-
Bager, J.: ¬Die Text-KI ChatGPT schreibt Fachtexte, Prosa, Gedichte und Programmcode (2023)
0.03
0.025105907 = product of:
0.08787067 = sum of:
0.02733519 = weight(_text_:j in 835) [ClassicSimilarity], result of:
0.02733519 = score(doc=835,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.28085366 = fieldWeight in 835, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.0625 = fieldNorm(doc=835)
0.060535483 = sum of:
0.02733519 = weight(_text_:j in 835) [ClassicSimilarity], result of:
0.02733519 = score(doc=835,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.28085366 = fieldWeight in 835, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.0625 = fieldNorm(doc=835)
0.033200294 = weight(_text_:22 in 835) [ClassicSimilarity], result of:
0.033200294 = score(doc=835,freq=2.0), product of:
0.10726349 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.030630698 = queryNorm
0.30952093 = fieldWeight in 835, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.0625 = fieldNorm(doc=835)
0.2857143 = coord(2/7)
- Date
- 29.12.2022 18:22:55
-
Dietze, J.: Einführung in die Informationslinguistik : die linguistische Datenverarbeitung in der Informationswissenschaft (1989)
0.02
0.020501394 = product of:
0.07175487 = sum of:
0.04783658 = weight(_text_:j in 5084) [ClassicSimilarity], result of:
0.04783658 = score(doc=5084,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.4914939 = fieldWeight in 5084, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.109375 = fieldNorm(doc=5084)
0.02391829 = product of:
0.04783658 = sum of:
0.04783658 = weight(_text_:j in 5084) [ClassicSimilarity], result of:
0.04783658 = score(doc=5084,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.4914939 = fieldWeight in 5084, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.109375 = fieldNorm(doc=5084)
0.5 = coord(1/2)
0.2857143 = coord(2/7)
-
Inhaltserschließung von Massendaten : zur Wirksamkeit informationslinguistischer Verfahren am Beispiel des deutschen Patentinformationssystems (1987)
0.02
0.020501394 = product of:
0.07175487 = sum of:
0.04783658 = weight(_text_:j in 6764) [ClassicSimilarity], result of:
0.04783658 = score(doc=6764,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.4914939 = fieldWeight in 6764, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.109375 = fieldNorm(doc=6764)
0.02391829 = product of:
0.04783658 = sum of:
0.04783658 = weight(_text_:j in 6764) [ClassicSimilarity], result of:
0.04783658 = score(doc=6764,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.4914939 = fieldWeight in 6764, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.109375 = fieldNorm(doc=6764)
0.5 = coord(1/2)
0.2857143 = coord(2/7)
- Editor
- Krause, J.
-
Krause, J.: Mensch-Maschine-Interaktion in natürlicher Sprache : Evaluierungsstudien zu praxisorientierten Frage-Antwort-Systemen und ihre Methodik (1982)
0.02
0.020501394 = product of:
0.07175487 = sum of:
0.04783658 = weight(_text_:j in 8964) [ClassicSimilarity], result of:
0.04783658 = score(doc=8964,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.4914939 = fieldWeight in 8964, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.109375 = fieldNorm(doc=8964)
0.02391829 = product of:
0.04783658 = sum of:
0.04783658 = weight(_text_:j in 8964) [ClassicSimilarity], result of:
0.04783658 = score(doc=8964,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.4914939 = fieldWeight in 8964, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.109375 = fieldNorm(doc=8964)
0.5 = coord(1/2)
0.2857143 = coord(2/7)
-
Meyer, J.: ¬Die Verwendung hierarchisch strukturierter Sprachnetzwerke zur redundanzarmen Codierung von Texten (1989)
0.02
0.020501394 = product of:
0.07175487 = sum of:
0.04783658 = weight(_text_:j in 2176) [ClassicSimilarity], result of:
0.04783658 = score(doc=2176,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.4914939 = fieldWeight in 2176, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.109375 = fieldNorm(doc=2176)
0.02391829 = product of:
0.04783658 = sum of:
0.04783658 = weight(_text_:j in 2176) [ClassicSimilarity], result of:
0.04783658 = score(doc=2176,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.4914939 = fieldWeight in 2176, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.109375 = fieldNorm(doc=2176)
0.5 = coord(1/2)
0.2857143 = coord(2/7)
-
Dietze, J.: Texterschließung : lexikalische Semantik und Wissensrepräsentation (1994)
0.02
0.020501394 = product of:
0.07175487 = sum of:
0.04783658 = weight(_text_:j in 2822) [ClassicSimilarity], result of:
0.04783658 = score(doc=2822,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.4914939 = fieldWeight in 2822, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.109375 = fieldNorm(doc=2822)
0.02391829 = product of:
0.04783658 = sum of:
0.04783658 = weight(_text_:j in 2822) [ClassicSimilarity], result of:
0.04783658 = score(doc=2822,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.4914939 = fieldWeight in 2822, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.109375 = fieldNorm(doc=2822)
0.5 = coord(1/2)
0.2857143 = coord(2/7)
-
Krause, J.: Principles of content analysis for information retrieval systems : an overview (1996)
0.02
0.020501394 = product of:
0.07175487 = sum of:
0.04783658 = weight(_text_:j in 5270) [ClassicSimilarity], result of:
0.04783658 = score(doc=5270,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.4914939 = fieldWeight in 5270, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.109375 = fieldNorm(doc=5270)
0.02391829 = product of:
0.04783658 = sum of:
0.04783658 = weight(_text_:j in 5270) [ClassicSimilarity], result of:
0.04783658 = score(doc=5270,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.4914939 = fieldWeight in 5270, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.109375 = fieldNorm(doc=5270)
0.5 = coord(1/2)
0.2857143 = coord(2/7)
-
Gräbnitz, V.: PASSAT: Programm zur automatischen Selektion von Stichwörtern aus Texten (1987)
0.02
0.017572623 = product of:
0.061504178 = sum of:
0.041002784 = weight(_text_:j in 932) [ClassicSimilarity], result of:
0.041002784 = score(doc=932,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.4212805 = fieldWeight in 932, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.09375 = fieldNorm(doc=932)
0.020501392 = product of:
0.041002784 = sum of:
0.041002784 = weight(_text_:j in 932) [ClassicSimilarity], result of:
0.041002784 = score(doc=932,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.4212805 = fieldWeight in 932, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.09375 = fieldNorm(doc=932)
0.5 = coord(1/2)
0.2857143 = coord(2/7)
- Source
- Inhaltserschließung von Massendaten zur Wirksamkeit informationslinguistischer Verfahren am Beispiel des Deutschen Patentinformationssystems. Hrsg. J. Krause
-
Krause, J.: Was leisten informationslinguistische Komponenten von Referenz-Retrievalsystemen für Massendaten? : Von der 'Pragmatik im Computer' zur Pragmatikanalyse als Designgrundlage (1986)
0.02
0.017572623 = product of:
0.061504178 = sum of:
0.041002784 = weight(_text_:j in 7395) [ClassicSimilarity], result of:
0.041002784 = score(doc=7395,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.4212805 = fieldWeight in 7395, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.09375 = fieldNorm(doc=7395)
0.020501392 = product of:
0.041002784 = sum of:
0.041002784 = weight(_text_:j in 7395) [ClassicSimilarity], result of:
0.041002784 = score(doc=7395,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.4212805 = fieldWeight in 7395, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.09375 = fieldNorm(doc=7395)
0.5 = coord(1/2)
0.2857143 = coord(2/7)
-
Sonnenberger, G.: Automatische Wissensakquisition aus Texten : Textparsing (1990)
0.02
0.017572623 = product of:
0.061504178 = sum of:
0.041002784 = weight(_text_:j in 8428) [ClassicSimilarity], result of:
0.041002784 = score(doc=8428,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.4212805 = fieldWeight in 8428, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.09375 = fieldNorm(doc=8428)
0.020501392 = product of:
0.041002784 = sum of:
0.041002784 = weight(_text_:j in 8428) [ClassicSimilarity], result of:
0.041002784 = score(doc=8428,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.4212805 = fieldWeight in 8428, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.09375 = fieldNorm(doc=8428)
0.5 = coord(1/2)
0.2857143 = coord(2/7)
- Source
- Pragmatische Aspekte beim Entwurf und Betrieb von Informationssystemen: Proc. 1. Int. Symposiums für Informationswissenschaft, Universität Konstanz, 17.-19.10.1990. Hrsg.: J. Herget u. R. Kuhlen
-
Rolland, M.T.: Sprachverarbeitung durch Logotechnik : Sprachtheorie, Methodik, Anwendungen (1994)
0.02
0.017572623 = product of:
0.061504178 = sum of:
0.041002784 = weight(_text_:j in 5365) [ClassicSimilarity], result of:
0.041002784 = score(doc=5365,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.4212805 = fieldWeight in 5365, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.09375 = fieldNorm(doc=5365)
0.020501392 = product of:
0.041002784 = sum of:
0.041002784 = weight(_text_:j in 5365) [ClassicSimilarity], result of:
0.041002784 = score(doc=5365,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.4212805 = fieldWeight in 5365, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.09375 = fieldNorm(doc=5365)
0.5 = coord(1/2)
0.2857143 = coord(2/7)
- Footnote
- Rez. in: Nachrichten für Dokumentation 46(1995) H.2, S.130-132 (E. Lutterbeck); Knowledge organization 23(1996) no.3, S.147-156 (Ausführliche Rezension als eigener Beitrag von J. Heinrichs)
-
Rapke, K.: Automatische Indexierung von Volltexten für die Gruner+Jahr Pressedatenbank (2001)
0.02
0.017572623 = product of:
0.061504178 = sum of:
0.041002784 = weight(_text_:j in 6386) [ClassicSimilarity], result of:
0.041002784 = score(doc=6386,freq=8.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.4212805 = fieldWeight in 6386, product of:
2.828427 = tf(freq=8.0), with freq of:
8.0 = termFreq=8.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.046875 = fieldNorm(doc=6386)
0.020501392 = product of:
0.041002784 = sum of:
0.041002784 = weight(_text_:j in 6386) [ClassicSimilarity], result of:
0.041002784 = score(doc=6386,freq=8.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.4212805 = fieldWeight in 6386, product of:
2.828427 = tf(freq=8.0), with freq of:
8.0 = termFreq=8.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.046875 = fieldNorm(doc=6386)
0.5 = coord(1/2)
0.2857143 = coord(2/7)
- Abstract
- Retrieval Tests sind die anerkannteste Methode, um neue Verfahren der Inhaltserschließung gegenüber traditionellen Verfahren zu rechtfertigen. Im Rahmen einer Diplomarbeit wurden zwei grundsätzlich unterschiedliche Systeme der automatischen inhaltlichen Erschließung anhand der Pressedatenbank des Verlagshauses Gruner + Jahr (G+J) getestet und evaluiert. Untersucht wurde dabei natürlichsprachliches Retrieval im Vergleich zu Booleschem Retrieval. Bei den beiden Systemen handelt es sich zum einen um Autonomy von Autonomy Inc. und DocCat, das von IBM an die Datenbankstruktur der G+J Pressedatenbank angepasst wurde. Ersteres ist ein auf natürlichsprachlichem Retrieval basierendes, probabilistisches System. DocCat demgegenüber basiert auf Booleschem Retrieval und ist ein lernendes System, das auf Grund einer intellektuell erstellten Trainingsvorlage indexiert. Methodisch geht die Evaluation vom realen Anwendungskontext der Textdokumentation von G+J aus. Die Tests werden sowohl unter statistischen wie auch qualitativen Gesichtspunkten bewertet. Ein Ergebnis der Tests ist, dass DocCat einige Mängel gegenüber der intellektuellen Inhaltserschließung aufweist, die noch behoben werden müssen, während das natürlichsprachliche Retrieval von Autonomy in diesem Rahmen und für die speziellen Anforderungen der G+J Textdokumentation so nicht einsetzbar ist
-
Ludwig, B.; Reischer, J.: Informationslinguistik in Regensburg (2012)
0.02
0.016567627 = product of:
0.05798669 = sum of:
0.038657796 = weight(_text_:j in 555) [ClassicSimilarity], result of:
0.038657796 = score(doc=555,freq=4.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.39718705 = fieldWeight in 555, product of:
2.0 = tf(freq=4.0), with freq of:
4.0 = termFreq=4.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.0625 = fieldNorm(doc=555)
0.019328898 = product of:
0.038657796 = sum of:
0.038657796 = weight(_text_:j in 555) [ClassicSimilarity], result of:
0.038657796 = score(doc=555,freq=4.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.39718705 = fieldWeight in 555, product of:
2.0 = tf(freq=4.0), with freq of:
4.0 = termFreq=4.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.0625 = fieldNorm(doc=555)
0.5 = coord(1/2)
0.2857143 = coord(2/7)
- Content
- Vgl.: http://www.degruyter.com/view/j/iwp.2012.63.issue-5/iwp-2012-0065/iwp-2012-0065.xml?format=INT.
-
Sienel, J.; Weiss, M.; Laube, M.: Sprachtechnologien für die Informationsgesellschaft des 21. Jahrhunderts (2000)
0.02
0.015691191 = product of:
0.05491917 = sum of:
0.017084492 = weight(_text_:j in 5557) [ClassicSimilarity], result of:
0.017084492 = score(doc=5557,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.17553353 = fieldWeight in 5557, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.0390625 = fieldNorm(doc=5557)
0.037834678 = sum of:
0.017084492 = weight(_text_:j in 5557) [ClassicSimilarity], result of:
0.017084492 = score(doc=5557,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.17553353 = fieldWeight in 5557, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.0390625 = fieldNorm(doc=5557)
0.020750185 = weight(_text_:22 in 5557) [ClassicSimilarity], result of:
0.020750185 = score(doc=5557,freq=2.0), product of:
0.10726349 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.030630698 = queryNorm
0.19345059 = fieldWeight in 5557, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.0390625 = fieldNorm(doc=5557)
0.2857143 = coord(2/7)
- Date
- 26.12.2000 13:22:17
-
Rapke, K.: Automatische Indexierung von Volltexten für die Gruner+Jahr Pressedatenbank (2001)
0.01
0.014643851 = product of:
0.051253475 = sum of:
0.034168985 = weight(_text_:j in 5863) [ClassicSimilarity], result of:
0.034168985 = score(doc=5863,freq=8.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.35106707 = fieldWeight in 5863, product of:
2.828427 = tf(freq=8.0), with freq of:
8.0 = termFreq=8.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.0390625 = fieldNorm(doc=5863)
0.017084492 = product of:
0.034168985 = sum of:
0.034168985 = weight(_text_:j in 5863) [ClassicSimilarity], result of:
0.034168985 = score(doc=5863,freq=8.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.35106707 = fieldWeight in 5863, product of:
2.828427 = tf(freq=8.0), with freq of:
8.0 = termFreq=8.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.0390625 = fieldNorm(doc=5863)
0.5 = coord(1/2)
0.2857143 = coord(2/7)
- Abstract
- Retrievaltests sind die anerkannteste Methode, um neue Verfahren der Inhaltserschließung gegenüber traditionellen Verfahren zu rechtfertigen. Im Rahmen einer Diplomarbeit wurden zwei grundsätzlich unterschiedliche Systeme der automatischen inhaltlichen Erschließung anhand der Pressedatenbank des Verlagshauses Gruner + Jahr (G+J) getestet und evaluiert. Untersucht wurde dabei natürlichsprachliches Retrieval im Vergleich zu Booleschem Retrieval. Bei den beiden Systemen handelt es sich zum einen um Autonomy von Autonomy Inc. und DocCat, das von IBM an die Datenbankstruktur der G+J Pressedatenbank angepasst wurde. Ersteres ist ein auf natürlichsprachlichem Retrieval basierendes, probabilistisches System. DocCat demgegenüber basiert auf Booleschem Retrieval und ist ein lernendes System, das aufgrund einer intellektuell erstellten Trainingsvorlage indexiert. Methodisch geht die Evaluation vom realen Anwendungskontext der Textdokumentation von G+J aus. Die Tests werden sowohl unter statistischen wie auch qualitativen Gesichtspunkten bewertet. Ein Ergebnis der Tests ist, dass DocCat einige Mängel gegenüber der intellektuellen Inhaltserschließung aufweist, die noch behoben werden müssen, während das natürlichsprachliche Retrieval von Autonomy in diesem Rahmen und für die speziellen Anforderungen der G+J Textdokumentation so nicht einsetzbar ist
-
Barthel, J.; Ciesielski, R.: Regeln zu ChatGPT an Unis oft unklar : KI in der Bildung (2023)
0.01
0.014643851 = product of:
0.051253475 = sum of:
0.034168985 = weight(_text_:j in 925) [ClassicSimilarity], result of:
0.034168985 = score(doc=925,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.35106707 = fieldWeight in 925, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.078125 = fieldNorm(doc=925)
0.017084492 = product of:
0.034168985 = sum of:
0.034168985 = weight(_text_:j in 925) [ClassicSimilarity], result of:
0.034168985 = score(doc=925,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.35106707 = fieldWeight in 925, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.078125 = fieldNorm(doc=925)
0.5 = coord(1/2)
0.2857143 = coord(2/7)
-
Janssen, J.-K.: ChatGPT-Klon läuft lokal auf jedem Rechner : Alpaca/LLaMA ausprobiert (2023)
0.01
0.014643851 = product of:
0.051253475 = sum of:
0.034168985 = weight(_text_:j in 927) [ClassicSimilarity], result of:
0.034168985 = score(doc=927,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.35106707 = fieldWeight in 927, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.078125 = fieldNorm(doc=927)
0.017084492 = product of:
0.034168985 = sum of:
0.034168985 = weight(_text_:j in 927) [ClassicSimilarity], result of:
0.034168985 = score(doc=927,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.35106707 = fieldWeight in 927, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.078125 = fieldNorm(doc=927)
0.5 = coord(1/2)
0.2857143 = coord(2/7)
-
Dietze, J.; Völkel, H.: Verifikation einer Methode der lexikalischen Semantik : zur computergestützten Bestimmung der semantischen Konsistenz und des semantischen Abstands (1992)
0.01
0.0117150815 = product of:
0.041002784 = sum of:
0.02733519 = weight(_text_:j in 6680) [ClassicSimilarity], result of:
0.02733519 = score(doc=6680,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.28085366 = fieldWeight in 6680, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.0625 = fieldNorm(doc=6680)
0.013667595 = product of:
0.02733519 = sum of:
0.02733519 = weight(_text_:j in 6680) [ClassicSimilarity], result of:
0.02733519 = score(doc=6680,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.28085366 = fieldWeight in 6680, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.0625 = fieldNorm(doc=6680)
0.5 = coord(1/2)
0.2857143 = coord(2/7)
-
Lehrndorfer, A.: Kontrolliertes Deutsch : Linguistische und sprachpsychologische Leitlinien für eine (maschinell) kontrollierte Sprache in der Technischen Dokumentation (1996)
0.01
0.0117150815 = product of:
0.041002784 = sum of:
0.02733519 = weight(_text_:j in 2039) [ClassicSimilarity], result of:
0.02733519 = score(doc=2039,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.28085366 = fieldWeight in 2039, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.0625 = fieldNorm(doc=2039)
0.013667595 = product of:
0.02733519 = sum of:
0.02733519 = weight(_text_:j in 2039) [ClassicSimilarity], result of:
0.02733519 = score(doc=2039,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.28085366 = fieldWeight in 2039, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.0625 = fieldNorm(doc=2039)
0.5 = coord(1/2)
0.2857143 = coord(2/7)
- Footnote
- Rez. in: Knowledge organization 25(1998) nos.1/2, S.51-52 (J. Heinrichs)
-
Bager, J.: Teurer Dolmetscher : Forschungsprojekt Verbmobil - Rückblick und Ausblick (2001)
0.01
0.0117150815 = product of:
0.041002784 = sum of:
0.02733519 = weight(_text_:j in 5659) [ClassicSimilarity], result of:
0.02733519 = score(doc=5659,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.28085366 = fieldWeight in 5659, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.0625 = fieldNorm(doc=5659)
0.013667595 = product of:
0.02733519 = sum of:
0.02733519 = weight(_text_:j in 5659) [ClassicSimilarity], result of:
0.02733519 = score(doc=5659,freq=2.0), product of:
0.09732894 = queryWeight, product of:
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.030630698 = queryNorm
0.28085366 = fieldWeight in 5659, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1774964 = idf(docFreq=5010, maxDocs=44218)
0.0625 = fieldNorm(doc=5659)
0.5 = coord(1/2)
0.2857143 = coord(2/7)
