To: | "[ontolog-forum]" <ontolog-forum@xxxxxxxxxxxxxxxx> |
---|---|
From: | sowa@xxxxxxxxxxx |
Date: | Thu, 21 Mar 2013 01:42:16 -0400 (EDT) |
Message-id: | <b689419713f34aa49dac7ce113c68ef5.squirrel@xxxxxxxxxxxxxxxxxxxx> |
Ed, The issues about how people interpret NLs and how they use
CNLs are very complex and highly context dependent. The issues cannot be
summarized in a short explanation that covers all possibilities. No. I said that the responses that they would generate in any CNL would agree about 50% of the time. It's not clear what the source of the error might be -- their interpretation of the original text, their use of CNL to express themselves, or some combination of both. In any case, my estimate of 50% is based on various studies, and those studies showed a high variability. But all of the studies show that inter-annotator agreement is usually disappointingly low. That is why I believe that software that analyzes the original NL can do as well or better than software that depends on what some human annotator wrote about the original NL. (Of course, I am assuming that the NLP software is as intelligent as the software produced by VivoMind Research, LLC.) > The view that my project takes is that restricted NL is
written by That is a way of using controlled NLs that has been fairly successful. I would agree that it's a good way to go. But note that (a) the authors are highly trained and (b) they use tools that provide an *echo* to the author for verification. >
You might be amused to know that the aerospace industry developed a Yes. I'm aware of that work, and I believe it's a good way to go for that purpose. But it is a different purpose. John _________________________________________________________________ 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 (01) |
Previous by Date: | Re: [ontolog-forum] Fwd: MOVED: Re: [ontology-summit] Hackathon: BACnet Ontology, Barkmeyer, Edward J |
---|---|
Next by Date: | Re: [ontolog-forum] Fwd: MOVED: Re: [ontology-summit] Hackathon: BACnet Ontology, Steven Ericsson-Zenith |
Previous by Thread: | Re: [ontolog-forum] Fwd: MOVED: Re: [ontology-summit] Hackathon: BACnet Ontology, Barkmeyer, Edward J |
Next by Thread: | Re: [ontolog-forum] Fwd: MOVED: Re: [ontology-summit] Hackathon: BACnet Ontology, Steven Ericsson-Zenith |
Indexes: | [Date] [Thread] [Top] [All Lists] |