How Does Data Corruption Affect Natural Language Understanding Models? A Study on GLUE datasets. (arXiv:2201.04467v1 [cs.CL])

A central question in natural language understanding (NLU) research is
whether high performance demonstrates the models' strong reasoning
capabilities. We present an extensive series of controlled experiments where
pre-trained language models are exposed to data that have undergone specific
corruption transformations. The transformations involve removing instances of
specific word classes and often lead to non-sensical sentences. Our results
show that performance remains high for most GLUE tasks when the models are
fine-tuned or tested on corrupted data, suggesting that the …

arxiv data datasets language natural natural language study