6 datasets found

The dataset used in the paper for testing the proposed squared curvature regularization approach.

The Enwik8 dataset is a large-scale language modeling dataset.

The Penn Treebank Character dataset is a character-level language modeling dataset.

Highly regularized LSTMs achieve impressive results on several benchmark datasets in language modeling. We propose a new regularization method based on decoding the last token...

Mixup as a regularizer can surprisingly improve accuracy and out distribution robustness.

The Penn Treebank dataset contains one million words of 1989 Wall Street Journal material annotated in Treebank II style, with 42k sentences of varying lengths.