Document (#43372)

Author

Sack, H.

Title

Hybride Künstliche Intelligenz in der automatisierten Inhaltserschließung

Source

Qualität in der Inhaltserschließung. Hrsg.: M. Franke-Maier, u.a

Imprint

München : DeGruyter-Saur

Year

2021

Pages

S.387-405

Series

Bibliotheks- und Informationspraxis; 70

Abstract

Effizienter (Online-)Zugang zu Bibliotheks- und Archivmaterialien erfordert eine qualitativ hinreichende inhaltliche Erschließung dieser Dokumente. Die passgenaue Verschlagwortung und Kategorisierung dieser unstrukturierten Dokumente ermöglichen einen strukturell gegliederten Zugang sowohl in der analogen als auch in der digitalen Welt. Darüber hinaus erweitert eine vollständige Transkription der Dokumente den Zugang über die Möglichkeiten der Volltextsuche. Angesichts der in jüngster Zeit erzielten spektakulären Erfolge der Künstlichen Intelligenz liegt die Schlussfolgerung nahe, dass auch das Problem der automatisierten Inhaltserschließung für Bibliotheken und Archive als mehr oder weniger gelöst anzusehen wäre. Allerdings lassen sich die oftmals nur in thematisch engen Teilbereichen erzielten Erfolge nicht immer problemlos verallgemeinern oder in einen neuen Kontext übertragen. Das Ziel der vorliegenden Darstellung liegt in der Diskussion des aktuellen Stands der Technik der automatisierten inhaltlichen Erschließung anhand ausgewählter Beispiele sowie möglicher Fortschritte und Prognosen basierend auf aktuellen Entwicklungen des maschinellen Lernens und der Künstlichen Intelligenz einschließlich deren Kritik.

Theme

Automatisches Indexieren

Similar documents (content)

1. Kasprzik, A.: Automatisierte und semiautomatisierte Klassifizierung : eine Analyse aktueller Projekte (2014) 0.17

   0.17358479 = sum of:
     0.17358479 = product of:
       0.72327 = sum of:
         0.02542246 = weight(abstract_txt:dieser in 4468) [ClassicSimilarity], result of:
           0.02542246 = score(doc=4468,freq=1.0), product of:
             0.074156724 = queryWeight, product of:
               1.0103774 = boost
               4.388105 = idf(docFreq=1470, maxDocs=43556)
               0.016725916 = queryNorm
             0.3428207 = fieldWeight in 4468, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.388105 = idf(docFreq=1470, maxDocs=43556)
               0.078125 = fieldNorm(doc=4468)
         0.07047717 = weight(abstract_txt:aktuellen in 4468) [ClassicSimilarity], result of:
           0.07047717 = score(doc=4468,freq=1.0), product of:
             0.14634272 = queryWeight, product of:
               1.4193645 = boost
               6.16435 = idf(docFreq=248, maxDocs=43556)
               0.016725916 = queryNorm
             0.48158985 = fieldWeight in 4468, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.16435 = idf(docFreq=248, maxDocs=43556)
               0.078125 = fieldNorm(doc=4468)
         0.114703804 = weight(abstract_txt:künstlichen in 4468) [ClassicSimilarity], result of:
           0.114703804 = score(doc=4468,freq=1.0), product of:
             0.20248401 = queryWeight, product of:
               1.6695665 = boost
               7.250986 = idf(docFreq=83, maxDocs=43556)
               0.016725916 = queryNorm
             0.56648326 = fieldWeight in 4468, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.250986 = idf(docFreq=83, maxDocs=43556)
               0.078125 = fieldNorm(doc=4468)
         0.110546656 = weight(abstract_txt:dokumente in 4468) [ClassicSimilarity], result of:
           0.110546656 = score(doc=4468,freq=1.0), product of:
             0.22615159 = queryWeight, product of:
               2.1609952 = boost
               6.2568526 = idf(docFreq=226, maxDocs=43556)
               0.016725916 = queryNorm
             0.48881662 = fieldWeight in 4468, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.2568526 = idf(docFreq=226, maxDocs=43556)
               0.078125 = fieldNorm(doc=4468)
         0.12459044 = weight(abstract_txt:intelligenz in 4468) [ClassicSimilarity], result of:
           0.12459044 = score(doc=4468,freq=1.0), product of:
             0.24492083 = queryWeight, product of:
               2.248883 = boost
               6.5113187 = idf(docFreq=175, maxDocs=43556)
               0.016725916 = queryNorm
             0.5086968 = fieldWeight in 4468, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.5113187 = idf(docFreq=175, maxDocs=43556)
               0.078125 = fieldNorm(doc=4468)
         0.27752948 = weight(abstract_txt:automatisierten in 4468) [ClassicSimilarity], result of:
           0.27752948 = score(doc=4468,freq=1.0), product of:
             0.4177425 = queryWeight, product of:
               2.9370296 = boost
               8.503749 = idf(docFreq=23, maxDocs=43556)
               0.016725916 = queryNorm
             0.6643554 = fieldWeight in 4468, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.503749 = idf(docFreq=23, maxDocs=43556)
               0.078125 = fieldNorm(doc=4468)
       0.24 = coord(6/25)
   

2. Voß, J.: Datenqualität als Grundlage qualitativer Inhaltserschließung (2021) 0.13

   0.12794596 = sum of:
     0.12794596 = product of:
       0.79966223 = sum of:
         0.020337967 = weight(abstract_txt:dieser in 2657) [ClassicSimilarity], result of:
           0.020337967 = score(doc=2657,freq=1.0), product of:
             0.074156724 = queryWeight, product of:
               1.0103774 = boost
               4.388105 = idf(docFreq=1470, maxDocs=43556)
               0.016725916 = queryNorm
             0.27425656 = fieldWeight in 2657, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.388105 = idf(docFreq=1470, maxDocs=43556)
               0.0625 = fieldNorm(doc=2657)
         0.070615806 = weight(abstract_txt:erschließung in 2657) [ClassicSimilarity], result of:
           0.070615806 = score(doc=2657,freq=2.0), product of:
             0.1349595 = queryWeight, product of:
               1.3630447 = boost
               5.919751 = idf(docFreq=317, maxDocs=43556)
               0.016725916 = queryNorm
             0.523237 = fieldWeight in 2657, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               5.919751 = idf(docFreq=317, maxDocs=43556)
               0.0625 = fieldNorm(doc=2657)
         0.07260026 = weight(abstract_txt:liegt in 2657) [ClassicSimilarity], result of:
           0.07260026 = score(doc=2657,freq=2.0), product of:
             0.13747624 = queryWeight, product of:
               1.3756951 = boost
               5.9746923 = idf(docFreq=300, maxDocs=43556)
               0.016725916 = queryNorm
             0.52809316 = fieldWeight in 2657, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               5.9746923 = idf(docFreq=300, maxDocs=43556)
               0.0625 = fieldNorm(doc=2657)
         0.63610816 = weight(title_txt:inhaltserschließung in 2657) [ClassicSimilarity], result of:
           0.63610816 = score(doc=2657,freq=1.0), product of:
             0.20117196 = queryWeight, product of:
               1.6641486 = boost
               7.2274556 = idf(docFreq=85, maxDocs=43556)
               0.016725916 = queryNorm
             3.1620119 = fieldWeight in 2657, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.2274556 = idf(docFreq=85, maxDocs=43556)
               0.4375 = fieldNorm(doc=2657)
       0.16 = coord(4/25)
   

3. Lohmann, H.: KASCADE: Dokumentanreicherung und automatische Inhaltserschließung : Projektbericht und Ergebnisse des Retrievaltests (2000) 0.09

   0.09287696 = sum of:
     0.09287696 = product of:
       0.58048105 = sum of:
         0.01271123 = weight(abstract_txt:dieser in 2492) [ClassicSimilarity], result of:
           0.01271123 = score(doc=2492,freq=1.0), product of:
             0.074156724 = queryWeight, product of:
               1.0103774 = boost
               4.388105 = idf(docFreq=1470, maxDocs=43556)
               0.016725916 = queryNorm
             0.17141035 = fieldWeight in 2492, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.388105 = idf(docFreq=1470, maxDocs=43556)
               0.0390625 = fieldNorm(doc=2492)
         0.035238586 = weight(abstract_txt:aktuellen in 2492) [ClassicSimilarity], result of:
           0.035238586 = score(doc=2492,freq=1.0), product of:
             0.14634272 = queryWeight, product of:
               1.4193645 = boost
               6.16435 = idf(docFreq=248, maxDocs=43556)
               0.016725916 = queryNorm
             0.24079493 = fieldWeight in 2492, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.16435 = idf(docFreq=248, maxDocs=43556)
               0.0390625 = fieldNorm(doc=2492)
         0.45436296 = weight(title_txt:inhaltserschließung in 2492) [ClassicSimilarity], result of:
           0.45436296 = score(doc=2492,freq=1.0), product of:
             0.20117196 = queryWeight, product of:
               1.6641486 = boost
               7.2274556 = idf(docFreq=85, maxDocs=43556)
               0.016725916 = queryNorm
             2.25858 = fieldWeight in 2492, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.2274556 = idf(docFreq=85, maxDocs=43556)
               0.3125 = fieldNorm(doc=2492)
         0.07816829 = weight(abstract_txt:dokumente in 2492) [ClassicSimilarity], result of:
           0.07816829 = score(doc=2492,freq=2.0), product of:
             0.22615159 = queryWeight, product of:
               2.1609952 = boost
               6.2568526 = idf(docFreq=226, maxDocs=43556)
               0.016725916 = queryNorm
             0.34564555 = fieldWeight in 2492, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               6.2568526 = idf(docFreq=226, maxDocs=43556)
               0.0390625 = fieldNorm(doc=2492)
       0.16 = coord(4/25)
   

4. Groß, T.; Faden, M.: Automatische Indexierung elektronischer Dokumente an der Deutschen Zentralbibliothek für Wirtschaftswissenschaften : Bericht über die Jahrestagung der Internationalen Buchwissenschaftlichen Gesellschaft (2010) 0.09

   0.08653717 = sum of:
     0.08653717 = product of:
       0.36057153 = sum of:
         0.015253475 = weight(abstract_txt:dieser in 1049) [ClassicSimilarity], result of:
           0.015253475 = score(doc=1049,freq=1.0), product of:
             0.074156724 = queryWeight, product of:
               1.0103774 = boost
               4.388105 = idf(docFreq=1470, maxDocs=43556)
               0.016725916 = queryNorm
             0.20569241 = fieldWeight in 1049, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.388105 = idf(docFreq=1470, maxDocs=43556)
               0.046875 = fieldNorm(doc=1049)
         0.03744969 = weight(abstract_txt:erschließung in 1049) [ClassicSimilarity], result of:
           0.03744969 = score(doc=1049,freq=1.0), product of:
             0.1349595 = queryWeight, product of:
               1.3630447 = boost
               5.919751 = idf(docFreq=317, maxDocs=43556)
               0.016725916 = queryNorm
             0.27748835 = fieldWeight in 1049, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.919751 = idf(docFreq=317, maxDocs=43556)
               0.046875 = fieldNorm(doc=1049)
         0.042286303 = weight(abstract_txt:aktuellen in 1049) [ClassicSimilarity], result of:
           0.042286303 = score(doc=1049,freq=1.0), product of:
             0.14634272 = queryWeight, product of:
               1.4193645 = boost
               6.16435 = idf(docFreq=248, maxDocs=43556)
               0.016725916 = queryNorm
             0.2889539 = fieldWeight in 1049, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.16435 = idf(docFreq=248, maxDocs=43556)
               0.046875 = fieldNorm(doc=1049)
         0.13679582 = weight(abstract_txt:erzielten in 1049) [ClassicSimilarity], result of:
           0.13679582 = score(doc=1049,freq=1.0), product of:
             0.32010067 = queryWeight, product of:
               2.0991895 = boost
               9.116854 = idf(docFreq=12, maxDocs=43556)
               0.016725916 = queryNorm
             0.42735252 = fieldWeight in 1049, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               9.116854 = idf(docFreq=12, maxDocs=43556)
               0.046875 = fieldNorm(doc=1049)
         0.06245827 = weight(abstract_txt:zugang in 1049) [ClassicSimilarity], result of:
           0.06245827 = score(doc=1049,freq=1.0), product of:
             0.21726765 = queryWeight, product of:
               2.1181247 = boost
               6.1327267 = idf(docFreq=256, maxDocs=43556)
               0.016725916 = queryNorm
             0.28747156 = fieldWeight in 1049, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.1327267 = idf(docFreq=256, maxDocs=43556)
               0.046875 = fieldNorm(doc=1049)
         0.06632799 = weight(abstract_txt:dokumente in 1049) [ClassicSimilarity], result of:
           0.06632799 = score(doc=1049,freq=1.0), product of:
             0.22615159 = queryWeight, product of:
               2.1609952 = boost
               6.2568526 = idf(docFreq=226, maxDocs=43556)
               0.016725916 = queryNorm
             0.29328996 = fieldWeight in 1049, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.2568526 = idf(docFreq=226, maxDocs=43556)
               0.046875 = fieldNorm(doc=1049)
       0.24 = coord(6/25)
   

5. Kempf, A.O.: Automatische Inhaltserschließung in der Fachinformation (2013) 0.08

   0.08476549 = sum of:
     0.08476549 = product of:
       0.70637906 = sum of:
         0.020337967 = weight(abstract_txt:dieser in 2903) [ClassicSimilarity], result of:
           0.020337967 = score(doc=2903,freq=1.0), product of:
             0.074156724 = queryWeight, product of:
               1.0103774 = boost
               4.388105 = idf(docFreq=1470, maxDocs=43556)
               0.016725916 = queryNorm
             0.27425656 = fieldWeight in 2903, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.388105 = idf(docFreq=1470, maxDocs=43556)
               0.0625 = fieldNorm(doc=2903)
         0.04993292 = weight(abstract_txt:erschließung in 2903) [ClassicSimilarity], result of:
           0.04993292 = score(doc=2903,freq=1.0), product of:
             0.1349595 = queryWeight, product of:
               1.3630447 = boost
               5.919751 = idf(docFreq=317, maxDocs=43556)
               0.016725916 = queryNorm
             0.36998445 = fieldWeight in 2903, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.919751 = idf(docFreq=317, maxDocs=43556)
               0.0625 = fieldNorm(doc=2903)
         0.63610816 = weight(title_txt:inhaltserschließung in 2903) [ClassicSimilarity], result of:
           0.63610816 = score(doc=2903,freq=1.0), product of:
             0.20117196 = queryWeight, product of:
               1.6641486 = boost
               7.2274556 = idf(docFreq=85, maxDocs=43556)
               0.016725916 = queryNorm
             3.1620119 = fieldWeight in 2903, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.2274556 = idf(docFreq=85, maxDocs=43556)
               0.4375 = fieldNorm(doc=2903)
       0.12 = coord(3/25)