Reviewers argued that different questions require distinct systems and that treating them as the same would not help solve problems.

“they say no all these questions require very different systems to answer and trying to pretend they are the same doesn't help anyone solve any problems that's what it says right there right that's how hard it was to fathom and now of course people when i say oh we're inventing problems people like you can't even invent problems it's such an obvious idea to have one neural network that of course does everything in nlp but at the time it was like extremely controversial and the paper got rejected”