Attribute-controlled translation (ACT) is a subtask of machine translati...
Naturally-occurring information-seeking questions often contain question...
It is well documented that NLP models learn social biases present in the...
Recent years have seen numerous NLP datasets introduced to evaluate the
...
Intermediate-task training has been shown to substantially improve pretr...
While pretrained models such as BERT have shown large gains across natur...
We introduce jiant, an open source toolkit for conducting multitask and
...
We investigate the extent to which individual attention heads in pretrai...
Many (but not all) approaches self-qualifying as "meta-learning" in deep...
Latent tree learning(LTL) methods learn to parse sentences using only
in...
Though state-of-the-art sentence representation models can perform tasks...
In recent years, sequence-to-sequence models have been very effective fo...
A substantial thread of recent work on latent tree learning has attempte...
In recent years, there have been amazing advances in deep learning metho...