Bingo. So many people think they can do NLU (or robotics, or even driving) without having a commonsense knowledge database, and I just don’t see how that’s remotely possible.https://twitter.com/punkstrategy/status/1071560512662515712 …
-
operations on identifiable entities to underpin "true" NLU. Assuming I understand you, why couldn't instead that logic occur as learned NN transformations on embedded representations of concepts and entities? It may require an order of magnitude more training data /2
see the argument i made in chapter 3 of algebraic mind re training space, encoded in Bengio’s recent baby paper. you won’t get enough data.