"Metadata is a love note to the future"

[Thomas Sødring]

Nice catches Petter.

When it comes to machine learning, I would like to autoclassify new incoming documents based on existing documents. Take for example the Hallingdal kommuner that I worked with.  I generated 7 database dump extractions with related documents. The classification code and other metadata and documents are linked. So we could try a machine learning training run on 2 of the extractions and verify the algorithm on the other 5.  There are so many factors that we can finetune and play with during such experiments.

The limiting factor here is privacy laws, but we could do this without ever looking at the sensitive data, but it would require a strict technical setup at an IKA.

 - Tom

On 06/20/2017 10:10 PM, Petter Reinholdtsen wrote:

I found the marvelous quote above in a slide set about the NRK Origo
project,
<URL: https://kulturognaturreise.files.wordpress.com/2014/09/nrk-semantisk-teknologi-kulturlod-konferanse-gmoen-okt-2014.pdf >,
and thought it might be well received here. :)

Found the project via
<URL: https://www.digi.no/artikler/bruker-stemme-og-ansiktsgjenkjenning-for-a-gjore-det-enklere-a-finne-skjulte-skatter-i-nrk-arkivet/395984 >,
which mention work to automatically extract metadata using machine
learning.  Seem like good inspiration for what we could do in Nikita. :)

Found the T-shirt over at
<URL: https://behappy.me/poster/metadata-is-a-love-note-to-the-future-heart-97740 >


Hvordan plassere oss for fremtiden - endrede krav til ...<https://kulturognaturreise.files.wordpress.com/2014/09/nrk-semantisk-teknologi-kulturlod-konferanse-gmoen-okt-2014.pdf>
kulturognaturreise.files.wordpress.com
Nordlod-konferansen 24. Oktober 2014 Hvordan plassere oss for fremtiden - endrede krav til interne systemer for å imøtekomme fremtidens behov



-------------- next part --------------
An HTML attachment was scrubbed...
URL: https://lists.nuug.no/pipermail/nikita-noark/attachments/20170621/0299bfcc/attachment.htm