To: | Neil Raden <nraden@xxxxxxxxx> |
---|---|
Cc: | Tony Shaw <anthonypetershaw@xxxxxxxxx>, "[ontolog-forum]" <ontolog-forum@xxxxxxxxxxxxxxxx>, dm-discuss@xxxxxxxxxxxxxxx |
From: | Adrian Walker <adriandwalker@xxxxxxxxx> |
Date: | Tue, 2 Jun 2009 21:08:42 -0400 |
Message-id: | <1e89d6a40906021808m65c17801h4d788974a74a4d84@xxxxxxxxxxxxxx> |
Hi Neil -- Nice review of Wolfram|Alpha. You wrote... Because 'context' in WolframAlpha is limited to the equations (I'm using the term 'equations' loosely) of a particular knowledge domain, the meaning of a term can change depending on how it is used, giving you completely wrong answers, with no warning that they are wrong. All of this is enough to make a data governance geek cringe. The only thing worse than being wrong is being wrong and believing you are right, and acting on it. A key technical problem would seem to be how to prevent the system from answering questions it does not understand. In the system online at the site below, we tackle this by having an end-user-extensible set of '' base" question sentences that the system knows how to answer. On receiving a free English question, the system uses conventional IR to present a ranked selection of base question sentences to the user. The user picks a base sentence from the list and asks the question. The system can then produce a step-by-step English explanation of the answer. Of course, the user may decide that nothing in the ranked selection captures the intent of his question. He can then edit the underlying knowledge (in open vocabulary English, live in the browser) to add a base question sentence. Without solving the "AI-complete" natural language understanding problem, does anything better come to mind? Cheers, -- Adrian Internet Business Logic A Wiki and SOA Endpoint for Executable Open Vocabulary English over SQL and RDF Online at www.reengineeringllc.com Shared use is free Adrian Walker Reengineering Phone: USA 860 830 2085 _________________________________________________________________ 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 (01) |
<Prev in Thread] | Current Thread | [Next in Thread> |
---|---|---|
|
Previous by Date: | Re: [ontolog-forum] IKL mailing list for discussions?, Richard H. McCullough |
---|---|
Next by Date: | Re: [ontolog-forum] Guo's word senses and Foundational Ontologies, John F. Sowa |
Previous by Thread: | [ontolog-forum] Common Logic and decimal numerals, Jawit Kien |
Next by Thread: | Re: [ontolog-forum] Wolfram|Alpha and NL QA, Duane Nickull |
Indexes: | [Date] [Thread] [Top] [All Lists] |