Document (#36263)

Author

Alvers, M.R.

Title

Semantische wissensbasierte Suche in den Life Sciences am Beispiel von GoPubMed

Source

Semantic web & linked data: Elemente zukünftiger Informationsinfrastrukturen ; 1. DGI-Konferenz ; 62. Jahrestagung der DGI ; Frankfurt am Main, 7. - 9. Oktober 2010 ; Proceedings / Deutsche Gesellschaft für Informationswissenschaft und Informationspraxis. Hrsg.: M. Ockenfeld

Imprint

Frankfurt. / M. : DGI

Year

2010

Pages

S.49-54

Series

Tagungen der Deutschen Gesellschaft für Informationswissenschaft und Informationspraxis ; Bd. 14) (DGI-Konferenz ; 1

Abstract

Nie zuvor war der Zugriff auf Informationen so einfach und schnell wie heute. Die Suchmaschine Google ist dabei mit einem Marktanteil von 95 Prozent in Deutschland führend. Aber reicht der heutige Status Quo aus? Wir meinen nein - andere meinen ja. Die Verwendung von Stichworten für die Suche ist sehr begrenzt, nicht intelligent und der Algorithmus zum ranking der Suchergebnisse fragwürdig. Wir zeigen neue Wege der semantischen Suche mittels der Verwendung von Hintergrundwissen. Die (semi)automatische Generierung von Ontologien wird ebenfalls als zentraler Bestandteil einer universellen Wissensplattform vorgestellt und gezeigt, wie Anwender mit dieser Technologie signifikant Zeit sparen und deutlich relevantere Informationen finden.

Content

"Im Vortrag werden Aspekte der Suche nach Informationen und Antworten aus dem breiten Spektrum von der Suche nach einer Telefonnummer bis zur Frage nach dem "Sinn des Lebens" (deren Antwort auch im Vortrag leider nicht gegeben werden kann) angesprochen. Die Verwendung von Hintergrundwissen in Form von semantischen Begriffsnetzwerken, sogenannten Ontologien, hilft enorm, der Beantwortung von Fragen näher zu kommen. Sie garantieren Vollständigkeit der Suchergebnisse und schnelles Fokussieren auf Relevantes. Das bedeutungs-getriebene Einsortieren oder das Klassifizieren von Informationen aus Dokumenten oder von Internetinhalten, ermöglicht die Disambiguierung von Begriffen wie Salz und 01, " Cyclooxygenase Inhibitoren" - eher bekannt als Aspirin - oder das Auffinden aller Dokumente, die zum Thema CO2 - Sequestrierung gehören - also auch solcher, in den Begriff CO2 - Sequestrierung nicht direkt enthalten aber solche, die für das Thema relevant sind. Die Technologie hinter GoPubMed automatisiert schwierige Analysen, die normaler Weise von Wissenschaftlern getätigt werden. Dabei werden die notwendigen Informationen, wie sie von ausgefeilten Algorithmen ([DS05]) vorausgesagt wurden, mit einer deutlich höheren Genauigkeit bereitgestellt. Transinsights semantische Suchtechnologien wurde als erstes Beispiel der nächsten Generation der Suche entwickelt. Die Stärke liegt in der Fähigkeit, große Textkorpora (> 500 Millionen Dokumente) mit großen Ontologien (> 15 Millionen Konzepte) zu verknüpfen. In GoPubMed wird die Gene Ontology und MeSH verwendet, die zusammen mit einer Geo-Ontologie und allen Autoren ca. 15 Millionen Konzepte beinhalten.m"

Theme

Wissensrepräsentation

Field

Medizin

Object

GoPubMed

Similar documents (content)

1. Multimedia-Inhalte in Factiva : Produkten gezielt recherchierbar (2007) 0.11

   0.109795004 = sum of:
     0.109795004 = product of:
       0.4574792 = sum of:
         0.0981364 = weight(abstract_txt:anwender in 500) [ClassicSimilarity], result of:
           0.0981364 = score(doc=500,freq=3.0), product of:
             0.14282024 = queryWeight, product of:
               1.0408546 = boost
               7.2542357 = idf(docFreq=84, maxDocs=44218)
               0.018915074 = queryNorm
             0.6871323 = fieldWeight in 500, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               7.2542357 = idf(docFreq=84, maxDocs=44218)
               0.0546875 = fieldNorm(doc=500)
         0.088807404 = weight(abstract_txt:prozent in 500) [ClassicSimilarity], result of:
           0.088807404 = score(doc=500,freq=2.0), product of:
             0.1529559 = queryWeight, product of:
               1.0771552 = boost
               7.5072327 = idf(docFreq=65, maxDocs=44218)
               0.018915074 = queryNorm
             0.5806079 = fieldWeight in 500, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               7.5072327 = idf(docFreq=65, maxDocs=44218)
               0.0546875 = fieldNorm(doc=500)
         0.06357166 = weight(abstract_txt:suchergebnisse in 500) [ClassicSimilarity], result of:
           0.06357166 = score(doc=500,freq=1.0), product of:
             0.15421234 = queryWeight, product of:
               1.0815703 = boost
               7.538004 = idf(docFreq=63, maxDocs=44218)
               0.018915074 = queryNorm
             0.4122346 = fieldWeight in 500, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.538004 = idf(docFreq=63, maxDocs=44218)
               0.0546875 = fieldNorm(doc=500)
         0.091756076 = weight(abstract_txt:begrenzt in 500) [ClassicSimilarity], result of:
           0.091756076 = score(doc=500,freq=1.0), product of:
             0.19695483 = queryWeight, product of:
               1.222302 = boost
               8.518833 = idf(docFreq=23, maxDocs=44218)
               0.018915074 = queryNorm
             0.4658737 = fieldWeight in 500, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.518833 = idf(docFreq=23, maxDocs=44218)
               0.0546875 = fieldNorm(doc=500)
         0.036588132 = weight(abstract_txt:informationen in 500) [ClassicSimilarity], result of:
           0.036588132 = score(doc=500,freq=1.0), product of:
             0.13443539 = queryWeight, product of:
               1.4281275 = boost
               4.976667 = idf(docFreq=828, maxDocs=44218)
               0.018915074 = queryNorm
             0.27216148 = fieldWeight in 500, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.976667 = idf(docFreq=828, maxDocs=44218)
               0.0546875 = fieldNorm(doc=500)
         0.07861955 = weight(abstract_txt:suche in 500) [ClassicSimilarity], result of:
           0.07861955 = score(doc=500,freq=1.0), product of:
             0.25625414 = queryWeight, product of:
               2.414856 = boost
               5.6101127 = idf(docFreq=439, maxDocs=44218)
               0.018915074 = queryNorm
             0.30680305 = fieldWeight in 500, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.6101127 = idf(docFreq=439, maxDocs=44218)
               0.0546875 = fieldNorm(doc=500)
       0.24 = coord(6/25)
   

2. Pfeiffer, S.: Entwicklung einer Ontologie für die wissensbasierte Erschließung des ISDC-Repository und die Visualisierung kontextrelevanter semantischer Zusammenhänge (2010) 0.11

   0.108821675 = sum of:
     0.108821675 = product of:
       0.6801355 = sum of:
         0.064217076 = weight(abstract_txt:suchergebnisse in 4658) [ClassicSimilarity], result of:
           0.064217076 = score(doc=4658,freq=2.0), product of:
             0.15421234 = queryWeight, product of:
               1.0815703 = boost
               7.538004 = idf(docFreq=63, maxDocs=44218)
               0.018915074 = queryNorm
             0.4164198 = fieldWeight in 4658, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               7.538004 = idf(docFreq=63, maxDocs=44218)
               0.0390625 = fieldNorm(doc=4658)
         0.47248477 = weight(title_txt:wissensbasierte in 4658) [ClassicSimilarity], result of:
           0.47248477 = score(doc=4658,freq=1.0), product of:
             0.21322298 = queryWeight, product of:
               1.2717806 = boost
               8.863674 = idf(docFreq=16, maxDocs=44218)
               0.018915074 = queryNorm
             2.2159185 = fieldWeight in 4658, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.863674 = idf(docFreq=16, maxDocs=44218)
               0.25 = fieldNorm(doc=4658)
         0.0640159 = weight(abstract_txt:informationen in 4658) [ClassicSimilarity], result of:
           0.0640159 = score(doc=4658,freq=6.0), product of:
             0.13443539 = queryWeight, product of:
               1.4281275 = boost
               4.976667 = idf(docFreq=828, maxDocs=44218)
               0.018915074 = queryNorm
             0.4761834 = fieldWeight in 4658, product of:
               2.4494898 = tf(freq=6.0), with freq of:
                 6.0 = termFreq=6.0
               4.976667 = idf(docFreq=828, maxDocs=44218)
               0.0390625 = fieldNorm(doc=4658)
         0.079417735 = weight(abstract_txt:suche in 4658) [ClassicSimilarity], result of:
           0.079417735 = score(doc=4658,freq=2.0), product of:
             0.25625414 = queryWeight, product of:
               2.414856 = boost
               5.6101127 = idf(docFreq=439, maxDocs=44218)
               0.018915074 = queryNorm
             0.30991787 = fieldWeight in 4658, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               5.6101127 = idf(docFreq=439, maxDocs=44218)
               0.0390625 = fieldNorm(doc=4658)
       0.16 = coord(4/25)
   

3. Renker, L.: Exploration von Textkorpora : Topic Models als Grundlage der Interaktion (2015) 0.08

   0.079483785 = sum of:
     0.079483785 = product of:
       0.39741892 = sum of:
         0.062095348 = weight(abstract_txt:bestandteil in 2380) [ClassicSimilarity], result of:
           0.062095348 = score(doc=2380,freq=1.0), product of:
             0.13888484 = queryWeight, product of:
               1.026414 = boost
               7.1535926 = idf(docFreq=93, maxDocs=44218)
               0.018915074 = queryNorm
             0.44709954 = fieldWeight in 2380, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.1535926 = idf(docFreq=93, maxDocs=44218)
               0.0625 = fieldNorm(doc=2380)
         0.06475323 = weight(abstract_txt:anwender in 2380) [ClassicSimilarity], result of:
           0.06475323 = score(doc=2380,freq=1.0), product of:
             0.14282024 = queryWeight, product of:
               1.0408546 = boost
               7.2542357 = idf(docFreq=84, maxDocs=44218)
               0.018915074 = queryNorm
             0.45338973 = fieldWeight in 2380, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.2542357 = idf(docFreq=84, maxDocs=44218)
               0.0625 = fieldNorm(doc=2380)
         0.04181501 = weight(abstract_txt:informationen in 2380) [ClassicSimilarity], result of:
           0.04181501 = score(doc=2380,freq=1.0), product of:
             0.13443539 = queryWeight, product of:
               1.4281275 = boost
               4.976667 = idf(docFreq=828, maxDocs=44218)
               0.018915074 = queryNorm
             0.31104168 = fieldWeight in 2380, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.976667 = idf(docFreq=828, maxDocs=44218)
               0.0625 = fieldNorm(doc=2380)
         0.13890442 = weight(abstract_txt:verwendung in 2380) [ClassicSimilarity], result of:
           0.13890442 = score(doc=2380,freq=2.0), product of:
             0.23755246 = queryWeight, product of:
               1.8984097 = boost
               6.615483 = idf(docFreq=160, maxDocs=44218)
               0.018915074 = queryNorm
             0.5847316 = fieldWeight in 2380, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               6.615483 = idf(docFreq=160, maxDocs=44218)
               0.0625 = fieldNorm(doc=2380)
         0.08985091 = weight(abstract_txt:suche in 2380) [ClassicSimilarity], result of:
           0.08985091 = score(doc=2380,freq=1.0), product of:
             0.25625414 = queryWeight, product of:
               2.414856 = boost
               5.6101127 = idf(docFreq=439, maxDocs=44218)
               0.018915074 = queryNorm
             0.35063204 = fieldWeight in 2380, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.6101127 = idf(docFreq=439, maxDocs=44218)
               0.0625 = fieldNorm(doc=2380)
       0.2 = coord(5/25)
   

4. Web-2.0-Dienste als Ergänzung zu algorithmischen Suchmaschinen (2008) 0.08

   0.07699092 = sum of:
     0.07699092 = product of:
       0.48119324 = sum of:
         0.097129844 = weight(abstract_txt:anwender in 4323) [ClassicSimilarity], result of:
           0.097129844 = score(doc=4323,freq=1.0), product of:
             0.14282024 = queryWeight, product of:
               1.0408546 = boost
               7.2542357 = idf(docFreq=84, maxDocs=44218)
               0.018915074 = queryNorm
             0.6800846 = fieldWeight in 4323, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.2542357 = idf(docFreq=84, maxDocs=44218)
               0.09375 = fieldNorm(doc=4323)
         0.10897999 = weight(abstract_txt:suchergebnisse in 4323) [ClassicSimilarity], result of:
           0.10897999 = score(doc=4323,freq=1.0), product of:
             0.15421234 = queryWeight, product of:
               1.0815703 = boost
               7.538004 = idf(docFreq=63, maxDocs=44218)
               0.018915074 = queryNorm
             0.70668787 = fieldWeight in 4323, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.538004 = idf(docFreq=63, maxDocs=44218)
               0.09375 = fieldNorm(doc=4323)
         0.14030707 = weight(abstract_txt:generierung in 4323) [ClassicSimilarity], result of:
           0.14030707 = score(doc=4323,freq=1.0), product of:
             0.18250482 = queryWeight, product of:
               1.1766095 = boost
               8.200379 = idf(docFreq=32, maxDocs=44218)
               0.018915074 = queryNorm
             0.7687856 = fieldWeight in 4323, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.200379 = idf(docFreq=32, maxDocs=44218)
               0.09375 = fieldNorm(doc=4323)
         0.13477637 = weight(abstract_txt:suche in 4323) [ClassicSimilarity], result of:
           0.13477637 = score(doc=4323,freq=1.0), product of:
             0.25625414 = queryWeight, product of:
               2.414856 = boost
               5.6101127 = idf(docFreq=439, maxDocs=44218)
               0.018915074 = queryNorm
             0.52594805 = fieldWeight in 4323, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.6101127 = idf(docFreq=439, maxDocs=44218)
               0.09375 = fieldNorm(doc=4323)
       0.16 = coord(4/25)
   

5. Schmude, A.N.: Ontologiebasierte Suche und Navigation in webbasierten Informationssystemen : am Beispiel Bürgerinformationsdienste (2004) 0.07

   0.074839644 = sum of:
     0.074839644 = product of:
       0.3741982 = sum of:
         0.054489996 = weight(abstract_txt:ontologien in 4605) [ClassicSimilarity], result of:
           0.054489996 = score(doc=4605,freq=1.0), product of:
             0.15421234 = queryWeight, product of:
               1.0815703 = boost
               7.538004 = idf(docFreq=63, maxDocs=44218)
               0.018915074 = queryNorm
             0.35334393 = fieldWeight in 4605, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.538004 = idf(docFreq=63, maxDocs=44218)
               0.046875 = fieldNorm(doc=4605)
         0.054489996 = weight(abstract_txt:suchergebnisse in 4605) [ClassicSimilarity], result of:
           0.054489996 = score(doc=4605,freq=1.0), product of:
             0.15421234 = queryWeight, product of:
               1.0815703 = boost
               7.538004 = idf(docFreq=63, maxDocs=44218)
               0.018915074 = queryNorm
             0.35334393 = fieldWeight in 4605, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.538004 = idf(docFreq=63, maxDocs=44218)
               0.046875 = fieldNorm(doc=4605)
         0.094179176 = weight(abstract_txt:heutige in 4605) [ClassicSimilarity], result of:
           0.094179176 = score(doc=4605,freq=2.0), product of:
             0.17627926 = queryWeight, product of:
               1.1563673 = boost
               8.059301 = idf(docFreq=37, maxDocs=44218)
               0.018915074 = queryNorm
             0.5342612 = fieldWeight in 4605, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               8.059301 = idf(docFreq=37, maxDocs=44218)
               0.046875 = fieldNorm(doc=4605)
         0.05431929 = weight(abstract_txt:informationen in 4605) [ClassicSimilarity], result of:
           0.05431929 = score(doc=4605,freq=3.0), product of:
             0.13443539 = queryWeight, product of:
               1.4281275 = boost
               4.976667 = idf(docFreq=828, maxDocs=44218)
               0.018915074 = queryNorm
             0.404055 = fieldWeight in 4605, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               4.976667 = idf(docFreq=828, maxDocs=44218)
               0.046875 = fieldNorm(doc=4605)
         0.11671976 = weight(abstract_txt:suche in 4605) [ClassicSimilarity], result of:
           0.11671976 = score(doc=4605,freq=3.0), product of:
             0.25625414 = queryWeight, product of:
               2.414856 = boost
               5.6101127 = idf(docFreq=439, maxDocs=44218)
               0.018915074 = queryNorm
             0.4554844 = fieldWeight in 4605, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               5.6101127 = idf(docFreq=439, maxDocs=44218)
               0.046875 = fieldNorm(doc=4605)
       0.2 = coord(5/25)