Tweeted By @stanfordnlp

Guessing is for fakers: At #acl2020nlp, Selective Question Answering under Domain Shift by Amita Kamath, @robinomial & @percyliang examine how you can get a QA model to abstain from answering when it doesn’t know the answer by using a calibrator https://t.co/xdbVzjdr0r #NLProc pic.twitter.com/6sLTeToLIA

— Stanford NLP Group (@stanfordnlp) June 29, 2020