Re:Rover: Reasoning over Rules
by asacalowww on Monday February 17, 2020 @02:32PM
(#22350002)
Mm don't think so. It's a non-monotonic statement, in that given Tweety is a bird, and therefore might also be a penguin then it can't make an assertion either way as to whether Tweety can fly or not. Non-monotonic reasoning is especially useful in many real world scenarios where a derived logic system doesn't have tidy yes/no answers throughout.
[ Parent
| on HN ]
Re:Rover: Reasoning over Rules
by YeGoblynQueenne on Tuesday February 18, 2020 @07:22AM
(#22355414)
The funny thing is that they report results on some hand-crafted examples of reasoning over Birds flying or not, (by Marek Sergot from Imperial) and they have a little table where all the language models perform almost perfectly.
And yet, as you have found, they do not. Or perhaps- they do, but you have to run the same experiment a few thousand times (it's a tiny dataset of five clauses or so) until you get the good results, eh?
I'm just being a big old meanie now.