Predicting when ML models fail in productionTo Annotate or Not? Predicting Performance Drop under Domain Shift. An #EMNLP2019 paper by Hady Elsahar and Matthias GalleOct 30, 2019Oct 30, 2019
How do you manage your Machine Learning Experiments?“Every experiment is sacred Every experiment is great If an experiment is wasted God gets quite irate” ~SacredAug 4, 20197Aug 4, 20197
Writing code for Natural language processing Research #EMNLP2018 #NLProc“Code is available upon request”, “Author promise ..”, a repo that only contains model.py? we all know... no need to explain further.Nov 5, 20182Nov 5, 20182
Copy Actions for Neural Text Generation: choose your words carefullyCopying, Pointing and Placeholders are terms that have been popping up in NLP papers since 2015 in Neural Machine Translation (NMT) and…Dec 28, 2017Dec 28, 2017