Description | Parameters | Dataset | Model and Test set(s) |
---|---|---|---|
Adaptive Inputs (Baevski and Auli, 2018) |
1026M | Google Billion Words | download (.tar.bz2) |
Adaptive Inputs (Baevski and Auli, 2018) |
247M | WikiText-103 | download (.tar.bz2) |
See the language modeling README for instructions on reproducing results for WikiText-103
using the transformer_lm_wiki103
model architecture.
@inproceedings{
baevski2018adaptive,
title={Adaptive Input Representations for Neural Language Modeling},
author={Alexei Baevski and Michael Auli},
booktitle={International Conference on Learning Representations},
year={2019},
url={https://openreview.net/forum?id=ByxZX20qFQ},
}