.@YejinChoinka is right about this. are there other models that do better?
(serious question, not a rhetorical question.)https://twitter.com/YejinChoinka/status/1188310808008130561 …
-
Yes,
COMET by @ABosselut et al. Demo: https://mosaickg.apps.allenai.org Paper: https://arxiv.org/abs/1906.05317 It's not perfect, but it's better than anything out there. I dare say that my speculation is that one can't do better with entirely non-neural methods.
i don’t actually see how to directly apply comet to these, but am interested to hear more and was just reading about it:pic.twitter.com/23klv9X7Dl
-
-
more generally i am working on a set of problems to test whether a system can understand consequences in connected sentences. can comet be tested on such a thing? how?
-
sorry
@GaryMarcus, one can't solve AI (or more narrowly, commonsense AI) in one paper. One step at a time... but i know some folks are investigating that question based on COMET. it's an exciting time where we have so many ideas yet to explore!
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.