Document (#43052)

Author

Mödden, E.

Title

Maschinelle Beschlagwortung mit Algorithmen : Ein Blick in die Werkstatt des KI-Projektes der Deutschen Nationalbibliothek

Source

B.I.T. Online. 27(2024) H.3, S.242- 253

Year

2024

Abstract

Die Deutsche Nationalbibliothek nutzt Künstliche Intelligenz (KI), um ihre Erschließungsprozesse zu optimieren. Ein Schwerpunkt liegt dabei auf der Integration innovativer Technologien für die Erschließung von Dokumenten mit der Gemeinsamen Normdatei. Das Forschungsprojekt "Automatisches Erschließungssystem - Inhaltserschließung von Publikationen mit KI" untersucht, wie KI-Lösungen die maschinelle Beschlagwortung von Publikationen verbessern können. Ziel des im Rahmen der Nationalen Strategie Künstliche Intelligenz geförderten Projekts ist es, die Qualität maschinell generierter Erschließungsdaten zu verbessern. Das KI-Projekt konzentriert sich auf deutschsprachige wissenschaftliche Online-Publikationen und strebt an, die entwickelten Werkzeuge als Open-Source-Software zur Verfügung zu stellen.

Theme

Automatisches Indexieren

Object

GND
Annif

Similar documents (content)

1. Aleksander, K.: Wie steht es um die geschlechtersensible Beschlagwortung in der Gemeinsamen Normdatei (2022) 0.23

   0.23043507 = sum of:
     0.23043507 = product of:
       1.4402193 = sum of:
         0.11064276 = weight(abstract_txt:inhaltserschließung in 1577) [ClassicSimilarity], result of:
           0.11064276 = score(doc=1577,freq=1.0), product of:
             0.12347027 = queryWeight, product of:
               1.0305228 = boost
               7.168868 = idf(docFreq=92, maxDocs=44421)
               0.016712992 = queryNorm
             0.8961085 = fieldWeight in 1577, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.168868 = idf(docFreq=92, maxDocs=44421)
               0.125 = fieldNorm(doc=1577)
         0.1453447 = weight(abstract_txt:normdatei in 1577) [ClassicSimilarity], result of:
           0.1453447 = score(doc=1577,freq=1.0), product of:
             0.1480971 = queryWeight, product of:
               1.128625 = boost
               7.85132 = idf(docFreq=46, maxDocs=44421)
               0.016712992 = queryNorm
             0.981415 = fieldWeight in 1577, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.85132 = idf(docFreq=46, maxDocs=44421)
               0.125 = fieldNorm(doc=1577)
         0.967343 = weight(title_txt:beschlagwortung in 1577) [ClassicSimilarity], result of:
           0.967343 = score(doc=1577,freq=1.0), product of:
             0.41590172 = queryWeight, product of:
               2.674772 = boost
               9.303573 = idf(docFreq=10, maxDocs=44421)
               0.016712992 = queryNorm
             2.3258932 = fieldWeight in 1577, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               9.303573 = idf(docFreq=10, maxDocs=44421)
               0.25 = fieldNorm(doc=1577)
         0.21688882 = weight(abstract_txt:publikationen in 1577) [ClassicSimilarity], result of:
           0.21688882 = score(doc=1577,freq=1.0), product of:
             0.27891952 = queryWeight, product of:
               2.682727 = boost
               6.2208285 = idf(docFreq=239, maxDocs=44421)
               0.016712992 = queryNorm
             0.77760357 = fieldWeight in 1577, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.2208285 = idf(docFreq=239, maxDocs=44421)
               0.125 = fieldNorm(doc=1577)
       0.16 = coord(4/25)
   

2. Junger, U.; Schwens, U.: ¬Die inhaltliche Erschließung des schriftlichen kulturellen Erbes auf dem Weg in die Zukunft : Automatische Vergabe von Schlagwörtern in der Deutschen Nationalbibliothek (2017) 0.20

   0.20217781 = sum of:
     0.20217781 = product of:
       0.7220636 = sum of:
         0.056345407 = weight(abstract_txt:algorithmen in 4780) [ClassicSimilarity], result of:
           0.056345407 = score(doc=4780,freq=1.0), product of:
             0.12498927 = queryWeight, product of:
               1.0368425 = boost
               7.212831 = idf(docFreq=88, maxDocs=44421)
               0.016712992 = queryNorm
             0.45080194 = fieldWeight in 4780, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.212831 = idf(docFreq=88, maxDocs=44421)
               0.0625 = fieldNorm(doc=4780)
         0.08294125 = weight(abstract_txt:maschinell in 4780) [ClassicSimilarity], result of:
           0.08294125 = score(doc=4780,freq=1.0), product of:
             0.16173875 = queryWeight, product of:
               1.1794606 = boost
               8.20496 = idf(docFreq=32, maxDocs=44421)
               0.016712992 = queryNorm
             0.51281 = fieldWeight in 4780, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.20496 = idf(docFreq=32, maxDocs=44421)
               0.0625 = fieldNorm(doc=4780)
         0.07793243 = weight(abstract_txt:intelligenz in 4780) [ClassicSimilarity], result of:
           0.07793243 = score(doc=4780,freq=1.0), product of:
             0.1954891 = queryWeight, product of:
               1.8338029 = boost
               6.3784575 = idf(docFreq=204, maxDocs=44421)
               0.016712992 = queryNorm
             0.3986536 = fieldWeight in 4780, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.3784575 = idf(docFreq=204, maxDocs=44421)
               0.0625 = fieldNorm(doc=4780)
         0.1364743 = weight(abstract_txt:nationalbibliothek in 4780) [ClassicSimilarity], result of:
           0.1364743 = score(doc=4780,freq=2.0), product of:
             0.22542442 = queryWeight, product of:
               1.9692093 = boost
               6.849437 = idf(docFreq=127, maxDocs=44421)
               0.016712992 = queryNorm
             0.60541046 = fieldWeight in 4780, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               6.849437 = idf(docFreq=127, maxDocs=44421)
               0.0625 = fieldNorm(doc=4780)
         0.103862636 = weight(abstract_txt:verbessern in 4780) [ClassicSimilarity], result of:
           0.103862636 = score(doc=4780,freq=1.0), product of:
             0.23674634 = queryWeight, product of:
               2.0180552 = boost
               7.019336 = idf(docFreq=107, maxDocs=44421)
               0.016712992 = queryNorm
             0.4387085 = fieldWeight in 4780, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.019336 = idf(docFreq=107, maxDocs=44421)
               0.0625 = fieldNorm(doc=4780)
         0.111144066 = weight(abstract_txt:künstliche in 4780) [ClassicSimilarity], result of:
           0.111144066 = score(doc=4780,freq=1.0), product of:
             0.24768588 = queryWeight, product of:
               2.0641537 = boost
               7.179679 = idf(docFreq=91, maxDocs=44421)
               0.016712992 = queryNorm
             0.44872993 = fieldWeight in 4780, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.179679 = idf(docFreq=91, maxDocs=44421)
               0.0625 = fieldNorm(doc=4780)
         0.15336354 = weight(abstract_txt:publikationen in 4780) [ClassicSimilarity], result of:
           0.15336354 = score(doc=4780,freq=2.0), product of:
             0.27891952 = queryWeight, product of:
               2.682727 = boost
               6.2208285 = idf(docFreq=239, maxDocs=44421)
               0.016712992 = queryNorm
             0.54984874 = fieldWeight in 4780, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               6.2208285 = idf(docFreq=239, maxDocs=44421)
               0.0625 = fieldNorm(doc=4780)
       0.28 = coord(7/25)
   

3. Henze, V.; Junger, U.; Mödden, E.: Grundzüge und erste Schritte der künftigen inhaltlichen Erschliessung von Publikationen in der Deutschen Nationalbibliothek (2017) 0.13

   0.12735371 = sum of:
     0.12735371 = product of:
       0.6367685 = sum of:
         0.08797248 = weight(abstract_txt:maschinell in 4772) [ClassicSimilarity], result of:
           0.08797248 = score(doc=4772,freq=2.0), product of:
             0.16173875 = queryWeight, product of:
               1.1794606 = boost
               8.20496 = idf(docFreq=32, maxDocs=44421)
               0.016712992 = queryNorm
             0.5439171 = fieldWeight in 4772, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               8.20496 = idf(docFreq=32, maxDocs=44421)
               0.046875 = fieldNorm(doc=4772)
         0.096684106 = weight(abstract_txt:erschließungsdaten in 4772) [ClassicSimilarity], result of:
           0.096684106 = score(doc=4772,freq=1.0), product of:
             0.21701825 = queryWeight, product of:
               1.3662323 = boost
               9.504243 = idf(docFreq=8, maxDocs=44421)
               0.016712992 = queryNorm
             0.4455114 = fieldWeight in 4772, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               9.504243 = idf(docFreq=8, maxDocs=44421)
               0.046875 = fieldNorm(doc=4772)
         0.14475285 = weight(abstract_txt:nationalbibliothek in 4772) [ClassicSimilarity], result of:
           0.14475285 = score(doc=4772,freq=4.0), product of:
             0.22542442 = queryWeight, product of:
               1.9692093 = boost
               6.849437 = idf(docFreq=127, maxDocs=44421)
               0.016712992 = queryNorm
             0.6421347 = fieldWeight in 4772, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               6.849437 = idf(docFreq=127, maxDocs=44421)
               0.046875 = fieldNorm(doc=4772)
         0.10813396 = weight(abstract_txt:maschinelle in 4772) [ClassicSimilarity], result of:
           0.10813396 = score(doc=4772,freq=1.0), product of:
             0.29460782 = queryWeight, product of:
               2.251197 = boost
               7.8302665 = idf(docFreq=47, maxDocs=44421)
               0.016712992 = queryNorm
             0.36704373 = fieldWeight in 4772, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.8302665 = idf(docFreq=47, maxDocs=44421)
               0.046875 = fieldNorm(doc=4772)
         0.19922511 = weight(abstract_txt:publikationen in 4772) [ClassicSimilarity], result of:
           0.19922511 = score(doc=4772,freq=6.0), product of:
             0.27891952 = queryWeight, product of:
               2.682727 = boost
               6.2208285 = idf(docFreq=239, maxDocs=44421)
               0.016712992 = queryNorm
             0.7142745 = fieldWeight in 4772, product of:
               2.4494898 = tf(freq=6.0), with freq of:
                 6.0 = termFreq=6.0
               6.2208285 = idf(docFreq=239, maxDocs=44421)
               0.046875 = fieldNorm(doc=4772)
       0.2 = coord(5/25)
   

4. Bense, H.: Finden ohne Suchen : automatische Benachrichtigungen über relevante wissenschaftliche Publikationen mit regelbasierter KI (2021) 0.11

   0.11489941 = sum of:
     0.11489941 = product of:
       0.71812135 = sum of:
         0.118851274 = weight(abstract_txt:nutzt in 1694) [ClassicSimilarity], result of:
           0.118851274 = score(doc=1694,freq=1.0), product of:
             0.14156121 = queryWeight, product of:
               1.1034396 = boost
               7.676116 = idf(docFreq=55, maxDocs=44421)
               0.016712992 = queryNorm
             0.8395752 = fieldWeight in 1694, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.676116 = idf(docFreq=55, maxDocs=44421)
               0.109375 = fieldNorm(doc=1694)
         0.13638176 = weight(abstract_txt:intelligenz in 1694) [ClassicSimilarity], result of:
           0.13638176 = score(doc=1694,freq=1.0), product of:
             0.1954891 = queryWeight, product of:
               1.8338029 = boost
               6.3784575 = idf(docFreq=204, maxDocs=44421)
               0.016712992 = queryNorm
             0.6976438 = fieldWeight in 1694, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.3784575 = idf(docFreq=204, maxDocs=44421)
               0.109375 = fieldNorm(doc=1694)
         0.19450212 = weight(abstract_txt:künstliche in 1694) [ClassicSimilarity], result of:
           0.19450212 = score(doc=1694,freq=1.0), product of:
             0.24768588 = queryWeight, product of:
               2.0641537 = boost
               7.179679 = idf(docFreq=91, maxDocs=44421)
               0.016712992 = queryNorm
             0.78527737 = fieldWeight in 1694, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.179679 = idf(docFreq=91, maxDocs=44421)
               0.109375 = fieldNorm(doc=1694)
         0.2683862 = weight(abstract_txt:publikationen in 1694) [ClassicSimilarity], result of:
           0.2683862 = score(doc=1694,freq=2.0), product of:
             0.27891952 = queryWeight, product of:
               2.682727 = boost
               6.2208285 = idf(docFreq=239, maxDocs=44421)
               0.016712992 = queryNorm
             0.9622353 = fieldWeight in 1694, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               6.2208285 = idf(docFreq=239, maxDocs=44421)
               0.109375 = fieldNorm(doc=1694)
       0.16 = coord(4/25)
   

5. Pollmeier, M.: Verlagsschlagwörter als Grundlage für den Einsatz eines maschinellen Verfahrens zur verbalen Erschließung der Kinder- und Jugendliteratur durch die Deutsche Nationalbibliothek : eine Datenanalyse (2019) 0.10

   0.10448837 = sum of:
     0.10448837 = product of:
       0.52244186 = sum of:
         0.095819436 = weight(abstract_txt:inhaltserschließung in 2083) [ClassicSimilarity], result of:
           0.095819436 = score(doc=2083,freq=3.0), product of:
             0.12347027 = queryWeight, product of:
               1.0305228 = boost
               7.168868 = idf(docFreq=92, maxDocs=44421)
               0.016712992 = queryNorm
             0.7760527 = fieldWeight in 2083, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               7.168868 = idf(docFreq=92, maxDocs=44421)
               0.0625 = fieldNorm(doc=2083)
         0.07267235 = weight(abstract_txt:normdatei in 2083) [ClassicSimilarity], result of:
           0.07267235 = score(doc=2083,freq=1.0), product of:
             0.1480971 = queryWeight, product of:
               1.128625 = boost
               7.85132 = idf(docFreq=46, maxDocs=44421)
               0.016712992 = queryNorm
             0.4907075 = fieldWeight in 2083, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.85132 = idf(docFreq=46, maxDocs=44421)
               0.0625 = fieldNorm(doc=2083)
         0.08294125 = weight(abstract_txt:maschinell in 2083) [ClassicSimilarity], result of:
           0.08294125 = score(doc=2083,freq=1.0), product of:
             0.16173875 = queryWeight, product of:
               1.1794606 = boost
               8.20496 = idf(docFreq=32, maxDocs=44421)
               0.016712992 = queryNorm
             0.51281 = fieldWeight in 2083, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.20496 = idf(docFreq=32, maxDocs=44421)
               0.0625 = fieldNorm(doc=2083)
         0.16714619 = weight(abstract_txt:nationalbibliothek in 2083) [ClassicSimilarity], result of:
           0.16714619 = score(doc=2083,freq=3.0), product of:
             0.22542442 = queryWeight, product of:
               1.9692093 = boost
               6.849437 = idf(docFreq=127, maxDocs=44421)
               0.016712992 = queryNorm
             0.7414733 = fieldWeight in 2083, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               6.849437 = idf(docFreq=127, maxDocs=44421)
               0.0625 = fieldNorm(doc=2083)
         0.103862636 = weight(abstract_txt:verbessern in 2083) [ClassicSimilarity], result of:
           0.103862636 = score(doc=2083,freq=1.0), product of:
             0.23674634 = queryWeight, product of:
               2.0180552 = boost
               7.019336 = idf(docFreq=107, maxDocs=44421)
               0.016712992 = queryNorm
             0.4387085 = fieldWeight in 2083, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.019336 = idf(docFreq=107, maxDocs=44421)
               0.0625 = fieldNorm(doc=2083)
       0.2 = coord(5/25)