The most ambitious effort I know of along the lines of using classical
NLP to try and label the Web for meaning is the very trendy new Web
startup Powerset: (01)
http://www.powerset.com (02)
As I recall they have got funding in the area of $10+ M to index the
whole Web. They've bought rights to PARC's NLP technology. (03)
Are people here aware of that company? (04)
I have a soft spot for any NLP effort, but anyone who has seen my
posts here will probably realize I think they have got the problem
exactly the wrong way around. Instead of using NLP to help with
search, I think they should be using something like search to fix NLP
(and improve search at the same time.) (05)
But that's another story. The effort is interesting. (06)
-Rob (07)
On Thu, Feb 14, 2008 at 7:29 PM, <matthew.west@xxxxxxxxx> wrote:
>
>
> Dear Pat,
>
> This looks somewhat similar to what I have seen from a couple of EC funded
> research projects I was a reviewer for over the last several years. There is
> no doubt that if you consider this sort of thing to be a tool for computer
> assisted ontology development, then it can be very helpful, particularly
> where we are talking about extracting brute facts. However, if you are
> talking about more general ontology extraction, then of course the ontolgoy
> produced is going to be no better than that of the document considered, and
> there are the usual issues with ambiguity that computers usually struggle
> with, especially using words with different senses in close proximity.
>
>
>
> Regards
>
> Matthew West (08)
_________________________________________________________________
Message Archives: http://ontolog.cim3.net/forum/ontolog-forum/
Subscribe/Config: http://ontolog.cim3.net/mailman/listinfo/ontolog-forum/
Unsubscribe: mailto:ontolog-forum-leave@xxxxxxxxxxxxxxxx
Shared Files: http://ontolog.cim3.net/file/
Community Wiki: http://ontolog.cim3.net/wiki/
To Post: mailto:ontolog-forum@xxxxxxxxxxxxxxxx (09)
|