🚀 go-pugleaf

In article <13510@pt.cs.cmu.edu> mickey@a.nl.cs.cmu.edu (Raman Chandrasekar) writes:

   I have read about a system (?prototype) developed at the
   MIT Media Lab, which extracts news of relevance to a 
   *particular* reader, and customizes it to the reader's
   preference, and presents it to her in a multimedia 
   electronic form.

A paper about this system can be found in the most recent proceedings of
Usenix:

Multimedia - For Now and the Future
USENIX Summer '91 Conference Proceedings -- June 10-14
Newspace: Mass Media and Personal Computing, Page 329-347

--mark

verber@pacific.mps.ohio-state.edu (Mark Verber) writes:

>In article <13510@pt.cs.cmu.edu> mickey@a.nl.cs.cmu.edu (Raman Chandrasekar) writes:

>   ... a system (?prototype)... MIT Media Lab, ... extracts news ...
>   ... relevance to a  *particular* reader, and customizes it to 
>   the reader's preference, and presents it to her in a multimedia 
>   electronic form.

>A paper about this system can be found in the most recent proceedings of
>Usenix:

>Multimedia - For Now and the Future
>USENIX Summer '91 Conference Proceedings -- June 10-14
>Newspace: Mass Media and Personal Computing, Page 329-347

Well, the Media Lab isn't the only group working on this. GMD in
Darmstadt has been working on the (huge number of) problems for
a while and expect to release a prototype systems soon. The non-
prototype version is expected for September (but I don't know which
September).

I must admit some doubts about this. I had a postgrad student working
on something a bit like this a few years ago (automatic indexing and
content addressable retrieval). Some that retrieval from headlines and
intro paragraphs is fraught with problems - the key words are there,
but so is a lot of attention attracting hype. Manual key-wording is a
possible fix, but it seems that non-experts are poor at this (they 
devise keys from their own perspective well, but for readers badly).

Educating writers or demanding a higher editorial standard may be
the only way. Ie, for whatever reason, news contains a lot of noise.

Also, the *personalised* customising is very problematic. Eh?

Tomasso.
--
Tom Osborn,                        
School of Computing Sciences,        " Beware of the small carrots "
University of Technology, Sydney,
PO Box 123 Broadway 2007,  AUSTRALIA.                          R H-M.

In article <osborn.677813746@dragon> osborn@socs.uts.edu.au (Tom Osborn) writes:
>
>I must admit some doubts about this. I had a postgrad student working
>on something a bit like this a few years ago (automatic indexing and
>content addressable retrieval). Some that retrieval from headlines and
>intro paragraphs is fraught with problems - the key words are there,
>but so is a lot of attention attracting hype. Manual key-wording is a
>possible fix, but it seems that non-experts are poor at this (they 
>devise keys from their own perspective well, but for readers badly).


At AAAI-90 in one of the applications seminars, a company presented
a rule-based system developed for Reuters to do automatic indexing of
news stories coming off of the wire.  They have had tremendous success
with the system.  It is more accurate at indexing stories than humans,
because humans get bored and careless.  (Evidently, indexing is tedious.)
And it's much quicker: stories are indexed within an hour, if I remember
correctly, instead of two days.    (There is no paper about this
in the proceedings.  There might have been a separate set of proceedings
for the applications conference; I'm not sure.)

The system is very simple in its design.  For example, it distinguishes
the meaning of the word "lead" ("I lead them to the conference room"
versus "our widgit is made of lead") by looking for the presence or
absence of certain other words in the surrounding text.  What is interesting
about the system is not its design but its tremendous practical success.

-- Amy