Document (#31018)

Author
Endres-Niggemeyer, B.
Jauris-Heipke, S.
Pinsky, S.M.
Ulbricht, U.
Title
Wissen gewinnen durch Wissen : Ontologiebasierte Informationsextraktion
Source
Information - Wissenschaft und Praxis. 57(2006) H.6/7, S.301-308
Year
2006
Abstract
Die ontologiebasierte Informationsextraktion, über die hier berichtet wird, ist Teil eines Systems zum automatischen Zusammenfassen, das sich am Vorgehen kompetenter Menschen orientiert. Dahinter steht die Annahme, dass Menschen die Ergebnisse eines Systems leichter übernehmen können, wenn sie mit Verfahren erarbeitet worden sind, die sie selbst auch benutzen. Das erste Anwendungsgebiet ist Knochenmarktransplantation (KMT). Im Kern des Systems Summit-BMT (Summarize It in Bone Marrow Transplantation) steht eine Ontologie des Fachgebietes. Sie ist als MySQL-Datenbank realisiert und versorgt menschliche Benutzer und Systemkomponenten mit Wissen. Summit-BMT unterstützt die Frageformulierung mit einem empirisch fundierten Szenario-Interface. Die Retrievalergebnisse werden durch ein Textpassagenretrieval vorselektiert und dann kognitiv fundierten Agenten unterbreitet, die unter Einsatz ihrer Wissensbasis / Ontologie genauer prüfen, ob die Propositionen aus der Benutzerfrage getroffen werden. Die relevanten Textclips aus dem Duelldokument werden in das Szenarioformular eingetragen und mit einem Link zu ihrem Vorkommen im Original präsentiert. In diesem Artikel stehen die Ontologie und ihr Gebrauch zur wissensbasierten Informationsextraktion im Mittelpunkt. Die Ontologiedatenbank hält unterschiedliche Wissenstypen so bereit, dass sie leicht kombiniert werden können: Konzepte, Propositionen und ihre syntaktisch-semantischen Schemata, Unifikatoren, Paraphrasen und Definitionen von Frage-Szenarios. Auf sie stützen sich die Systemagenten, welche von Menschen adaptierte Zusammenfassungsstrategien ausführen. Mängel in anderen Verarbeitungsschritten führen zu Verlusten, aber die eigentliche Qualität der Ergebnisse steht und fällt mit der Qualität der Ontologie. Erste Tests der Extraktionsleistung fallen verblüffend positiv aus.
Theme
Automatisches Abstracting
Wissensrepräsentation

Similar documents (author)

  1. Endres-Niggemeyer, B.: Sprachverarbeitung im Informationsbereich (1989) 5.93
    5.925562 = sum of:
      5.925562 = sum of:
        2.8624542 = weight(author_txt:niggemeyer in 4860) [ClassicSimilarity], result of:
          2.8624542 = score(doc=4860,freq=1.0), product of:
            0.6909644 = queryWeight, product of:
              8.285388 = idf(docFreq=28, maxDocs=42306)
              0.08339554 = queryNorm
            4.142694 = fieldWeight in 4860, product of:
              1.0 = tf(freq=1.0), with freq of:
                1.0 = termFreq=1.0
              8.285388 = idf(docFreq=28, maxDocs=42306)
              0.5 = fieldNorm(doc=4860)
        3.0631075 = weight(author_txt:endres in 4860) [ClassicSimilarity], result of:
          3.0631075 = score(doc=4860,freq=1.0), product of:
            0.72288877 = queryWeight, product of:
              1.0228405 = boost
              8.47463 = idf(docFreq=23, maxDocs=42306)
              0.08339554 = queryNorm
            4.237315 = fieldWeight in 4860, product of:
              1.0 = tf(freq=1.0), with freq of:
                1.0 = termFreq=1.0
              8.47463 = idf(docFreq=23, maxDocs=42306)
              0.5 = fieldNorm(doc=4860)
    
  2. Endres-Niggemeyer, B.: ¬An empirical process model of abstracting (1992) 5.93
    5.925562 = sum of:
      5.925562 = sum of:
        2.8624542 = weight(author_txt:niggemeyer in 834) [ClassicSimilarity], result of:
          2.8624542 = score(doc=834,freq=1.0), product of:
            0.6909644 = queryWeight, product of:
              8.285388 = idf(docFreq=28, maxDocs=42306)
              0.08339554 = queryNorm
            4.142694 = fieldWeight in 834, product of:
              1.0 = tf(freq=1.0), with freq of:
                1.0 = termFreq=1.0
              8.285388 = idf(docFreq=28, maxDocs=42306)
              0.5 = fieldNorm(doc=834)
        3.0631075 = weight(author_txt:endres in 834) [ClassicSimilarity], result of:
          3.0631075 = score(doc=834,freq=1.0), product of:
            0.72288877 = queryWeight, product of:
              1.0228405 = boost
              8.47463 = idf(docFreq=23, maxDocs=42306)
              0.08339554 = queryNorm
            4.237315 = fieldWeight in 834, product of:
              1.0 = tf(freq=1.0), with freq of:
                1.0 = termFreq=1.0
              8.47463 = idf(docFreq=23, maxDocs=42306)
              0.5 = fieldNorm(doc=834)
    
  3. Endres-Niggemeyer, B.: Summarising text for intelligent communication : results of the Dagstuhl seminar (1994) 5.93
    5.925562 = sum of:
      5.925562 = sum of:
        2.8624542 = weight(author_txt:niggemeyer in 867) [ClassicSimilarity], result of:
          2.8624542 = score(doc=867,freq=1.0), product of:
            0.6909644 = queryWeight, product of:
              8.285388 = idf(docFreq=28, maxDocs=42306)
              0.08339554 = queryNorm
            4.142694 = fieldWeight in 867, product of:
              1.0 = tf(freq=1.0), with freq of:
                1.0 = termFreq=1.0
              8.285388 = idf(docFreq=28, maxDocs=42306)
              0.5 = fieldNorm(doc=867)
        3.0631075 = weight(author_txt:endres in 867) [ClassicSimilarity], result of:
          3.0631075 = score(doc=867,freq=1.0), product of:
            0.72288877 = queryWeight, product of:
              1.0228405 = boost
              8.47463 = idf(docFreq=23, maxDocs=42306)
              0.08339554 = queryNorm
            4.237315 = fieldWeight in 867, product of:
              1.0 = tf(freq=1.0), with freq of:
                1.0 = termFreq=1.0
              8.47463 = idf(docFreq=23, maxDocs=42306)
              0.5 = fieldNorm(doc=867)
    
  4. Endres-Niggemeyer, B.: Wissensbasierte Ansätze zur Formalerfassung (1988) 5.93
    5.925562 = sum of:
      5.925562 = sum of:
        2.8624542 = weight(author_txt:niggemeyer in 593) [ClassicSimilarity], result of:
          2.8624542 = score(doc=593,freq=1.0), product of:
            0.6909644 = queryWeight, product of:
              8.285388 = idf(docFreq=28, maxDocs=42306)
              0.08339554 = queryNorm
            4.142694 = fieldWeight in 593, product of:
              1.0 = tf(freq=1.0), with freq of:
                1.0 = termFreq=1.0
              8.285388 = idf(docFreq=28, maxDocs=42306)
              0.5 = fieldNorm(doc=593)
        3.0631075 = weight(author_txt:endres in 593) [ClassicSimilarity], result of:
          3.0631075 = score(doc=593,freq=1.0), product of:
            0.72288877 = queryWeight, product of:
              1.0228405 = boost
              8.47463 = idf(docFreq=23, maxDocs=42306)
              0.08339554 = queryNorm
            4.237315 = fieldWeight in 593, product of:
              1.0 = tf(freq=1.0), with freq of:
                1.0 = termFreq=1.0
              8.47463 = idf(docFreq=23, maxDocs=42306)
              0.5 = fieldNorm(doc=593)
    
  5. Endres-Niggemeyer, B.: Content analysis : a special case of text compression (1989) 5.93
    5.925562 = sum of:
      5.925562 = sum of:
        2.8624542 = weight(author_txt:niggemeyer in 3618) [ClassicSimilarity], result of:
          2.8624542 = score(doc=3618,freq=1.0), product of:
            0.6909644 = queryWeight, product of:
              8.285388 = idf(docFreq=28, maxDocs=42306)
              0.08339554 = queryNorm
            4.142694 = fieldWeight in 3618, product of:
              1.0 = tf(freq=1.0), with freq of:
                1.0 = termFreq=1.0
              8.285388 = idf(docFreq=28, maxDocs=42306)
              0.5 = fieldNorm(doc=3618)
        3.0631075 = weight(author_txt:endres in 3618) [ClassicSimilarity], result of:
          3.0631075 = score(doc=3618,freq=1.0), product of:
            0.72288877 = queryWeight, product of:
              1.0228405 = boost
              8.47463 = idf(docFreq=23, maxDocs=42306)
              0.08339554 = queryNorm
            4.237315 = fieldWeight in 3618, product of:
              1.0 = tf(freq=1.0), with freq of:
                1.0 = termFreq=1.0
              8.47463 = idf(docFreq=23, maxDocs=42306)
              0.5 = fieldNorm(doc=3618)
    

Similar documents (content)

  1. Endres-Niggemeyer, B.; Ziegert, C.: SummIt-BMT : (Summarize It in BMT) in Diagnose und Therapie, Abschlussbericht (2002) 0.19
    0.19470386 = sum of:
      0.19470386 = product of:
        0.9735193 = sum of:
          0.12695189 = weight(abstract_txt:zusammenfassen in 1498) [ClassicSimilarity], result of:
            0.12695189 = score(doc=1498,freq=2.0), product of:
              0.15361297 = queryWeight, product of:
                1.0102985 = boost
                9.3501 = idf(docFreq=9, maxDocs=42306)
                0.016261552 = queryNorm
              0.82643986 = fieldWeight in 1498, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                9.3501 = idf(docFreq=9, maxDocs=42306)
                0.0625 = fieldNorm(doc=1498)
          0.09635019 = weight(abstract_txt:syntaktisch in 1498) [ClassicSimilarity], result of:
            0.09635019 = score(doc=1498,freq=1.0), product of:
              0.1610325 = queryWeight, product of:
                1.0344095 = boost
                9.573242 = idf(docFreq=7, maxDocs=42306)
                0.016261552 = queryNorm
              0.59832764 = fieldWeight in 1498, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                9.573242 = idf(docFreq=7, maxDocs=42306)
                0.0625 = fieldNorm(doc=1498)
          0.05113569 = weight(abstract_txt:werden in 1498) [ClassicSimilarity], result of:
            0.05113569 = score(doc=1498,freq=7.0), product of:
              0.087595515 = queryWeight, product of:
                1.5258318 = boost
                3.530313 = idf(docFreq=3368, maxDocs=42306)
                0.016261552 = queryNorm
              0.58377063 = fieldWeight in 1498, product of:
                2.6457512 = tf(freq=7.0), with freq of:
                  7.0 = termFreq=7.0
                3.530313 = idf(docFreq=3368, maxDocs=42306)
                0.0625 = fieldNorm(doc=1498)
          0.35907415 = weight(abstract_txt:summit in 1498) [ClassicSimilarity], result of:
            0.35907415 = score(doc=1498,freq=4.0), product of:
              0.30722594 = queryWeight, product of:
                2.020597 = boost
                9.3501 = idf(docFreq=9, maxDocs=42306)
                0.016261552 = queryNorm
              1.1687624 = fieldWeight in 1498, product of:
                2.0 = tf(freq=4.0), with freq of:
                  4.0 = termFreq=4.0
                9.3501 = idf(docFreq=9, maxDocs=42306)
                0.0625 = fieldNorm(doc=1498)
          0.3400074 = weight(abstract_txt:ontologie in 1498) [ClassicSimilarity], result of:
            0.3400074 = score(doc=1498,freq=3.0), product of:
              0.4108188 = queryWeight, product of:
                3.3043869 = boost
                7.645351 = idf(docFreq=54, maxDocs=42306)
                0.016261552 = queryNorm
              0.8276335 = fieldWeight in 1498, product of:
                1.7320508 = tf(freq=3.0), with freq of:
                  3.0 = termFreq=3.0
                7.645351 = idf(docFreq=54, maxDocs=42306)
                0.0625 = fieldNorm(doc=1498)
        0.2 = coord(5/25)
    
  2. Stollberg, M.: Ontologiebasierte Wissensmodellierung : Verwendung als semantischer Grundbaustein des Semantic Web (2002) 0.14
    0.14437479 = sum of:
      0.14437479 = product of:
        0.6015616 = sum of:
          0.062774055 = weight(abstract_txt:anwendungsgebiet in 1496) [ClassicSimilarity], result of:
            0.062774055 = score(doc=1496,freq=1.0), product of:
              0.16555612 = queryWeight, product of:
                1.0488379 = boost
                9.706774 = idf(docFreq=6, maxDocs=42306)
                0.016261552 = queryNorm
              0.37917084 = fieldWeight in 1496, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                9.706774 = idf(docFreq=6, maxDocs=42306)
                0.0390625 = fieldNorm(doc=1496)
          0.022918072 = weight(abstract_txt:ergebnisse in 1496) [ClassicSimilarity], result of:
            0.022918072 = score(doc=1496,freq=1.0), product of:
              0.10655009 = queryWeight, product of:
                1.1899471 = boost
                5.506355 = idf(docFreq=466, maxDocs=42306)
                0.016261552 = queryNorm
              0.21509199 = fieldWeight in 1496, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.506355 = idf(docFreq=466, maxDocs=42306)
                0.0390625 = fieldNorm(doc=1496)
          0.04980576 = weight(abstract_txt:werden in 1496) [ClassicSimilarity], result of:
            0.04980576 = score(doc=1496,freq=17.0), product of:
              0.087595515 = queryWeight, product of:
                1.5258318 = boost
                3.530313 = idf(docFreq=3368, maxDocs=42306)
                0.016261552 = queryNorm
              0.568588 = fieldWeight in 1496, product of:
                4.1231055 = tf(freq=17.0), with freq of:
                  17.0 = termFreq=17.0
                3.530313 = idf(docFreq=3368, maxDocs=42306)
                0.0390625 = fieldNorm(doc=1496)
          0.08905955 = weight(abstract_txt:fundierten in 1496) [ClassicSimilarity], result of:
            0.08905955 = score(doc=1496,freq=1.0), product of:
              0.26336342 = queryWeight, product of:
                1.8708048 = boost
                8.656952 = idf(docFreq=19, maxDocs=42306)
                0.016261552 = queryNorm
              0.33816218 = fieldWeight in 1496, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                8.656952 = idf(docFreq=19, maxDocs=42306)
                0.0390625 = fieldNorm(doc=1496)
          0.131625 = weight(abstract_txt:ontologiebasierte in 1496) [ClassicSimilarity], result of:
            0.131625 = score(doc=1496,freq=1.0), product of:
              0.34171236 = queryWeight, product of:
                2.1309884 = boost
                9.860925 = idf(docFreq=5, maxDocs=42306)
                0.016261552 = queryNorm
              0.38519236 = fieldWeight in 1496, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                9.860925 = idf(docFreq=5, maxDocs=42306)
                0.0390625 = fieldNorm(doc=1496)
          0.2453792 = weight(abstract_txt:ontologie in 1496) [ClassicSimilarity], result of:
            0.2453792 = score(doc=1496,freq=4.0), product of:
              0.4108188 = queryWeight, product of:
                3.3043869 = boost
                7.645351 = idf(docFreq=54, maxDocs=42306)
                0.016261552 = queryNorm
              0.597293 = fieldWeight in 1496, product of:
                2.0 = tf(freq=4.0), with freq of:
                  4.0 = termFreq=4.0
                7.645351 = idf(docFreq=54, maxDocs=42306)
                0.0390625 = fieldNorm(doc=1496)
        0.24 = coord(6/25)
    
  3. Werrmann, J.: Modellierung im Kontext : Ontologie-basiertes Information Retrieval (2011) 0.08
    0.07572156 = sum of:
      0.07572156 = product of:
        0.63101304 = sum of:
          0.03382308 = weight(abstract_txt:werden in 2142) [ClassicSimilarity], result of:
            0.03382308 = score(doc=2142,freq=1.0), product of:
              0.087595515 = queryWeight, product of:
                1.5258318 = boost
                3.530313 = idf(docFreq=3368, maxDocs=42306)
                0.016261552 = queryNorm
              0.38612798 = fieldWeight in 2142, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                3.530313 = idf(docFreq=3368, maxDocs=42306)
                0.109375 = fieldNorm(doc=2142)
          0.11136396 = weight(abstract_txt:wissen in 2142) [ClassicSimilarity], result of:
            0.11136396 = score(doc=2142,freq=2.0), product of:
              0.13980198 = queryWeight, product of:
                1.6693716 = boost
                5.149894 = idf(docFreq=666, maxDocs=42306)
                0.016261552 = queryNorm
              0.7965836 = fieldWeight in 2142, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                5.149894 = idf(docFreq=666, maxDocs=42306)
                0.109375 = fieldNorm(doc=2142)
          0.48582602 = weight(abstract_txt:ontologie in 2142) [ClassicSimilarity], result of:
            0.48582602 = score(doc=2142,freq=2.0), product of:
              0.4108188 = queryWeight, product of:
                3.3043869 = boost
                7.645351 = idf(docFreq=54, maxDocs=42306)
                0.016261552 = queryNorm
              1.1825799 = fieldWeight in 2142, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                7.645351 = idf(docFreq=54, maxDocs=42306)
                0.109375 = fieldNorm(doc=2142)
        0.12 = coord(3/25)
    
  4. Aprin, L.: Entwicklung eines semantisch operierenden Risikomanagement-Informationssystems am Beispiel der Europäischen Organisation für Kernforschung (CERN) (2012) 0.07
    0.06764336 = sum of:
      0.06764336 = product of:
        0.33821678 = sum of:
          0.0399583 = weight(abstract_txt:qualität in 4287) [ClassicSimilarity], result of:
            0.0399583 = score(doc=4287,freq=1.0), product of:
              0.1366844 = queryWeight, product of:
                1.3477527 = boost
                6.2365837 = idf(docFreq=224, maxDocs=42306)
                0.016261552 = queryNorm
              0.29233986 = fieldWeight in 4287, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                6.2365837 = idf(docFreq=224, maxDocs=42306)
                0.046875 = fieldNorm(doc=4287)
          0.014495605 = weight(abstract_txt:werden in 4287) [ClassicSimilarity], result of:
            0.014495605 = score(doc=4287,freq=1.0), product of:
              0.087595515 = queryWeight, product of:
                1.5258318 = boost
                3.530313 = idf(docFreq=3368, maxDocs=42306)
                0.016261552 = queryNorm
              0.16548342 = fieldWeight in 4287, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                3.530313 = idf(docFreq=3368, maxDocs=42306)
                0.046875 = fieldNorm(doc=4287)
          0.089289814 = weight(abstract_txt:wissen in 4287) [ClassicSimilarity], result of:
            0.089289814 = score(doc=4287,freq=7.0), product of:
              0.13980198 = queryWeight, product of:
                1.6693716 = boost
                5.149894 = idf(docFreq=666, maxDocs=42306)
                0.016261552 = queryNorm
              0.6386878 = fieldWeight in 4287, product of:
                2.6457512 = tf(freq=7.0), with freq of:
                  7.0 = termFreq=7.0
                5.149894 = idf(docFreq=666, maxDocs=42306)
                0.046875 = fieldNorm(doc=4287)
          0.04724553 = weight(abstract_txt:steht in 4287) [ClassicSimilarity], result of:
            0.04724553 = score(doc=4287,freq=1.0), product of:
              0.17495184 = queryWeight, product of:
                1.8674786 = boost
                5.76104 = idf(docFreq=361, maxDocs=42306)
                0.016261552 = queryNorm
              0.27004877 = fieldWeight in 4287, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.76104 = idf(docFreq=361, maxDocs=42306)
                0.046875 = fieldNorm(doc=4287)
          0.14722751 = weight(abstract_txt:ontologie in 4287) [ClassicSimilarity], result of:
            0.14722751 = score(doc=4287,freq=1.0), product of:
              0.4108188 = queryWeight, product of:
                3.3043869 = boost
                7.645351 = idf(docFreq=54, maxDocs=42306)
                0.016261552 = queryNorm
              0.35837582 = fieldWeight in 4287, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                7.645351 = idf(docFreq=54, maxDocs=42306)
                0.046875 = fieldNorm(doc=4287)
        0.2 = coord(5/25)
    
  5. Smith, B.; Siebert, D.; Ceusters, W.: Was die philosophische Ontologie zur biomedizinischen Informatik beitragen kann (2004) 0.06
    0.061215933 = sum of:
      0.061215933 = product of:
        0.5101328 = sum of:
          0.051857673 = weight(abstract_txt:ergebnisse in 3182) [ClassicSimilarity], result of:
            0.051857673 = score(doc=3182,freq=2.0), product of:
              0.10655009 = queryWeight, product of:
                1.1899471 = boost
                5.506355 = idf(docFreq=466, maxDocs=42306)
                0.016261552 = queryNorm
              0.48669758 = fieldWeight in 3182, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                5.506355 = idf(docFreq=466, maxDocs=42306)
                0.0625 = fieldNorm(doc=3182)
          0.019327475 = weight(abstract_txt:werden in 3182) [ClassicSimilarity], result of:
            0.019327475 = score(doc=3182,freq=1.0), product of:
              0.087595515 = queryWeight, product of:
                1.5258318 = boost
                3.530313 = idf(docFreq=3368, maxDocs=42306)
                0.016261552 = queryNorm
              0.22064456 = fieldWeight in 3182, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                3.530313 = idf(docFreq=3368, maxDocs=42306)
                0.0625 = fieldNorm(doc=3182)
          0.43894765 = weight(abstract_txt:ontologie in 3182) [ClassicSimilarity], result of:
            0.43894765 = score(doc=3182,freq=5.0), product of:
              0.4108188 = queryWeight, product of:
                3.3043869 = boost
                7.645351 = idf(docFreq=54, maxDocs=42306)
                0.016261552 = queryNorm
              1.0684702 = fieldWeight in 3182, product of:
                2.236068 = tf(freq=5.0), with freq of:
                  5.0 = termFreq=5.0
                7.645351 = idf(docFreq=54, maxDocs=42306)
                0.0625 = fieldNorm(doc=3182)
        0.12 = coord(3/25)