mickey@a.nl.cs.cmu.edu (Raman Chandrasekar) (06/19/91)
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. For example, this system would highlight sports stories (perhaps, specifically, tennis stories) for a sports (tennis) fanatic. It would prominently display Chicago weather if you planned to take a trip there. I have a few questions about this and related systems: 1. If you have a contact (name + email address) for the person(s) who developed the system above, could you please mail it to me? 2. If you know of any similar systems (multimedia, or just plain text), could you please send whatever you have: contact names, addresses, email addresses, bibliographic references -- anything relevant? I would appreciate any help in this. Many thanks. -- Chandrasekar mickey@cs.cmu.edu ______________________________________________________________________ R Chandrasekar Email: mickey@a.nl.cs.cmu.edu Center for Machine Translation Fax : +1 (412) 268-6298 Smith Hall 109, Carnegie Mellon Univ Phone: +1 (412) 268-5113 Pittsburgh PA 15213-3890 Home: +1 (412) 361-5150 ______________________________________________________________________
verber@pacific.mps.ohio-state.edu (Mark Verber) (06/24/91)
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
osborn@socs.uts.edu.au (Tom Osborn) (06/25/91)
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.
asb@media-lab.media.mit.edu (Amy Bruckman) (06/26/91)
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