Traumwind - keyword similarity works (too)

Well the "Textarchiv" search vor "Ähnliche Artikel" for this German Newspaper shows that using keyword searches to find similar articles does actually work rather well. And given the state of the technology, this might actually be a very feasible approach, as is requires hardly any new tech to implement it...

I think the main difference - that is often overlooked - here is the fact that the semantic approaches offer one step further. They can find related text that share no keywords at all, but might share neighbours

[btw. the 'bayesian approach' I talk about in my essay is nothing less than a glorified keyword-occurence-comparison...]

[ by Martin>] [permalink] [similar entries]

similar entries (vs):

what I like about similarity stuff (# 11%)
similar entries really work (# 11%)
Some thought on similarity (# 10%)
An angel (# 10%)

similar entries (cg):

whatis kartOO (# 6%)
Remembrance Agents Page (# 1%)
BananaSlug (# 1%)

relevant words

Big things to come (TM) 30th Dez 2002

Cut a vital connection
Oblique Strategies, Ed.3 Brian Eno and Peter Schmidt

amazon.de Wunschliste

usefull links:
Google Graph browser
Traumwind 6-Colormatch
UAV News

keyword (2.5)
share (2.3)
approach (2.1)
actually (1.7)
find (1.7)
approaches (1.6)
overlooked (1.6)
glorified (1.6)
newspaper (1.6)
textarchiv (1.6)
http://www.berlinonline.de/berliner-zeitung/archiv/.bin/index.fcgi?match=strict&keywords=Zeppelin,Firma,Passagiere,Str%E4ter,Luftschiff,Friedrichshafen,Bodensee,Luftschifftechnik,L%E4nge,Cargolifter (1.6)
www.berlinonline.de (1.6)
hnliche (1.6)
vor (1.6)
implement (1.6)
artikel (1.6)
might (1.5)
feasible (1.5)
similarity (1.5)
neighbours (1.5)
offer (1.5)
http://traumwind.de/computer/search/three_approaches_to_searching.html (1.5)
requires (1.5)
the (1.5)
that (1.4)
searches (1.4)
hardly (1.4)
btw (1.4)
is (1.4)
well (1.4)
difference (1.4)
articles (1.4)
shows (1.4)
keywords (1.3)
technology (1.3)
bayesian (1.3)
tech (1.3)
essay (1.3)
semantic (1.3)
talk (1.2)
state (1.2)
main (1.2)
less (1.2)
german (1.2)
nothing (1.2)
further (1.2)
fact (1.2)
given (1.2)
step (1.2)
related (1.1)
often (1.1)
works (1.1)
traumwind.de (1.1)
this (1.1)
rather (1)
similar (1)
does (1)
too (1)
text (1)
than (1)
using (0.9)
think (0.9)
i (0.9)
they (0.9)
search (0.9)
a (0.9)
work (0.9)
to (0.9)
no (0.9)
new (0.8)
any (0.8)
very (0.8)
here (0.8)
at (0.8)
about (0.8)
all (0.7)
as (0.7)
one (0.7)
can (0.7)
be (0.7)
but (0.7)
my (0.6)
it (0.6)
in (0.5)
for (0.5)
of (0.5)
and (0.5)
martin (0.4)
(0)