8 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/978-3-319-13560-1_62 schema:about anzsrc-for:08
    2 anzsrc-for:0806
    3 schema:author N0fad66795ecb4492b2ed5de0175a7389
    4 schema:citation sg:pub.10.1007/3-540-36755-1_4
    5 sg:pub.10.1007/3-540-45164-1_14
    6 sg:pub.10.1007/3-540-45357-1_50
    7 sg:pub.10.1007/3-540-46769-6_2
    8 sg:pub.10.1007/s10107-010-0420-4
    9 sg:pub.10.1023/a:1007614523901
    10 sg:pub.10.1023/a:1007618119488
    11 sg:pub.10.1023/a:1007649029923
    12 sg:pub.10.1023/a:1013912006537
    13 https://doi.org/10.1006/jcss.1997.1504
    14 https://doi.org/10.1016/j.artint.2006.10.014
    15 https://doi.org/10.1037/h0042519
    16 https://doi.org/10.1145/1273496.1273533
    17 https://doi.org/10.1145/1553374.1553439
    18 https://doi.org/10.1214/aos/1013203451
    19 https://doi.org/10.1214/aos/1016218223
    20 https://doi.org/10.3115/1118693.1118694
    21 schema:datePublished 2014
    22 schema:datePublishedReg 2014-01-01
    23 schema:description We propose a boosting algorithm based on AdaBoost for using real-valued weak hypotheses that return confidences of their classifications as real numbers with an approximated upper bound of the training error. The approximated upper bound is induced with Bernoulli’s inequality and the upper bound enables us to analytically calculate a confidence-value that satisfies a reduction in the original upper bound. The experimental results on the Reuters-21578 data set and an Amazon review data show that our boosting algorithm with the perceptron attains better accuracy than Support Vector Machines, decision stumps-based boosting algorithms and a perceptron.
    24 schema:editor N0dc9a5b1e2734ffbba480fe50a7e3efc
    25 schema:genre chapter
    26 schema:inLanguage en
    27 schema:isAccessibleForFree false
    28 schema:isPartOf N67b1802a88824cfa8e93409be96e26d4
    29 schema:name An AdaBoost for Efficient Use of Confidences of Weak Hypotheses on Text Categorization
    30 schema:pagination 782-794
    31 schema:productId N20fcdb5944694549bb3e942c52e1fb82
    32 N32bc3a06607f4f6d932b09a024a9767c
    33 Ncf80c0c40c7048be9200ebb41030fb79
    34 schema:publisher N8fb448735be94193bf2296805bcc234d
    35 schema:sameAs https://app.dimensions.ai/details/publication/pub.1013843827
    36 https://doi.org/10.1007/978-3-319-13560-1_62
    37 schema:sdDatePublished 2019-04-15T11:33
    38 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    39 schema:sdPublisher N663655e9691049298736bffb2ca994b2
    40 schema:url http://link.springer.com/10.1007/978-3-319-13560-1_62
    41 sgo:license sg:explorer/license/
    42 sgo:sdDataset chapters
    43 rdf:type schema:Chapter
    44 N01db05bd8e05465fb6b6e20d71ebaffb schema:familyName Pham
    45 schema:givenName Duc-Nghia
    46 rdf:type schema:Person
    47 N0dc9a5b1e2734ffbba480fe50a7e3efc rdf:first N01db05bd8e05465fb6b6e20d71ebaffb
    48 rdf:rest Ne45458c56bd54f1a8608212d5c25bf0e
    49 N0fad66795ecb4492b2ed5de0175a7389 rdf:first sg:person.010334324445.74
    50 rdf:rest N893d11fc79bd415c807bc1c328fd397a
    51 N20fcdb5944694549bb3e942c52e1fb82 schema:name dimensions_id
    52 schema:value pub.1013843827
    53 rdf:type schema:PropertyValue
    54 N32bc3a06607f4f6d932b09a024a9767c schema:name readcube_id
    55 schema:value 41f304e8b2765c2fbdc580d7ef751413b97190b3bbab7070dedaf961e346c243
    56 rdf:type schema:PropertyValue
    57 N48dca0d3b14e4f94a78393cb58f0b7f6 schema:affiliation https://www.grid.ac/institutes/grid.418251.b
    58 schema:familyName Saitou
    59 schema:givenName Takahiro
    60 rdf:type schema:Person
    61 N663655e9691049298736bffb2ca994b2 schema:name Springer Nature - SN SciGraph project
    62 rdf:type schema:Organization
    63 N67b1802a88824cfa8e93409be96e26d4 schema:isbn 978-3-319-13559-5
    64 978-3-319-13560-1
    65 schema:name PRICAI 2014: Trends in Artificial Intelligence
    66 rdf:type schema:Book
    67 N893d11fc79bd415c807bc1c328fd397a rdf:first N48dca0d3b14e4f94a78393cb58f0b7f6
    68 rdf:rest Nf89f6e61922d4067afdc4ba961db1c19
    69 N8fb448735be94193bf2296805bcc234d schema:location Cham
    70 schema:name Springer International Publishing
    71 rdf:type schema:Organisation
    72 Nbaf6860850bf46b99969edb8cc603b58 schema:familyName Park
    73 schema:givenName Seong-Bae
    74 rdf:type schema:Person
    75 Ncf80c0c40c7048be9200ebb41030fb79 schema:name doi
    76 schema:value 10.1007/978-3-319-13560-1_62
    77 rdf:type schema:PropertyValue
    78 Ne45458c56bd54f1a8608212d5c25bf0e rdf:first Nbaf6860850bf46b99969edb8cc603b58
    79 rdf:rest rdf:nil
    80 Nf89f6e61922d4067afdc4ba961db1c19 rdf:first sg:person.012442023053.51
    81 rdf:rest rdf:nil
    82 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    83 schema:name Information and Computing Sciences
    84 rdf:type schema:DefinedTerm
    85 anzsrc-for:0806 schema:inDefinedTermSet anzsrc-for:
    86 schema:name Information Systems
    87 rdf:type schema:DefinedTerm
    88 sg:person.010334324445.74 schema:affiliation https://www.grid.ac/institutes/grid.418251.b
    89 schema:familyName Iwakura
    90 schema:givenName Tomoya
    91 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010334324445.74
    92 rdf:type schema:Person
    93 sg:person.012442023053.51 schema:affiliation https://www.grid.ac/institutes/grid.418251.b
    94 schema:familyName Okamoto
    95 schema:givenName Seishi
    96 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012442023053.51
    97 rdf:type schema:Person
    98 sg:pub.10.1007/3-540-36755-1_4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040986348
    99 https://doi.org/10.1007/3-540-36755-1_4
    100 rdf:type schema:CreativeWork
    101 sg:pub.10.1007/3-540-45164-1_14 schema:sameAs https://app.dimensions.ai/details/publication/pub.1002927114
    102 https://doi.org/10.1007/3-540-45164-1_14
    103 rdf:type schema:CreativeWork
    104 sg:pub.10.1007/3-540-45357-1_50 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042567650
    105 https://doi.org/10.1007/3-540-45357-1_50
    106 rdf:type schema:CreativeWork
    107 sg:pub.10.1007/3-540-46769-6_2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045955876
    108 https://doi.org/10.1007/3-540-46769-6_2
    109 rdf:type schema:CreativeWork
    110 sg:pub.10.1007/s10107-010-0420-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1050541291
    111 https://doi.org/10.1007/s10107-010-0420-4
    112 rdf:type schema:CreativeWork
    113 sg:pub.10.1023/a:1007614523901 schema:sameAs https://app.dimensions.ai/details/publication/pub.1050587930
    114 https://doi.org/10.1023/a:1007614523901
    115 rdf:type schema:CreativeWork
    116 sg:pub.10.1023/a:1007618119488 schema:sameAs https://app.dimensions.ai/details/publication/pub.1003090683
    117 https://doi.org/10.1023/a:1007618119488
    118 rdf:type schema:CreativeWork
    119 sg:pub.10.1023/a:1007649029923 schema:sameAs https://app.dimensions.ai/details/publication/pub.1001772171
    120 https://doi.org/10.1023/a:1007649029923
    121 rdf:type schema:CreativeWork
    122 sg:pub.10.1023/a:1013912006537 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017358459
    123 https://doi.org/10.1023/a:1013912006537
    124 rdf:type schema:CreativeWork
    125 https://doi.org/10.1006/jcss.1997.1504 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004338842
    126 rdf:type schema:CreativeWork
    127 https://doi.org/10.1016/j.artint.2006.10.014 schema:sameAs https://app.dimensions.ai/details/publication/pub.1013181560
    128 rdf:type schema:CreativeWork
    129 https://doi.org/10.1037/h0042519 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030890551
    130 rdf:type schema:CreativeWork
    131 https://doi.org/10.1145/1273496.1273533 schema:sameAs https://app.dimensions.ai/details/publication/pub.1034579123
    132 rdf:type schema:CreativeWork
    133 https://doi.org/10.1145/1553374.1553439 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030162420
    134 rdf:type schema:CreativeWork
    135 https://doi.org/10.1214/aos/1013203451 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030645893
    136 rdf:type schema:CreativeWork
    137 https://doi.org/10.1214/aos/1016218223 schema:sameAs https://app.dimensions.ai/details/publication/pub.1020629296
    138 rdf:type schema:CreativeWork
    139 https://doi.org/10.3115/1118693.1118694 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099201575
    140 rdf:type schema:CreativeWork
    141 https://www.grid.ac/institutes/grid.418251.b schema:alternateName Fujitsu (Japan)
    142 schema:name Fujitsu Laboratories Ltd., 1-1, Kamikodanaka 4-chome, Nakahara-ku Kawasaki, 211-8588, Japan
    143 rdf:type schema:Organization
     




    Preview window. Press ESC to close (or click here)


    ...