Learning to Model and Ignore Dataset Bias with Mixed Capacity Ensembles
EMNLP, pp. 3031-3045, 2020.
Many datasets have been shown to contain incidental correlations created by idiosyncrasies in the data collection process. For example, sentence entailment datasets can have spurious word-class correlations if nearly all contradiction sentences contain the word "not", and image recognition datasets can have tell-tale object-background c...More
PPT (Upload PPT)