f4f2f2b3c67da711df6df557fc870c4a-Paper-Conference.pdf

We find that the inconsistency between training and inference of BN is the leading cause that results in the failure of BN in NLP. We define Training Inference Discrepancy (TID) to quantitatively measure this inconsistencyand reveal that TID can indicate BN'sperformance, supported by extensiveexperiments,includingimageclassification,neuralmachinetranslation, language modeling, sequence labeling, andtextclassification tasks.