seems manifold surgery, pulling back to higher space and seeking local assignments to make global section of sheaf
terrific new benchmark from @YejinChoinka lab that does indeed appear to get at the challenge I have been raising, re getting AI systems to understand how events unfold over time.https://twitter.com/YejinChoinka/status/1190840264589398016 …
The
TimeTraveldataset of our #EMNLP2019 paper, 
Counterfactual Story Reasoning and Generation (https://arxiv.org/abs/1909.04076 ) tests counterfactual reasoning over events that unfold over time, directly addressing @GaryMarcus's call for a challenge against current neural models.... https://twitter.com/GaryMarcus/status/1189022077853958145 … pic.twitter.com/bWDbRAjLPg
TimeTraveldataset of our Counterfactual Story Reasoning and Generation (https://arxiv.org/abs/1909.04076 ) tests counterfactual reasoning over events that unfold over time, directly addressing
Show this thread
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
There is a reason that the brain's sensors convert all stimuli to precisely timed spikes but I'm sure you have a hybrid GOFAI/DL solution hidden somewhere that will knock everybody's socks off. Real soon now.
- 1 more reply
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.