AUTOMATIC CLUSTERING TECHNIQUES IN INFORMATION RETRIEVAL

-

Documents
152 pages
Obtenez un accès à la bibliothèque pour le consulter en ligne
En savoir plus

Description

I lifllll BF» m ι %Æ Α. SOS lom Β e¡M»K liiiliÊSI MÍI COMMISSIONOF THE EUROPEAN¡Frø:."· ν,ίκ^ 'ifr,Mt· t u ™$ $r# £$&*' i'd·*: Äpfe« sm AUTOMATIC CLUSTERING TECHNIQUES IN INFORMATION RETRIEVAL M. FRITSCHE II» mmm 1 §Mw lili ' PLi' tW' .til' %i Η Joint Nuclear Research Centre Ispra Establishment ­ Italy Scientific Data Processing Gentre ­ CETI S IñMi RffiK ii LEGAL NOTICE J* document was prepared under the sponsorship of the Commission âlil of the European Communities. Neither the Commission of the European Communities, its contractors T1/-.T- onir norona „„+.'„ J/L „:_ 1 t.-« . nor any person acting on their behalf : $*iii! tilt Ά>. make any warranty or representation, express or implied, with respect to the accuracy, completeness, or usefulness of the information contained in this document, or that the use of any information, apparatus, method from the use of any information, apparatus, method or process disclosed in this document. iiliílTS/'lil^^ í^llJPli^rí!; i' This report is on sale at the addresses listed on cover page 4 mÊKÀ&Hw Ι»Ή,: r ö Hi at the price of B.Fr. 185.— Hi When ordering, please quote the EUR number and the title which are indicated on the cover of each report. II mm Commission of the European Communities D.G. XIII - C.I.D. 29, rue Aldringen Luxembourg im February 1974 i' ^^iiißiiiiilii This document was reproduced on the basis of the best available copy. Mila! ft A.

Sujets

Informations

Publié par
Nombre de visites sur la page 8
Langue English
Signaler un problème

I lifllll
BF» m ι
%Æ Α. SOS
lom Β
e¡M»K
liiiliÊSI MÍI
COMMISSIONOF THE EUROPEAN
¡Frø:."· ν,ίκ^ 'ifr,Mt· t u ™$ $r# £$&*' i'd·*:
Äpfe« sm
AUTOMATIC CLUSTERING TECHNIQUES
IN INFORMATION RETRIEVAL
M. FRITSCHE
II» mmm 1
§Mw lili
' PLi' tW' .til'
%i
Η
Joint Nuclear Research Centre
Ispra Establishment ­ Italy
Scientific Data Processing Gentre ­ CETI S
IñMi RffiK ii
LEGAL NOTICE
J*
document was prepared under the sponsorship of the Commission âlil
of the European Communities.
Neither the Commission of the European Communities, its contractors
T1/-.T- onir norona „„+.'„ J/L „:_ 1 t.-« . nor any person acting on their behalf :
$*iii! tilt Ά>.
make any warranty or representation, express or implied, with respect
to the accuracy, completeness, or usefulness of the information contained
in this document, or that the use of any information, apparatus, method
from the use of any information, apparatus, method or process disclosed
in this document. iiliílTS/'lil^^ í^llJPli^rí!; i'
This report is on sale at the addresses listed on cover page 4
mÊKÀ&Hw Ι»Ή,: r ö Hi
at the price of B.Fr. 185.—
Hi
When ordering, please quote the EUR number and the title
which are indicated on the cover of each report.
II mm
Commission of the
European Communities
D.G. XIII - C.I.D.
29, rue Aldringen
Luxembourg
im
February 1974
i' ^^iiißiiiiilii
This document was reproduced on the basis of the best available copy.
Mila!
ft A. Sût ili' f "tû l'li'*;-EUR 5051 e
AUTOMATIC CLUSTERING TECHNIQUES IN INFORMATION
RETRIEVAL by M. FRITSCHE
Commission of the European Communities
Joint Nuclear Research Centre - Ispra Establishment (Italy)
Scientific Data Processing Centre - CETIS
Luxembourg, February 1974 - 146 Pages - 10 Figures - B.Fr. 185.—
The present study is a state-of-the-art report on automatic clustering
techniques which reviews the research performed in the field since 1967.
Although emphasis was given to methods applicable in the field of information
science, many approaches can be used in other applications as well.
EUR 5051 e
AUTOMATIC CLUSTERING TECHNIQUES IN INFORMATION
RETRIEVAL by M. FRITSCHE
Commission of the European Communities
Joint Nuclear Research Centre - Ispra Establishment (Italy)
Scientific Data Processing Centre - CETIS
Luxembourg, February 1974 - 146 Pages - 10 Figures - B.Fr. 185 —
The present study is a state-of-the-art report on automatic clustering
techniques which reviews the research performed in the field since 1967.
Although emphasis was given to methods applicable in the field of information
science, many approaches can be used in other applications as well.
EUR 5051 e
AUTOMATIC CLUSTERING TECHNIQUES IN INFORMATION
RETRIEVAL by M. FRITSCHE
Commission of the European Communities
Joint Nuclear Research Centre - Tspra Establishment (Italy)
Scientific Data Processing Centre - CETIS
Luxembourg, February 1974 - 146 Pages - 10 Figures - B.Fr. 185 —
The present study is a state-of-the-art report on automatic clustering
techniques which reviews the research performed in the field since 1967.
Although emphasis was given to methods applicable in the field of information
science, many approaches can be used in other applications as well. EUR SOS1 e
COMMISSION OF THE EUROPEAN COMMUNITIES
AUTOMATIC CLUSTERING TECHNIQUES
IN INFORMATION RETRIEVAL
by
M. FRITSCHE
1974
Joint Nuclear Research Centre
Ispra Establishment - Italy
Scientific Data Processing Centre - CETIS
Diploma-thesis presented at
the Faculty of Mathematics of the
University of Stuttgart ABSTRAGT
The present study is a state-of-the-art report on automatic clustering
techniques which reviews the research performed in the field since 1967.
Although emphasis was given to methods applicable in the field of information
science, many approaches can be used in other applications as well.
KEYWORDS
AUTOMATION MATHEMATICS
INFORMATION RETRIEVAL PROGRAMMING
UNIVERSITIES INFORMATION - 3 -
The present report is the second publication in the context of the
coorperation between the
Information Science Research Unit of the
European Scientific Information Processing Centre (CETIS) of the
Joint Research Centre of the
Commission of the European Communities in Ispra
and the
Institute for Informatics (IFI) of the
University of Stuttgart.
This diploma-the sis (Diplom-Arbeit) is presented to the
Faculty of Mathematics of the
University of Stuttgart.
Although such theses usually are not published (because of the limited
time schedule in which they have to be compiled), it was deemed
worthwhile to record this one in contrast to the practice for two reasons:
- A large amount of time was dedicated to discussions and
consultations by the two responsible persons, and
- the argument treated is of great interest in the field of
information science.
This thesis reviews the research performed in automatic clustering
techniques in the last years (from 1967 on). 4 -
It describes the different approaches applied especially in the field
of information science.
A state-of-the-art in the field in question is considered to be useful
for the simple reason that automatic methods are more and more
applied in information science.
However, the techniques suffer either from their limited practicability,
as matrix representation of the objects to be clustered is involved,
or from the order dependency of the so-called fast clustering techniques,
Hence, research should be intensivated in order to develop reliable
algorithms which make sure the order independency and work at a
high speed.
Dipl. Math. H, Fangmeyer Dr. H.J. Schneider
for the for the
Information Science Research Unit Institute for Informatics
CETIS University of Stuttgart
EFT - 5
ACKNOWLEDGEMENTS
I thank Professor Dr. W. Knödel for the permission to complete the
underneath investigations at the Institute for Informatics, University
of Stuttgart, Germany.
I would like to thank also Dr. H.J. Schneider, who has been of great
help for me, and who arranged a stage period for me at EURATOM in
Ispra, Italy.
However, this work would certainly not have been possible without
reliance on materials and techniques previously and concurrently
developed at the European Scientific Information Research Centre
of EURATOM, where I found an excellent advisor and stimulator in
Mr. H. Fangmeyer.