On 3/1/2013 12:44 PM, Rich Cooper wrote:
> The point of my post was that using semantics to
> drive parsing, with a much more limited role for
> parsing, might yield better results than we have
> gotten so far, including ATNs and the various
> parser approaches. (01)
Using semantics is essential. But computational linguists implemented
versions of semantics to support the parsing stage in the 1960s. The
term 'semantic network' was introduced around 1961. Ross Quillian
popularized it with his dissertation in 1966. (02)
Bill Woods used the registers of ATNs to represent type constraints
(i.e., ontology) for his Q/A system about moon rocks in the early 1970s. (03)
And Roger Schank and his students used minimal syntax and lots of
domain-dependent semantics for their systems in the 1980s. (04)
More recently, Ron Kaplan's group had a license to use the full Cyc
ontology and software. The part they found most useful was the
hierarchy of concepts, not the axioms associated with those concepts. (05)
John (06)
_________________________________________________________________
Message Archives: http://ontolog.cim3.net/forum/ontolog-forum/
Config Subscr: 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 join: http://ontolog.cim3.net/cgi-bin/wiki.pl?WikiHomePage#nid1J (07)
|