On Wed, November 17, 2010 13:16, Rich Cooper said:
> Hi Doug,
>
> In general, I agree. But the specifics seem to have escaped everyone who
> has done research into this area of active NLP interfaces. (01)
For one system in use that uses ontologies to interpret natural language
queries and handle ambigities, see
http://www.cyc.com/technology/whitepapers_dir/Harnessing_Cyc_to_Answer_Clincal_Researchers_ad_hoc_Queries.pdf (02)
Although this is in a restricted field, some interesting results have
been achieved. [Disclaimer: I am not an author of the paper, but have
worked with most of the authors.] (03)
These are far more complex than Blocks World NLP. An example question
in the mentioned article is
"Are there cases in the last decade where patients had pericardial aortic
valves inserted in the reverse position, to serve as mitral valve
replacements, and how often in such cases did endocarditis or tricuspid
valve infection develop, and how long after the procedure?" (04)
The task deals with the following challenges:
Challenge 1: Getting the literal query understood: converting it from
highly ambiguous natural language to an unambiguous logical form.
Challenge 2: Getting the intended query understood. Often the physician
will leave off some obvious clauses and details
Challenge 3: Given a complete, unambiguous, logical form of the intended
query, finding the answer to that query.
Challenge 4: Present the answers to the physician in a useful fashion.
what "useful" means may change from user to user, situation ...
Challenge 5: In cases where the system would otherwise fail to return an
answer, it should ―fail soft‖: i.e., provide some form
of semantic
search results (05)
The "Final Conclusion":
We have made progress in getting SRA to answer physicians‘ ad hoc
queries about patient data orders of magnitude faster than what had
been "best practices", but there is much room for, and many
different directions for, future improvement and wider application. (06)
> After decades,
> the simple blocks world built by Terry Winograd remains the only well
> known
> example, and even that one is considered woefully inadequate for real use.
> I would like to know what is missing in the present spectrum of approaches
> to NLP, but I haven't yet been able to get a full read on it.
>
> Suggestions about what is missing would be appreciated.
>
> -Rich
>
> Sincerely,
> Rich Cooper
> EnglishLogicKernel.com
> Rich AT EnglishLogicKernel DOT com
> 9 4 9 \ 5 2 5 - 5 7 1 2
>
> -----Original Message-----
> From: ontolog-forum-bounces@xxxxxxxxxxxxxxxx
> [mailto:ontolog-forum-bounces@xxxxxxxxxxxxxxxx] On Behalf Of doug foxvog
> Sent: Saturday, November 06, 2010 8:22 PM
> To: ontolog-forum@xxxxxxxxxxxxxxxx
> Subject: Re: [ontolog-forum] Polysemy and Subjectivity in Ontolgies - the
> HDBIexample
>
> On 11/6/2010 12:44 PM, Rich Cooper wrote:
>> That supports my point that the individuals interpret even very common
>> words differently, and therefore an ontology based on language that is
>> understood differently by each subject. The probability of a monosemous
>> ontology is therefore very low, IMHO.
>
> An ontology certainly needs to be based on more than the names of the
> terms, in fact, more than language. Properties and rules should clarify
> differences between different senses of words.
>
> Contexts should also be defined, such that different rules apply in
> different contexts.
>
> -- doug (07)
=============================================================
doug foxvog doug@xxxxxxxxxx http://ProgressiveAustin.org (08)
"I speak as an American to the leaders of my own nation. The great
initiative in this war is ours. The initiative to stop it must be ours."
- Dr. Martin Luther King Jr.
============================================================= (09)
_________________________________________________________________
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
To Post: mailto:ontolog-forum@xxxxxxxxxxxxxxxx (010)
|