research
∙
11/16/2021
Adversarially Constructed Evaluation Sets Are More Challenging, but May Not Be Fair
More capable language models increasingly saturate existing task benchma...
share
research
∙
09/14/2021
Types of Out-of-Distribution Texts and How to Detect Them
Despite agreement on the importance of detecting out-of-distribution (OO...
research
∙
06/01/2021
Comparing Test Sets with Item Response Theory
Recent years have seen numerous NLP datasets introduced to evaluate the ...
research
∙
04/15/2021
Does Putting a Linguist in the Loop Improve NLU Data Collection?
Many crowdsourced NLP datasets contain systematic gaps and biases that a...
research
∙
10/09/2020
Counterfactually-Augmented SNLI Training Data Does Not Yield Better Generalization Than Unaugmented Data
A growing body of work shows that models exploit annotation artifacts to...
research
∙
10/08/2020