Going on with the #NLProc peer review debate!

The most thorny issue so far: should *ACL should require resource papers to have some proof-of-concept application?

* FOR: no ML experiments => go to LREC
* AGAINST: super-new methodology/ high-impact data could suffice

Your take?

I would *love* to hear more from both sides, especially FOR - maybe this is all just disgruntled linguists rant?
Summary of the arguments so far:

* FOR: NLP now means "deep learning"
* AGAINST: hurts cross-disciplinariness, discourages data work by requiring even more effort