Document (#10438)

Author
Sarre, F.
Güntzer, U.
Myka, A.
Jüttner, G.
Title
Maschinelles Lernen von Relationen für Thesauri und Hypertext
Source
Kognitive Ansätze zum Ordnen und Darstellen von Wissen. 2. Tagung der Deutschen ISKO Sektion einschl. der Vorträge des Workshops "Thesauri als Werkzeuge der Sprachtechnologie", Weilburg, 15.-18.10.1991
Imprint
Frankfurt : Indeks
Year
1992
Pages
S.265-276
Series
Fortschritte in der Wissensorganisation; Bd.2
Abstract
Fortschrittliche Informationssysteme stellen ihren Benutzern 2 wichtige Suchmethoden zur Verfügung: die gezielte (Volltext-) Suche und das Navigieren im Objektbestand mit Hilfe von Hypertext-Links. Der Grund, warum diese beiden Konzepte aber auf breiter Basis noch nicht in jedem Informationssystem Anwendung gefunden haben, ist darin zu sehen, daß der manuelle Aufbau von umfassenden Hypertext-Strukturen auf der einen Seite und von großen Thesauri, die den Erfolg von Volltextsuchen wesentlich steigern, auf der anderen Seite bislang enormen Aufwand und damit hohe Kosten verursachte. Langfristig werden Informationssysteme aber nur dann große Akzeptanz bei der Benutzerschaft erzielen, wenn sie ihre Benutzer mit diesen beiden Techniken unterstützen und wenn sie dynamisch neuen Informationsbedürfnissen anpassen können, also lernfähig sind. Für den einzelnen Benutzer ergibt sich daraus der wesentliche Vorteil, daß er von den Recherche-Erfahrungen anderer Benutzer profitieren kann. In diesem Papier stellen wir eine Lernkomponente vor, die für das Hypertextsystem 'HyperMan' an der TU München entwickelt und implementiert wurde. Wir zeigen beispielhaft, wie Volltext-Suchanfragen der HyperMan-Benutzer von der Lernkomponente untersucht werden, um Thesauruseinträge zu gewinnen. Bei der Entwicklung dieser Lerntechniken zum (automatischen) Thesaurusaufbau konnte auf Erfahrungen mit dem lernfähigen Information Retrieval System 'Tegen' zurückgegriffen werden. In dem HyperMan System werden aber nicht nur Beziehungen (Relationen) zwischen Begriffen erlernt, sondern auch zwischen Textstücken. Wir gehen daher auch darauf ein, wie aufgrund einer Analyse des Benutzerverhaltens sowohl neue Hypertext-Links erlernt als auch vorhandene Links, die zuvor von HyperMans Generierungskomponente automatisch erzeugt wurden, modifiziert werden
Theme
Hypertext
Konzeption und Anwendung des Prinzips Thesaurus
Object
HyperMan
TEGEN

Similar documents (content)

  1. Ellis, R.; Hindersmann, J.: Volltext- und Katalogverlinkungen in Online-Datenbanken (2003) 0.21
    0.21251413 = sum of:
      0.21251413 = product of:
        0.590317 = sum of:
          0.026293514 = weight(abstract_txt:zwischen in 1486) [ClassicSimilarity], result of:
            0.026293514 = score(doc=1486,freq=2.0), product of:
              0.11786169 = queryWeight, product of:
                1.1464018 = boost
                5.0479026 = idf(docFreq=771, maxDocs=44218)
                0.020366896 = queryNorm
              0.22308788 = fieldWeight in 1486, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                5.0479026 = idf(docFreq=771, maxDocs=44218)
                0.03125 = fieldNorm(doc=1486)
          0.027783886 = weight(abstract_txt:wenn in 1486) [ClassicSimilarity], result of:
            0.027783886 = score(doc=1486,freq=2.0), product of:
              0.122274406 = queryWeight, product of:
                1.1676651 = boost
                5.1415305 = idf(docFreq=702, maxDocs=44218)
                0.020366896 = queryNorm
              0.22722569 = fieldWeight in 1486, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                5.1415305 = idf(docFreq=702, maxDocs=44218)
                0.03125 = fieldNorm(doc=1486)
          0.025406536 = weight(abstract_txt:auch in 1486) [ClassicSimilarity], result of:
            0.025406536 = score(doc=1486,freq=5.0), product of:
              0.09716003 = queryWeight, product of:
                1.2747939 = boost
                3.742164 = idf(docFreq=2848, maxDocs=44218)
                0.020366896 = queryNorm
              0.26149166 = fieldWeight in 1486, product of:
                2.236068 = tf(freq=5.0), with freq of:
                  5.0 = termFreq=5.0
                3.742164 = idf(docFreq=2848, maxDocs=44218)
                0.03125 = fieldNorm(doc=1486)
          0.036128618 = weight(abstract_txt:aber in 1486) [ClassicSimilarity], result of:
            0.036128618 = score(doc=1486,freq=3.0), product of:
              0.14567146 = queryWeight, product of:
                1.5609299 = boost
                4.5821176 = idf(docFreq=1229, maxDocs=44218)
                0.020366896 = queryNorm
              0.24801439 = fieldWeight in 1486, product of:
                1.7320508 = tf(freq=3.0), with freq of:
                  3.0 = termFreq=3.0
                4.5821176 = idf(docFreq=1229, maxDocs=44218)
                0.03125 = fieldNorm(doc=1486)
          0.05363736 = weight(abstract_txt:informationssysteme in 1486) [ClassicSimilarity], result of:
            0.05363736 = score(doc=1486,freq=1.0), product of:
              0.23885179 = queryWeight, product of:
                1.6319797 = boost
                7.1860275 = idf(docFreq=90, maxDocs=44218)
                0.020366896 = queryNorm
              0.22456336 = fieldWeight in 1486, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                7.1860275 = idf(docFreq=90, maxDocs=44218)
                0.03125 = fieldNorm(doc=1486)
          0.16253762 = weight(abstract_txt:volltext in 1486) [ClassicSimilarity], result of:
            0.16253762 = score(doc=1486,freq=8.0), product of:
              0.25008607 = queryWeight, product of:
                1.6699185 = boost
                7.3530817 = idf(docFreq=76, maxDocs=44218)
                0.020366896 = queryNorm
              0.6499267 = fieldWeight in 1486, product of:
                2.828427 = tf(freq=8.0), with freq of:
                  8.0 = termFreq=8.0
                7.3530817 = idf(docFreq=76, maxDocs=44218)
                0.03125 = fieldNorm(doc=1486)
          0.09856552 = weight(abstract_txt:links in 1486) [ClassicSimilarity], result of:
            0.09856552 = score(doc=1486,freq=10.0), product of:
              0.19039871 = queryWeight, product of:
                1.7845477 = boost
                5.2385488 = idf(docFreq=637, maxDocs=44218)
                0.020366896 = queryNorm
              0.5176796 = fieldWeight in 1486, product of:
                3.1622777 = tf(freq=10.0), with freq of:
                  10.0 = termFreq=10.0
                5.2385488 = idf(docFreq=637, maxDocs=44218)
                0.03125 = fieldNorm(doc=1486)
          0.04405716 = weight(abstract_txt:werden in 1486) [ClassicSimilarity], result of:
            0.04405716 = score(doc=1486,freq=8.0), product of:
              0.14216016 = queryWeight, product of:
                1.9907168 = boost
                3.5062556 = idf(docFreq=3606, maxDocs=44218)
                0.020366896 = queryNorm
              0.30991215 = fieldWeight in 1486, product of:
                2.828427 = tf(freq=8.0), with freq of:
                  8.0 = termFreq=8.0
                3.5062556 = idf(docFreq=3606, maxDocs=44218)
                0.03125 = fieldNorm(doc=1486)
          0.11590683 = weight(abstract_txt:benutzer in 1486) [ClassicSimilarity], result of:
            0.11590683 = score(doc=1486,freq=3.0), product of:
              0.34875932 = queryWeight, product of:
                2.788871 = boost
                6.140059 = idf(docFreq=258, maxDocs=44218)
                0.020366896 = queryNorm
              0.33234045 = fieldWeight in 1486, product of:
                1.7320508 = tf(freq=3.0), with freq of:
                  3.0 = termFreq=3.0
                6.140059 = idf(docFreq=258, maxDocs=44218)
                0.03125 = fieldNorm(doc=1486)
        0.36 = coord(9/25)
    
  2. Nikolai, R.: Thesaurusföderationen : Ein Rahmenwerk für die flexible Integration von heterogenen, autonomen Thesauri (2002) 0.16
    0.16398582 = sum of:
      0.16398582 = product of:
        0.5124557 = sum of:
          0.06980685 = weight(abstract_txt:manuelle in 165) [ClassicSimilarity], result of:
            0.06980685 = score(doc=165,freq=2.0), product of:
              0.17936139 = queryWeight, product of:
                8.806516 = idf(docFreq=17, maxDocs=44218)
                0.020366896 = queryNorm
              0.38919666 = fieldWeight in 165, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                8.806516 = idf(docFreq=17, maxDocs=44218)
                0.03125 = fieldNorm(doc=165)
          0.019646175 = weight(abstract_txt:wenn in 165) [ClassicSimilarity], result of:
            0.019646175 = score(doc=165,freq=1.0), product of:
              0.122274406 = queryWeight, product of:
                1.1676651 = boost
                5.1415305 = idf(docFreq=702, maxDocs=44218)
                0.020366896 = queryNorm
              0.16067283 = fieldWeight in 165, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.1415305 = idf(docFreq=702, maxDocs=44218)
                0.03125 = fieldNorm(doc=165)
          0.09550038 = weight(abstract_txt:thesauri in 165) [ClassicSimilarity], result of:
            0.09550038 = score(doc=165,freq=17.0), product of:
              0.13645957 = queryWeight, product of:
                1.233538 = boost
                5.431586 = idf(docFreq=525, maxDocs=44218)
                0.020366896 = queryNorm
              0.69984376 = fieldWeight in 165, product of:
                4.1231055 = tf(freq=17.0), with freq of:
                  17.0 = termFreq=17.0
                5.431586 = idf(docFreq=525, maxDocs=44218)
                0.03125 = fieldNorm(doc=165)
          0.022724297 = weight(abstract_txt:auch in 165) [ClassicSimilarity], result of:
            0.022724297 = score(doc=165,freq=4.0), product of:
              0.09716003 = queryWeight, product of:
                1.2747939 = boost
                3.742164 = idf(docFreq=2848, maxDocs=44218)
                0.020366896 = queryNorm
              0.23388524 = fieldWeight in 165, product of:
                2.0 = tf(freq=4.0), with freq of:
                  4.0 = termFreq=4.0
                3.742164 = idf(docFreq=2848, maxDocs=44218)
                0.03125 = fieldNorm(doc=165)
          0.029498892 = weight(abstract_txt:aber in 165) [ClassicSimilarity], result of:
            0.029498892 = score(doc=165,freq=2.0), product of:
              0.14567146 = queryWeight, product of:
                1.5609299 = boost
                4.5821176 = idf(docFreq=1229, maxDocs=44218)
                0.020366896 = queryNorm
              0.20250289 = fieldWeight in 165, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                4.5821176 = idf(docFreq=1229, maxDocs=44218)
                0.03125 = fieldNorm(doc=165)
          0.13138418 = weight(abstract_txt:informationssysteme in 165) [ClassicSimilarity], result of:
            0.13138418 = score(doc=165,freq=6.0), product of:
              0.23885179 = queryWeight, product of:
                1.6319797 = boost
                7.1860275 = idf(docFreq=90, maxDocs=44218)
                0.020366896 = queryNorm
              0.5500657 = fieldWeight in 165, product of:
                2.4494898 = tf(freq=6.0), with freq of:
                  6.0 = termFreq=6.0
                7.1860275 = idf(docFreq=90, maxDocs=44218)
                0.03125 = fieldNorm(doc=165)
          0.049257405 = weight(abstract_txt:werden in 165) [ClassicSimilarity], result of:
            0.049257405 = score(doc=165,freq=10.0), product of:
              0.14216016 = queryWeight, product of:
                1.9907168 = boost
                3.5062556 = idf(docFreq=3606, maxDocs=44218)
                0.020366896 = queryNorm
              0.34649232 = fieldWeight in 165, product of:
                3.1622777 = tf(freq=10.0), with freq of:
                  10.0 = termFreq=10.0
                3.5062556 = idf(docFreq=3606, maxDocs=44218)
                0.03125 = fieldNorm(doc=165)
          0.09463753 = weight(abstract_txt:benutzer in 165) [ClassicSimilarity], result of:
            0.09463753 = score(doc=165,freq=2.0), product of:
              0.34875932 = queryWeight, product of:
                2.788871 = boost
                6.140059 = idf(docFreq=258, maxDocs=44218)
                0.020366896 = queryNorm
              0.27135482 = fieldWeight in 165, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                6.140059 = idf(docFreq=258, maxDocs=44218)
                0.03125 = fieldNorm(doc=165)
        0.32 = coord(8/25)
    
  3. Hutzler, E.; Scheuplein, M.: Elektronische Zeitschriftenbibliothek : Neue Dienste im Rahmen von vascoda (2004) 0.15
    0.14934099 = sum of:
      0.14934099 = product of:
        0.53336066 = sum of:
          0.024557719 = weight(abstract_txt:wenn in 2985) [ClassicSimilarity], result of:
            0.024557719 = score(doc=2985,freq=1.0), product of:
              0.122274406 = queryWeight, product of:
                1.1676651 = boost
                5.1415305 = idf(docFreq=702, maxDocs=44218)
                0.020366896 = queryNorm
              0.20084104 = fieldWeight in 2985, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.1415305 = idf(docFreq=702, maxDocs=44218)
                0.0390625 = fieldNorm(doc=2985)
          0.024599772 = weight(abstract_txt:auch in 2985) [ClassicSimilarity], result of:
            0.024599772 = score(doc=2985,freq=3.0), product of:
              0.09716003 = queryWeight, product of:
                1.2747939 = boost
                3.742164 = idf(docFreq=2848, maxDocs=44218)
                0.020366896 = queryNorm
              0.2531882 = fieldWeight in 2985, product of:
                1.7320508 = tf(freq=3.0), with freq of:
                  3.0 = termFreq=3.0
                3.742164 = idf(docFreq=2848, maxDocs=44218)
                0.0390625 = fieldNorm(doc=2985)
          0.05417036 = weight(abstract_txt:seite in 2985) [ClassicSimilarity], result of:
            0.05417036 = score(doc=2985,freq=1.0), product of:
              0.20719759 = queryWeight, product of:
                1.5199975 = boost
                6.6929407 = idf(docFreq=148, maxDocs=44218)
                0.020366896 = queryNorm
              0.261443 = fieldWeight in 2985, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                6.6929407 = idf(docFreq=148, maxDocs=44218)
                0.0390625 = fieldNorm(doc=2985)
          0.19005002 = weight(abstract_txt:volltext in 2985) [ClassicSimilarity], result of:
            0.19005002 = score(doc=2985,freq=7.0), product of:
              0.25008607 = queryWeight, product of:
                1.6699185 = boost
                7.3530817 = idf(docFreq=76, maxDocs=44218)
                0.020366896 = queryNorm
              0.7599385 = fieldWeight in 2985, product of:
                2.6457512 = tf(freq=7.0), with freq of:
                  7.0 = termFreq=7.0
                7.3530817 = idf(docFreq=76, maxDocs=44218)
                0.0390625 = fieldNorm(doc=2985)
          0.03896144 = weight(abstract_txt:links in 2985) [ClassicSimilarity], result of:
            0.03896144 = score(doc=2985,freq=1.0), product of:
              0.19039871 = queryWeight, product of:
                1.7845477 = boost
                5.2385488 = idf(docFreq=637, maxDocs=44218)
                0.020366896 = queryNorm
              0.2046308 = fieldWeight in 2985, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.2385488 = idf(docFreq=637, maxDocs=44218)
                0.0390625 = fieldNorm(doc=2985)
          0.033724237 = weight(abstract_txt:werden in 2985) [ClassicSimilarity], result of:
            0.033724237 = score(doc=2985,freq=3.0), product of:
              0.14216016 = queryWeight, product of:
                1.9907168 = boost
                3.5062556 = idf(docFreq=3606, maxDocs=44218)
                0.020366896 = queryNorm
              0.23722707 = fieldWeight in 2985, product of:
                1.7320508 = tf(freq=3.0), with freq of:
                  3.0 = termFreq=3.0
                3.5062556 = idf(docFreq=3606, maxDocs=44218)
                0.0390625 = fieldNorm(doc=2985)
          0.1672971 = weight(abstract_txt:benutzer in 2985) [ClassicSimilarity], result of:
            0.1672971 = score(doc=2985,freq=4.0), product of:
              0.34875932 = queryWeight, product of:
                2.788871 = boost
                6.140059 = idf(docFreq=258, maxDocs=44218)
                0.020366896 = queryNorm
              0.4796921 = fieldWeight in 2985, product of:
                2.0 = tf(freq=4.0), with freq of:
                  4.0 = termFreq=4.0
                6.140059 = idf(docFreq=258, maxDocs=44218)
                0.0390625 = fieldNorm(doc=2985)
        0.28 = coord(7/25)
    
  4. Hammwöhner, R.: Kohärenzrelationen in Hypertexten : Textparsing (1990) 0.13
    0.13347764 = sum of:
      0.13347764 = product of:
        0.8342353 = sum of:
          0.303947 = weight(abstract_txt:relationen in 8429) [ClassicSimilarity], result of:
            0.303947 = score(doc=8429,freq=1.0), product of:
              0.25963834 = queryWeight, product of:
                1.7015116 = boost
                7.4921947 = idf(docFreq=66, maxDocs=44218)
                0.020366896 = queryNorm
              1.1706554 = fieldWeight in 8429, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                7.4921947 = idf(docFreq=66, maxDocs=44218)
                0.15625 = fieldNorm(doc=8429)
          0.15584576 = weight(abstract_txt:links in 8429) [ClassicSimilarity], result of:
            0.15584576 = score(doc=8429,freq=1.0), product of:
              0.19039871 = queryWeight, product of:
                1.7845477 = boost
                5.2385488 = idf(docFreq=637, maxDocs=44218)
                0.020366896 = queryNorm
              0.8185232 = fieldWeight in 8429, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.2385488 = idf(docFreq=637, maxDocs=44218)
                0.15625 = fieldNorm(doc=8429)
          0.11014291 = weight(abstract_txt:werden in 8429) [ClassicSimilarity], result of:
            0.11014291 = score(doc=8429,freq=2.0), product of:
              0.14216016 = queryWeight, product of:
                1.9907168 = boost
                3.5062556 = idf(docFreq=3606, maxDocs=44218)
                0.020366896 = queryNorm
              0.7747804 = fieldWeight in 8429, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                3.5062556 = idf(docFreq=3606, maxDocs=44218)
                0.15625 = fieldNorm(doc=8429)
          0.26429966 = weight(abstract_txt:hypertext in 8429) [ClassicSimilarity], result of:
            0.26429966 = score(doc=8429,freq=1.0), product of:
              0.29801947 = queryWeight, product of:
                2.5780292 = boost
                5.6758637 = idf(docFreq=411, maxDocs=44218)
                0.020366896 = queryNorm
              0.8868537 = fieldWeight in 8429, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.6758637 = idf(docFreq=411, maxDocs=44218)
                0.15625 = fieldNorm(doc=8429)
        0.16 = coord(4/25)
    
  5. Block, B.; Hengel, C.; Heuvelmann, R.; Katz, C.; Rusch, B.; Schmidgall, K.; Sigrist, B.: Maschinelles Austauschformat für Bibliotheken und die Functional Requirements for Bibliographic Records : Oder: Wieviel FRBR verträgt MAB? (2005) 0.13
    0.12987885 = sum of:
      0.12987885 = product of:
        0.6493942 = sum of:
          0.44030097 = weight(title_txt:maschinelles in 467) [ClassicSimilarity], result of:
            0.44030097 = score(doc=467,freq=1.0), product of:
              0.192862 = queryWeight, product of:
                1.0369525 = boost
                9.131938 = idf(docFreq=12, maxDocs=44218)
                0.020366896 = queryNorm
              2.2829845 = fieldWeight in 467, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                9.131938 = idf(docFreq=12, maxDocs=44218)
                0.25 = fieldNorm(doc=467)
          0.037184644 = weight(abstract_txt:zwischen in 467) [ClassicSimilarity], result of:
            0.037184644 = score(doc=467,freq=4.0), product of:
              0.11786169 = queryWeight, product of:
                1.1464018 = boost
                5.0479026 = idf(docFreq=771, maxDocs=44218)
                0.020366896 = queryNorm
              0.3154939 = fieldWeight in 467, product of:
                2.0 = tf(freq=4.0), with freq of:
                  4.0 = termFreq=4.0
                5.0479026 = idf(docFreq=771, maxDocs=44218)
                0.03125 = fieldNorm(doc=467)
          0.025406536 = weight(abstract_txt:auch in 467) [ClassicSimilarity], result of:
            0.025406536 = score(doc=467,freq=5.0), product of:
              0.09716003 = queryWeight, product of:
                1.2747939 = boost
                3.742164 = idf(docFreq=2848, maxDocs=44218)
                0.020366896 = queryNorm
              0.26149166 = fieldWeight in 467, product of:
                2.236068 = tf(freq=5.0), with freq of:
                  5.0 = termFreq=5.0
                3.742164 = idf(docFreq=2848, maxDocs=44218)
                0.03125 = fieldNorm(doc=467)
          0.10529034 = weight(abstract_txt:relationen in 467) [ClassicSimilarity], result of:
            0.10529034 = score(doc=467,freq=3.0), product of:
              0.25963834 = queryWeight, product of:
                1.7015116 = boost
                7.4921947 = idf(docFreq=66, maxDocs=44218)
                0.020366896 = queryNorm
              0.40552694 = fieldWeight in 467, product of:
                1.7320508 = tf(freq=3.0), with freq of:
                  3.0 = termFreq=3.0
                7.4921947 = idf(docFreq=66, maxDocs=44218)
                0.03125 = fieldNorm(doc=467)
          0.0412117 = weight(abstract_txt:werden in 467) [ClassicSimilarity], result of:
            0.0412117 = score(doc=467,freq=7.0), product of:
              0.14216016 = queryWeight, product of:
                1.9907168 = boost
                3.5062556 = idf(docFreq=3606, maxDocs=44218)
                0.020366896 = queryNorm
              0.28989625 = fieldWeight in 467, product of:
                2.6457512 = tf(freq=7.0), with freq of:
                  7.0 = termFreq=7.0
                3.5062556 = idf(docFreq=3606, maxDocs=44218)
                0.03125 = fieldNorm(doc=467)
        0.2 = coord(5/25)